Zeta Global Holdings Corp - Ordinary Shares - Class A Aktie

Are we ready to go?

Yes.

Yes, we're live. Okay. So David, Chris, thanks you for joining us. I'm Ron Josey, covering the Internet sector here at Citi. And look, I had a ton of questions prepared for this, and there's late-breaking news for -- really for company. So David, why don't you take the stage and tell us what was announced?

This morning at 7:00 a.m., we announced we're fully integrating our platform with Palantir, and we're signing -- we signed a 7-year joint go-to-market strategy where we will be marketing to the vast majority of their customers. Putting our data cloud on top of Foundry is going to speed it up dramatically as it relates to data ingestation from our existing and new clients, and it's going to allow our algorithms to train even faster. We've built a joint forward deploy engineering team where we have one, they have one. And as we go to market, this is really one of the biggest pivots we've ever made as we move the company from what is a marketing technology company to what is really an AI infrastructure company.

If you think of our business, for those of you who don't know, we are a very large marketing -- I shouldn't say very large to this group. But as it relates to marketing platforms, we have a marketing platform, and we have a data cloud. Today, 51% of the Fortune 100 and 24% of the Fortune 500 use our platform to better manage customer acquisition, customer retention and customer monetization. We do that through what's called the Zeta marketing platform and through the Zeta Data Cloud.

In 2017, we made the decision to totally throw out our old platforms, when we ran them for cash flow, and we've created an entirely new platform that in 2021, we made Live which is the only marketing cloud that has data and artificial intelligence as native to the application layer. It's literally foundational. And when people tell me they hear this in every meeting they go to, I suggest they go back 5-plus years ago when we went public. We put a big sign on the side of the New York Stock Exchange that data plus AI equals intent. Everybody was asking me "who's Al? And why is he in charge of your data strategy?" But we've been doing this for a very long time.

Today, one of the biggest and most powerful statements about our platform is for every dollar that's spent on our marketing platform, we return an average of 600% to 700% return on marketing spent. That's an independent study that was done by Forrester. Our goal is to get that to 1,000%, an order of magnitude return for every dollar that's spent. And everything we do as a company is to try to get there.

A few months ago, we launched Athena, which is our voice-enabled super agent. If you think about enterprise software and not just us, any enterprise software company. I always make the joke about the Bloomberg terminal. What percentage of your Bloomberg terminals features and functions do you use on a regular basis? The vast majority of enterprise software people use between 5% and 10% of capabilities.

Athena you're no longer navigating a complex platform. You're going to Athena and simply saying I would like to create 2 million incremental customers this quarter, and I'd like to do it by lowering my average expense by about 7%. Athena will then access every feature, every function in every data set to come up with the best possible outcome. It will then change the user interface to show you the results. You can then say to Athena, amazing. That's a little big for me. I don't want to start with that. I'd like to do a test. Can you activate the test? And every hour sending an e-mail so I can keep track of the return on marketing spend per hour.

When you look at taking the Zeta Data Cloud and Athena and putting her on top of Foundry, which is Palantir's platform, it's going to massively speed her up. That speed every time we can remove incremental latency, we can return substantially higher return on marketing spend. And also the credibility that comes from partnering with Palantir and going to market, we think, is going to be a game changer for us as a company.

David, talk to us about how this came about, working with Palantir. We've been talking about Athena now for some quarters. We just launched not too long ago, and now we have a pretty big partnership here. So talk to us about the genesis of this and sort of where -- how you were thinking and when this came about.

Well, we'll try to get this going here, so I don't die. For those of you on the webcast, it is hot. So we are doing this as a web webcast from a Reg FD perspective because we literally just announced the Palantir relationship.

So listen, we've been building our business in a way that we've always really looked up to Palantir. We've always thought they were the type of company we would like to aspire to be.

So I was originally introduced to the CEO of Palantir through a very close mutual friend. We started talking and working together. And then I got to know Elias, who works directly with Alex. And the synergies just became so clear. Like if you look at what Alex said in the press release we put out, and I'll paraphrase here, Palantir plus Zeta should change the entire marketing landscape.

And when you think about it, Palantir's entire strategy, I mean it's -- I shouldn't sum it up to their entire strategy, but one of their biggest selling points to their client is we can help you meaningfully lower your cost and be more efficient with your business. Zeta is the best platform in the world for managing and lowering marketing and CRM expense. We're usually able to lower our clients' expenses anywhere from 50% to 75% on marketing or CRM expense.

I don't know if you saw yesterday, Ron, but Gap announced they were throwing 4 vendors out and replacing all 4 with Zeta as the system of record for Gap. That's the type of deals that we're winning at this point and you put Foundry underneath it. It's game changing. One of the interesting things about the Gap deal was we had bid the Gap RFP three times and come in second three times. And I was like, do we really need to waste our time with this again? And I ended up getting introduced to their CEO. And I said, "Listen, we're probably not going to bid it this year. You guys seem great". But they've been with Salesforce. I mean, they were a Salesforce shop forever. And he said, "bid it, just bid it".

We came in, we bid the RFP. Halfway through the RFP, Athena became generally available. So we went in and we did a full demo in the middle of the RFP process of Athena, the voice agent. And the next day, they asked us for pricing. So you start to look at Athena and where she is going in the marketplace, in partnership with Palantir and where they are in the marketplace.

This will be our fourth year of greater than 30% compounded organic top line growth and greater than 50% compounded organic EBITDA growth. And I think that Athena in partnership with Palantir is going to make us a 20-plus percent organic grower for many, many years to come.

That's a great segue. I think there were some dollar amounts maybe in the press release. Chris, talk to us about how you see the partnership. Obviously, David, just put some numbers and growth rates around there, but talk to us more about the dollar amounts, but then I want to get into execution too. So let's talk dollar amounts and then executions.

Yes. So I'll ladder down from our Zeta 2028 plan, which is to get to at least $2.3 billion by 2028. I'll remind investors that we got to our first long-term model to get to at least $1 billion a year early. Integral to the current long-term model we're operating in is partnership expansion. We've announced a number of partnerships over the last several months, this being the biggest inner history. But those partnerships being a vehicle to not just get to that longer model, but to get to there faster.

David had mentioned in the press release, we see this becoming at least $100 million business over the years to come annually, and there's joint selling incentives and partnership to drive that type of outcome.

So let's talk about the process to get there then and dollars will be dollars, but talk to us about -- we just had the announcement, Athena is 3 months old?

Yes. It's crazy.

So it seems like quite a catalyst and then we just talked about Gap. But David, talk us through the implementation process from here on out. What can we look forward?

So one of the big questions that -- I mean, I've been asked in the last hour. So it's not like I could say we've been doing this for a long time at this point was, is this going to mean to a meaningful increment in expense this year? The answer is no. In fact, we were able to move budget from other providers, to Palantir to have it being neutral this year, and we think this will help us lower operating expenses further starting next year and out.

Based on -- we've been obviously building this for quite some time. We're announcing it today. But I think we will have this live by the end of the third quarter of this year. And we're targeting even sooner than that. And we've already really, at a very high level, started identifying customers we want to jointly go to. And I think the joint go-to-market strategy is going to be a real game changer for us.

The other thing that's really important to note is when we turn it on. Our existing as of the end of Q1, 189 superscaled customers will all benefit that day. The speed in gestation, the model the model is speeding up, Athena's capabilities speeding up will all be available to every client.

That's great. That's fascinating. As we think about that scaling up I wanted to ask a little bit more just, I think you said, David, when we first started this webcast, speed will drive greater usage of Athena. And we just talked about OpEx may be going down with the scale.

Speed drives greater return on marketing spend, which drives greater spend on our platform.

So talk to us about the speed aspect of this.

So right now, we are probably the fastest you can get out there in marketing because we're the only one that AI is native to our application layer. Everybody else has to step out of their platform through an API to an algorithm to do a query, then the algorithm steps through another API to a data repository to draw data back to the algorithm to create intelligence and then it informs the platform what to do. That latency destroys return on marketing spend.

By adding Foundry underneath and replacing other infrastructure we've used in the past, we're going to even meaningfully speed up our ability to process data. And that will allow our algorithms to train faster. We're already seeing -- for those of you who don't know, Athena went live in March, and then on Thursday, we announced Athena for agencies. So now it's available to 100% of our total client base.

We're already seeing clients who are using Athena spending more on our platform and showing meaningfully higher than a 600% return on marketing spend. We think that Foundry's addition to that is going to supercharge that even further.

To that 10x goal...

The goal is to get 10x. I'm not saying we're there or I'm not saying we're not there.

It's a path to get there.

Yes. What I would say is we have some clients who are there, and we're trying to get that there.

So we can take questions from the audience. If there's any questions, I've got one in the back. I'll just repeat it, if you want to say.

Really exciting announcement this morning. May be a little bit more on the specifics of the Palantir deal. I assume you are now becoming a customer. Can you talk about how much you're going to be spending with Palantir? Can you say it's built on Foundry. Is there some sort of like OEM rev share [ premium ] for Palantir? Obviously, a really sophisticated data intelligence platform [indiscernible] to...

We're aware. And you're a client of ours.

What exactly [indiscernible]...

Well, so first of all, I cannot...

If you could repeat the question for the [indiscernible].

How much are we spending with Palantir? And is there a rev share? Or how does the joint go-to-market work? Let me start by saying, we're not going to disclose how much it is, what I will tell you is it is neutral to Zeta's guidance from an expense perspective for this calendar year, and we expect it to lower our expenses going into next year on. So this won't be like, Oh, you'll get surprised by expense creep or picking up; B, we are both heavily financially incentivized to jointly sell this product together, to be clear.

Palantir's strategy, and it's hard for me to say this with a Elias sitting here, but Palantir's strategy is always to help clients with cost and efficiency. Today, and I think one of the things Elias really liked about it, I know one of the things Alex really liked about it is you've got a $1 trillion TAM that's effectively opening up to the Palantir-Zeta partnership that we can go in together as partners and say to their enterprise clients, we can help you meaningfully lower one of your largest cost as an enterprise, while simultaneously increasing quality.

So the answer to your first question is it's neutral to lower. The answer to your second question is, yes.

Maybe to that, but let's take a step back and talk about Athena because it all sort of comes together here but we're 3.5 months in. Maybe David, just what surprised you the most about this platform? And you talked about the client win yesterday that was announced. What has changed, I guess, right? #2 to #1.

It's funny. So honestly, I -- and we're a big company at this point. I don't invent most things. I happen to invent Athena. It was something that I came up with last April. We were able to go from the day we decided to build this to generally available with Athena within 9 months. Within 90 days of that, we rolled out an entirely new platform for Athena for agencies. If you look at Zeta in the first quarter of 2026, we announced that by using our internal workflow management tool, SPADE, we generated 75% of all of our new code on an automated basis.

The goal with Athena is to become a full operating system and to truly become the infrastructure that artificial intelligence for our clients. The Palantir deal is mission-critical to that.

Now to actually answer the question you want me to answer instead of the question I want to answer. The thing that surprised me the most is the reaction from people because I've been so intimately involved in the creation of what we call the birth of Athena, you see the little steps every day, it gets better. And all of a sudden, somebody sees it for the first time.

Winnie and I did a demo for somebody yesterday, CMO of a very large company. And he was literally like this is the greatest thing I've ever seen. He's like, this blows me away. And I was like, great, you should move all your budget to us. And of course, he started laughing. But we'll start with the test and we'll move up from there. But human reaction to Athena is the thing that surprised me. What didn't surprise me is people who are adopting it are spending far more on the platform and enterprise clients that are adopting it are showing amongst the best return on marketing spend we've ever seen. But that didn't surprise me.

And we've left 10 minutes in this fireside for Winnie to do a demo for your team.

Are we at that level now?

I think we have until 5 after, but just know that we've got that ready to be queue now.

Winnie is going to do a demo of Athena so you guys can get a little taste of what she looks like.

So we've got maybe 5 more minutes of Q&A.

That gives us 12.

12 minutes of Q&A. Okay, great. So maybe last one on Athena. I believe, what was interesting is that I think every beta customer became a multi-use customer when you were doing it. And so I -- what we're trying to understand is how adoption goes forward and monetization of Athena? And I might have this wrong, are we monetizing Athena now? Or where are we on?

We we're monetizing Athena every moment of every day. I mean the way Athena works is instead of charging a modular fee for her. We are letting clients use her as a tool inside of the platform.

Let me give you some interesting statistics. A number of years ago, we rolled out our first ever voice interface. It was called ZOE. And clients who adopted ZOE spent between 300% and 350% more on our platform than clients that didn't adopt ZOE.

Now I'm not suggesting all of our clients to adopt Athena, we're going to grow by 350%. But what I am suggesting is clients who utilize her are not just spending far more money in utilization fees, but they're using multiple use cases. So for those of you who don't know our business that well, we have three main use cases, and it's pretty simple, customer acquisition, customer retention, customer monetization.

For the end of -- for companies?

For enterprises and agencies. Yes. Although 80% of our revenue is direct to enterprise, about 20% is agency. Those are round figures. Bottom line, what we found was clients who use multiple use cases, and we were pretty siloed for a while because we were selling that way. We've now broken through the silos. And when customers use multiple use cases instead of one, the data trains the algorithms substantially more effectively. So the data that informs customer acquisition further informs retention, which further informs monetization, which further informs acquisition.

We're seeing a massive uplift in return on marketing spend for clients who adopt multiple use cases. We call it, as you know, Ron, One Zeta. And then last year, we hired a gentleman named Ed See. Ed was the Head of McKinsey's global CMO practice. So we stole that away from McKinsey to become the head of -- we call him Chief One Zeta Officer. I think his technical title as Chief Growth Officer.

But with Athena, Athena does the cross-selling automatically. So if you're using a use case around customer acquisition, you might say, "Athena, I'd like to drive 2 million incremental customers this quarter. I'd like to do it in an average of 7% savings on a cost to create a customer". Athena will walk you through that whole process at the end of the activation. So you'll say, "please activate that".

Athena will then say, by the way, do you know that I've identified 700,000 of your existing customers who are in process of churning off your platform to your competitors' products? Would you like to save them? And it automatically creates a loop into the One Zeta. So that's why we're seeing with Athena, a meaningful uptick in One Zeta clients. What was the growth in One Zeta clients in the first quarter?

Well, we didn't -- growth in multi-use case, which would be One Zeta was 50% year-over-year.

So 50%.

And to that 50%, maybe we can talk a little bit about the sales pipeline, which I think was up 40% year-over-year in the last quarter. So as we sort of migrate from big news today to Athena's live, and we're seeing results and wins and everything to implementing sort of the go-to-market and everything else in the company, pipeline was up 40%.

So talk to us just about how you view the pipeline going forward. We'd love to have some insights on conversion rates, if that's possible. Anything that can help us better understand that pipeline number and metric?

Yes. Our -- as you said, our pipeline is up, and that's our model, frankly. We have quarters where it's up 30%, 40%, 50%, 60%. This was indicative of what we've been seeing. We'll often get the question from investors, how is the market reacting to a tougher macro or choppier macro times. When we look at our sales pipeline and specifically the industries that are closest to consumer discretionary wallet, they are our fastest growing industries, growing even north of 40%. Athena...

And I think that's because we're a cost savings, right? So when things get choppy, clients actually grow with us. I'm sorry, I [indiscernible].

Yes. No, and they become far more data-driven. What we've also found while the longer-term benefit of Athena is higher ARPU or higher usage, which then translate to revenue. What we're seeing at the top of the funnel, Ron is better conversion. So it is an accelerant to the sales process. As David mentioned, with the Gap, but with many other enterprises, putting Athena as a demo at the very first step of the sales process, which is probably a good jumping off point for Winnie, is a conversion factor that is allowing us to accelerate time to close.

If we've got -- so great, we've got 10 minutes left. 11 minutes left.

You could probably go 5 minutes longer because we started late.

Maybe we can ask if there's any audience questions before we get to Winnie. If not, we'll go to demo. We have one in the back.

Have you guys disclosed or talked about like how we should think about the impacts to gross margins like the economics of the relationship? Should this show up even in your numbers like -- or is it something that will only show up once customers start using it? Like any kind of [indiscernible]?

Yes. I think -- I mean, as we're going to get it live next quarter. It's not currently in our projections at all for this year. So it could be potential upside, maybe, maybe not. Next year, I think it's going to be very additive to top line revenue and the revenue should come in at a very comparable gross margin to our other gross margins. Maybe slightly higher for a few reasons, but it will not contract.

It will be -- it will aid at a lower OpEx, as David mentioned. We'll get synergies off of it, which then translates to better free cash flow and adjusted EBITDA margins year-over-year.

All right. Well, with that, thank you for the questions. Maybe Winnie, you take it away?

Great. Thanks, guys. We're going to switch over to our demo and showcase. I'll be navigating on my laptop at the same time. So I'm Winnie Shen, EVP of our Data Cloud. We've been doing a ton of these demos here at Cannes, as Das mentioned, some really great resonance with our clients.

So our Zeta Marketing Platform is where our entire ecosystem lives in terms of Athena as an operating system, where our data is, where all of our activation capabilities are all of our intelligence, all housed within this one platform. So we're going to transition over to our platform.

And before we get started, what I'm going to walk you guys through is, first, how do we glean intelligence from all the massive amount of data that we have. We have the ability to reach about 245 million people in the U.S., 586 million globally. We enrich those profiles with thousands of attributes and signals. We then transform that massive amount of data into intelligence. And from there, once we've unlocked opportunities, we then want to determine how do we activate off of it, how do we optimize it, how do we find the right creates and then measure all of it.

So I'm going to actually take you through that entire flow. Athena will pick up all the noise in the background. So I'll try to mute us and I'll pause and try to explain some of what's happening in the background as I ask Athena questions. I'm going to do this from the lens of travel since we've all traveled here today, we thought that would be a good use case. I'm going to do it from the lens of United Airlines just so that it makes it more real. None of the data I'm showing you today is any customer data. We're just using it as an example to help showcase some of the capabilities. So with that, let me get Athena started.

So for those of you who don't know, while we're setting it up, today, our proprietary data cloud has 550 million people globally opted into it, 245 million Americans, which -- with an average of 5,000 to 7,000 data elements per person, which includes demographic, psychographic, transactional, credit score, behaviors across 5.2 million publishers that have embedded our technology as a first-party component of their tech stack.

So we're feeding in trillions of marketing signals on a daily basis to power everything she's about to show you. All of this data is 100% proprietary and has never been shared with a large language model ever nor will it. We do not sell our data to anybody at any price at any time. We simply use our data to train our own proprietary models. And we've been doing that since we founded the data cloud and rolled out our AI many, many, many years ago. Sorry, Winnie.

No. Perfect set up.

Hi, Athena, can you take me to the application that looks at always-on intelligence, and I want to look at comparisons in online travel destination research comparing United Airlines intenders versus visitors versus transactors.

[AI Agent - Athena]

Among United Airlines intenders, online travel research leans heavily into broad destination inspiration, such as United States and North America travel, regional travel, family and seasonal travel plus big dream categories, cruises, national parks, theme parks and Europe-Caribbean trips. United Airlines visitors show more research around specific U.S. leisure hubs and short call getaways, e.g. Florida, California, Texas, Las Vegas, Orlando, New York, San Diego, Palm Springs, indicating strong interest in domestic vacations and repeatable fly to Sun destinations.

United Airlines transactors are more skewed towards practical trip enablement and concrete planning with higher relative focus on hotel reservations and mid-scale lifestyle hotels, car rentals and ridesharing, vacation packages and deals and travel services content like TravelAdvisor and TripAdvisor. Intenders over-index more than visitors and transactors on long-haul international inspiration, e.g. Australia, Africa, France, Italy, Spain, Greece, Portugal, Brazil, Caribbean, Indian Ocean and on aspirational experiences such as private jet travel and luxury hotels.

So this first part, she basically has compared 3 different reports all in one conversation. That meeting Das referred to, the reaction was, that was just a day's worth of work that we just compacted into a few minutes. Athena just tend to go a little bit. But basically, she's looked at people that are reading about traveling to United versus people that are visiting their actual terminals versus people that are spending with them.

She's identified the differences amongst them and identified an opportunity with the international travel. You'll notice that Spain -- you guys probably can't see. I will just tell you about it. So from the people in the back of the room, you'll see that Spain travel actually indexes high for intenders. We don't see that with the current people that are actually with United. So I want to pull that forward and see where does that ranking happen in our generative engine optimization. So I'm going to push it forward.

Okay, Athena, that's a great opportunity on the international side. Can we go GEO and see how does United rank on questions related to the best international travel brands?

[AI Agent - Athena]

United is the #1 brand in the entire network. On the generic international long-haul overseas prop specifically, it is mentioned in 100% of them. Its average share of voice is regularly the highest in the answer pool. It owns the broad best U.S. airline for international travel territory, beating American and Delta on most network reach and reliability prompts. For example, United ranked #1 for share of voice for one airline for all international trips, best long-haul international and wide international route networks.

Well, how does United compare when it comes to Spain travel?

[AI Agent - Athena]

On the 20 Spain, Madrid, Barcelona prompts, United strength evaporates. United is still mentioned in nearly 100% of responses, so it's not invisible, but it rates #1 on 0 of them. It's its third or fourth place in almost every case. United's average SOV is well behind the leaders. Iberia dominates Spain. The Spanish flight carrier leads around 15 of the 20 prompts hitting 61% to 70% SOV on the strongest. And American is usually ahead of United too.

American wins the most nonstop to Spain prompts, thanks to its Iberia oneworld joint venture. United's best Spain showings are only #2, Barcelona and Honeymoon to Barcelona. Overall, United is the category leader for international flags generally, but on Spain corridor, it's a clear laggard, consistently third or force behind Iberia and American.

So what we're seeing our Generative Engine Optimization is that we can hypothesize the type of questions people are asking in LLMs because we see such a massive amount across the open web.

So for those of you guys who don't know what GEO is, it's actually the ability to read the output from the large language models. So this is data coming right out of direct integrations we have with OpenAI, Anthropic and Gemini.

So one of the things our clients this year are really interested in is how are they doing in the large language models. And that's what this platform is showing you. It could just as easily show you this through any other methodology and we have already announced that we're able to serve ads into OpenAI.

So I actually think we're the only platform in the world now that matches to the MetaID, we match to the OpenAI ID, we match to the Palantir ID, the open web, connected TV, messaging, so on and so forth. But GEO is the hottest thing our clients are talking about right now and where they're investing, our GEO business is one of our fastest-growing businesses inside the company.

Exactly. It's been very powerful for us as a unique opportunity with our capabilities and innovation. And from here, I want to then understand, okay, with current travelers, are they actually interested in traveling to Spain? Or is this white space for me with acquiring net new customers? So I'm going to continue the conversation.

All right, Athena. So I want to check in leading indicators for my United visitors if they are actually researching about Spain or no.

[AI Agent - Athena]

Within this United visitor audience, interest in Spain travel itself is not surfaced as a top direct leading indicator signal. So Spain-specific intent is not present versus other destinations. Destination-wise, Europe hubs like France Travel and Italy travel are showing more pronounced steady growth as leading indicators, suggesting European near-term trip planning is prevalent yet country-specific.

Broader vacation content is also on a gradual upswing, indicating these customers are actively researching reviews, routes and tips for upcoming trips, including Europe, but not clustering specifically on Spain yet.

So what you're seeing here is people that are actually visiting, the level of interest in Spain is not there at all. They're not researching anything about Spain. Now if I flip it, Athena called out France, for example, as one of the destinations. So then if I switch over to France and look at those signals, you do actually see intent. So it's not that they don't have international travelers. They ranked high in that, in GEO. They -- as leading indicators for France and Italy. They just are not seeing that in Spain.

So this is a great opportunity for me to extend. Now I'm going to take you guys through how do we actually create a media plan around this opportunity here. Any questions so far as we move into the actual execution of it all? Yes, please.

[indiscernible] Can you say how much of this was like someone [indiscernible]. Was this moving something that's a little bit more technical for a broader audience [indiscernible] starts asking questions [indiscernible].

Yes. We like to call it democratizing intelligence. So you don't need a Winnie. I don't want to get myself out of a job to ask that. You don't need me to help navigate...

We're keeping you here forever.

Okay. Perfect. Put that on paper.

So to be a little more clear, we are seeing a 75% reduction in man hours for clients that are utilizing Athena. So what used to take 100 hours now is taking 25 and it's allowing different levels of the organization to access data that they could have never gotten to before. They would have had to go to a third party in their organization to put a report together to bring them 1/10 of this information would take hours to create.

How does the [indiscernible]. If you think about that particular [indiscernible], there's a portion of time required by Athena to [indiscernible].

This does all of that automatically.

And then there is [indiscernible], so which one seems more [indiscernible]?

So that's a great question. The most reduction we're seeing today is in segmentation. It's in the creation of the right audience for what they're trying to get to because that's where you had SQL and that's where you had a lot of big data pools. As it relates to the execution of the marketing, which she's about to show you, that's probably not as big a reduction because it wasn't as time consuming to do that.

And the preparing of the data [indiscernible] segmentation.

Correct. The data cleansing is all in the segmentation. Everything you're going to see and she's been doing thus far is totally cleansed data down to a deterministic individual. We're not looking at third-party cookies. This is literally looking at 245 million active Americans as they go through 5.2 million publisher sites where our JavaScript and our first-party tracking pixel sits on every page they publish. So you're talking trillions of pages. Let's move into the execution because I want to make sure we get to that.

Great. So Athena, I have $1 million budget to actually use with my partner hotel brand. Can you tell me how I should actually be spending on the different channels and media budgets?

[AI Agent - Athena]

Pulling up Performance Advisor, here's the recommended channel mix and where to rebalance spend.

Great. Can you actually project out for me for the $1 million and the destination opportunity that you identified, create a media plan for me to drive those vacation bookings, please.

[AI Agent - Athena]

This plan is designed to move travelers from inspiration booking. We allocate 65% of the budget or $650,000 to CTV because Zeta Data Cloud signals indicate this audience has a strong propensity for premium streaming content. That investment is expected to generate high video completion rates of over 99%, ensuring United Airlines brand message is fully consumed in driving awareness and consideration and scale. We then dedicate 10% of budget or $100,000 to OLV to extend incremental reach beyond CTV and reinforce key messaging through additional video touch points.

Finally, 25% of budget or $250,000 is allocated to display, where retargeting audiences exposed to video messaging helps increase engagement and drive stronger click-through and conversion rates. Together, this creates a connected full funnel strategy where CTV builds demand, OLV reinforces it and display converts high-intent travelers into bookings.

So we basically took the KPI of interest to get those bookings to happen and then look at if it is a new client without any data, we would look at our data cloud and what are the recommendations based on what's going to drive conversions. If it's already a client that's running, we would leverage all the data that they have in the past campaigns to then make recommendations on we want to create awareness first with CTV and online video and then pair that with display to drive to conversion.

All of this is totally dynamic, and it is recommended based on the deterministic individuals that are being targeted and how we know is the best way to communicate with that exact person. It's not just saying, "let's try these different things". It is all 100% data-driven.

Exactly. And from here, we know what is going to be the right type of campaign that we're going to run. Now I want to understand the right types of creates to run.

Okay, Athena. Can you help me actually pick out the best assets that are suited for this particular plan?

[AI Agent - Athena]

Based on their creative scores, this is the top-performing asset for the plan, a video built for high-impact CTV storytelling that scores strongest on engagement and brand impact, making it the best fit to lead inspiration and drive booking intent.

[Presentation]

So that was selected based on what we saw in signals as what's going to be most resonant to this audience.

So depending on the enterprise, we can either auto generate content in real time, creative or we can have as large a repository as that client would like us to have, mostly because we work with very large enterprises, they have an agency. And their agency is doing their creative. We never want to disrupt the relationship with the agency. So we'll take their creative. It goes into a very large repository of all of their creative and then the system automatically chooses the creative it thinks will resonate most to this audience.

It's really interesting, like if you look at one of our clients, which is a large seller of pet products through retail stores. God forbid, you send a cat image to a dog person and vice versa. I use that example because it really makes sense, right? If somebody is a dog person, you want the hero image to be a dog. If somebody is a cat person, you want the hero image to be a cat. That is like 101 class-wise of what we're doing here. This is 1,000x to data being driven into the decisioning for which creative gets picked. Winnie?

I'm also going to check, Athena, can you show me what I should actually advertise for display as well?

[AI Agent - Athena]

Here's the recommended display created for your plan. A 300x250 banner built to reinforce your brand and drive booking consideration as audiences moved from CTV-led inspiration toward conversion. The overall creative score is strong at 81, including brand guideline adherence and reusability across channels.

Okay. Can you go ahead and build out the campaign and prepare the campaign for launch?

[AI Agent - Athena]

I've built a campaign using the forecasted media plan and recommended creative. The campaign is set to run for 30 days with a $1 million budget, $650,000 allocated to CTV, $100,000 to OLV and $250,000 to display. This gives the campaign a balanced mix of premium video reach, incremental video exposure and lower funnel booking support. I've applied the high-intend consumers audience, assigned the recommended CTV, OLV and display assets, connected the vacation booking event and set CPA and VCR as the campaign goals. Campaign setup looks good and is ready to submit for activation.

Perfect. Now that the Zeta team has approved the actual campaign, let's go ahead and start monitoring the performance. Can you go ahead and create a dashboard to help me monitor the campaign performance?

[AI Agent - Athena]

Sure. Here is the dashboard to monitor your omnichannel campaign performance.

Okay. There's a lot of metrics here. Can you help me interpret how my campaign is actually performing?

You'll note this campaign, which is real...

[AI Agent - Athena]

Sure thing.

Had a 14x return on market [ expense ].

[AI Agent - Athena]

Looking into simulated dashboard over the last year, you spent about $1.1 million, generated roughly 12,413 bookings and brought in about $14 million in revenue. That works out to a cost per booking of around $88.84, a return on ad spend of about $12.77 and an average order value around $1,134. Overall, those numbers suggest strong efficiency and revenue impact.

Perfect. What about the best channels that I'm operating in?

[AI Agent - Athena]

Based on the data, display is your top channel with about 7,965 bookings, followed by CTV at roughly 4,357 bookings, OLV trails with just about 91 bookings. Display and CTV are clearly performing best for you.

Perfect. And what about the audience?

[AI Agent - Athena]

The strongest audience segments are summer travelers with about 2,984 bookings, travel enthusiasts close behind at roughly 2850 and look-alike audiences with around 2,372. Travel intent and retargeting audiences each delivered about 1,830 bookings and families with kids contributed around 553. These are the groups driving the bulk of conversions.

Perfect. Thank you, Athena. Great. So hopefully, you guys were able to see how do we take that massive amount of data, find opportunities for our clients to be able to transform that into a media activation plan, execute it, find the right -- well find the right creates, then execute it and be able to measure the impact of every dollar spent.

Today, I think you guys saw the power of this and how fast it is. When it's put on top of Foundry, it's going to be substantially faster. It's going to be substantially smarter.

So the reason the Palantir deal is so important to us is, A, the capabilities they bring to us from a found -- easy for me to say, a foundational level; B, the joint go-to-market, which is going to be very, very powerful; and three, our real move from being a marketing platform into an AI infrastructure platform.

I want to go back to what I said earlier about Athena, 9 months from idea to generally available, 90 days to launch her as fully and up agency capable product. We are turning her ultimately into a full operating system where this data will inform all of our clients' decisioning.

Let me give you a perfect example. This is a real example we've already done. A very large client, who's a very large hotel chain, was trying to figure out where to put their next 500 hotels. We researched, we took every one of their existing clients. We looked at every credit card transaction that they did in every market that they were not. We segmented it to their competitors from a landscape perspective, how many room nights were they consuming from their competitors in a 5-mile circumference around that competitor in markets they did not have hotels. And they made the decision that those markets where they had the most hotel nights for their most loyal customers were where they should put their next 500 hotels.

As they've opened those hotels, they're using us to launch the marketing and do conquesting against the competitors and move those consumers to them. That is the convergence of business intelligence and marketing in that case. But when you think of Zeta, we really think of ourselves more as a business intelligence/infrastructure company that chose marketing because it has a $1 trillion TAM. So it's something that we've been focused on, and we've been working through. You had a question back there, and then I'll go to you.

Yes, about the reference architecture. So it sounds like Foundry's [ going to ] get you guys efficiencies, [ obviously ] better answers, et cetera. But what was -- what's the [indiscernible] without giving too much away [indiscernible] architecture [indiscernible].

Yes, a lot of AWS. And by the way, we love AWS, we love Snowflake, we love a lot of our existing vendors, but we have moved some of the spend we were doing with others or spend we expected to increase to Palantir to replace those vendors in our tech stack.

Did you have a question?

Yes. I just want to -- can you help me just to understand the impact of the partnership with OpenAI and [indiscernible] levels [indiscernible].

The question is, how does Palantir affect OpenAI. It's not going to affect it in any way other than today, we use OpenAI to be the voice engine for Athena. The reason that's important is every time an individual enterprise or agency individual uses it, it gets to know them better. So it really begins to understand inference in addition to just what you're saying, okay?

So when we put Athena on top of Foundry, they'll stay independent, but the data that's fed to Athena will move much, much faster. And there's no problem there. As it relates to the advertising ramp of the open AI relationship, it's ramping as we expected it to. We're trying -- everybody is right now trying to figure out how to do it.

This is very emblematic of a number of partnerships we've started over the years. It actually reminds me years ago when we helped to build the API that helped a little company called Meta get into the advertising I think it's one of the reasons we're the only platform that I know of that matches the our ID to the Meta ID. And that, of course, is an amazing company and been an amazing partner. But when they first started, they were trying to figure it out.

So we're seeing it ramp nicely. We have a lot of demand for it. Enterprises want to be in it. I think a lot of it is sort of the new and cool factor. So we're super excited. I think we're the only platform that is partnering with OpenAI both ways. Let me -- go ahead.

Just on the comments earlier about reducing the Palantir [indiscernible] cost savings. What is the...

In out years, we're not suggesting this year, it's going to lower cost.

Is the like system and other technologies [indiscernible] consolidation, is that for application SaaS factors or is it more like, we talked about this data infrastructure [indiscernible].

Yes. We don't consume a lot of SaaS-based technology because we are a SaaS platform, right? And most of our architecture is our own. The only time we've used third parties in the past has been around cloud compute, primarily through either AWS or Snowflake, which, by the way, we've openly talked about our partnership with Snowflake. And I think it's pretty well known we're an AWS shop.

Although yesterday, when Gap announced that they were making us the system of record. We're doing that in partnership with Google Cloud. We're totally sort of, I don't know if Switzerland is still considered totally neutral, but we're very much like Switzerland in that we're trying to stay very, very neutral.

The reason Foundry made sense from a migration perspective was the quality of their architecture. And quite frankly, a lot of their architecture maps really well to our infrastructure today. And we've already done -- I mean, listen, we wouldn't have announced this today if we hadn't been building this for quite som time, right? So it's where we've been in process.

[indiscernible] some of the holding companies we met, they say they're still cautious about building tools [indiscernible].

Great.

[indiscernible] LLM data that just...

We don't feed our data into any large language model ever nor I believe any of our enterprise clients would allow us to do so. And so we totally agree with that. We're only using OpenAI as the voice interface for Athena. She never sees the underlying data. She's seeing an output that's coming from our data cloud.

By way of example, everything you saw here, you could have navigated through our platform using a keyboard a few months -- I mean you still can, if you could figure out how to do it. So none of the output or non of the underlying data goes to the large language model.

So this -- could there be a risk like kind of iOS model or moments where you have to have big [indiscernible].

So when iOS moved to a no cookie system, our growth that year was only 62%. So we don't rely on third-party systems to track people. So we do not fear that type of a thing. When people say to me, what are you most worried about, it's a data breach. For a company like us, where 51% of the Fortune 100 are trusting you with all of their data, if you have a breach, trust could be lost, and that's where you have a major problem.

So what do we do? Our network operating center operates on 4 continents, 24/7, 365. Our Head of Data Security, Dr. Jeff Nimeroff, who has his PhD from the University of Pennsylvania, used to help to run all data security for eBay before joining us, has designed a siloed data system with 28 different silos. Each of one has a different encryption key to connect the PII to the different data points and we invest very heavily in that.

The other thing that Foundry gives us is another added layer of data security. It's one of the best data security platforms in the world, whereas a number of our other competitors -- I'm sorry, our other partners didn't have that layer. Did you have another question?

Last one is going to be I think, early on when we saw Tiktok ads, we thought it was hard to kind of predict how these [indiscernible].

Yes. And we partner with TikTok, we partner with Snap. We partner with Meta. We partner with LinkedIn.

[indiscernible] tells he premise of the question but really I wanted to know based on what you're seeing where the LLM is with some of the [ churns ], some of the economics performance experience, how would you compare that to what's out there in the market?

Well, it's hard to compare it to TikTok because TikTok is so viral, right? You don't get that type of a viral nature in the natural outputs of the existing large language models. That being said, we are seeing very high click-through rates, but they're only showing -- we're only serving the ads in a very small percentage of what is a large inventory pool. So it's not going to be a small amount, but we're seeing higher click-through rates. It's still early on the return on marketing spend to be honest. One last question. Do you want Ron to sum us up or?

Just in terms of the return on ad spend [indiscernible].

We say marketing, but yes.

In terms of the third-party verification of just numbers...

It comes from Forrester. This is a Forrester independent study that they published showing that the average return on marketing spend was an average of 2.4x to 2.7x, and we were at 6x to 6.5x. We were more than 100% higher than #2 in their study.

[indiscernible].

I don't know. 2 minutes? I have 2 minutes. You can get the report from Forrester. It's available through them. I -- personally, I don't recall if they put a narrative around it, but...

What they did was they actually took a number of customers from different industries, looked at different channels that they were using and the different use cases of acquire, grow and retain. And the outcomes in that study by customer range from anywhere as low as 4.5x, I want to say, to as high as 9x.

By the way, when Forrester named us the #1 marketing automation company, again, third year in a row. I'll point out in the year that they just named us number one, we did not spend meaningful dollars with them as a client. So that's something I always like to point out. We're big fans of Forrester, but I like to be clear about that. They said, when putting us the highest and furthest to the right in their study, we take the most complex marketing problems and make them simple. And I think that's ultimately what clients want.

The CMOs are always under pressure. They're usually the lowest tenured employee in any CXO suite. So our job is to make them the hero of their own environment and ecosystem and keep things as simple as possible while driving the highest possible return on marketing spend. By the way, what she showed you was not like a demo. This was like a real interaction with the platform. The outputs are from a real campaign that ran and you'll note that it was 14x return on marketing spend. She did not cherry-pick that. We have a lot of clients who were well above that order of magnitude return, the average is 600% to 700%.

That's a great place to end it. David, Chris, Winnie, thank you for the time and congrats on the deal. Enjoy the heat. Yes.

All right. Hello, everybody. My name is Brett Miller. I'm the Co-Head of Software Investment Banking at JPMorgan. Thanks for being here. Today, it's my pleasure to lead a discussion with David Steinberg and Chris Greiner of Zeta Global. Zeta is an AI-powered omnichannel data-driven cloud platform that provides enterprises with consumer intelligence and marketing automation software, helping brands personalize marketing across channels, including e-mail, social, web, chat, connected TV and video. David, the company's CEO and Chairman, co-founded Zeta in 2011 and took it public in 2021. Chris, the CFO, joined Zeta in 2020 after serving as the CFO of LivePerson and Inovalon. David and Chris, thanks for being here today.

Thank you for having us.

First off, big picture, what is Zeta trying to become for the enterprise? Is it a marketing operating system, a data cloud and AI decision engine or some combo?

Well, let's start with yes. I mean we're -- our real vision is to become the operating system for our clients' entire marketing ecosystem. And if you look at Athena, our new sort of AI-driven super agent, she really positions us to do that really well. And if you look at the way we operate today, we're ingesting 100% of very large enterprises first-party data. We're matching it with our data. In the United States, we match it greater than 92%. And that's where the algorithms start training inside of the consumer data platform.

So once we do that, all of the business intelligence and all of the data for our clients exist in that ecosystem. And I think one of the things people don't really understand is we think of ourselves as an AI-driven business intelligence company that started focusing on marketing because it's a $1 trillion TAM, right? It was just a very good place to start. It's not where we expect to finish.

I spent a lot of my time today on the debate about the SaaS apocalypse and whether SaaS is going away. What is your view on this debate on the disintermediation by AI?

Well, I think it's going to be a lot like the dot-com, except I don't think we're going to follow that type of bubble because most of the enterprises that are making these investments have $1 trillion balance sheets. They're not start-ups. But what I would say is companies that adopted the Internet are the ones that have flourished from a technological perspective. And if you think about it, I remember -- and yes, I'm old. I remember when the dot-com boom was coming and they said it was going to kill Walmart. It was going to kill JPMorgan Chase. It was going to kill Federal Express.

In all those cases, those organizations adopted those technologies and became juggernauts. Now I do think I mean, first of all, right now, all funds are flowing to AI hardware, right? So that's one challenge that software companies are dealing with as public companies. The other really interesting thing is today, nobody is willing to take a risk on who's going to be the winners, who's going to be the losers.

And everybody is sort of throwing the baby out with the bathwater. If you think about companies that are going to win, there are going to be companies that have moats around their business. If you look at Zeta, we have 555 million global individuals who have opted in to be in our data cloud. The only other companies that have data at our scale are all trillion-dollar companies. You're talking about Meta, Google, Amazon. And you can go through that list. We use that data. And of course, we're ingesting the data today, 51% of the Fortune 100 largest companies in the United States use our platform, and they're trusting us with their first-party data. We're using that data to create intelligence. And according to an independent Forrester survey study, for every dollar a client spends on the Zeta Marketing Platform, today, we returned 600% return on market spend.

Now if you look at the adoption of Athena, which rolled out in the first quarter, we did say in the first quarter, we saw our Agentic workflows go up by 700%, and Athena was a very big driver of that. Clients that are using Athena are seeing an even greater return on investment than that 600%. So I think over the next quarter or 2, investors are going to start to figure out there are going to be some winners. There are going to be some losers. I think companies that are workflow management tools don't create intelligence, don't own data and don't have meaningful defendable assets are going to have to figure out how to pivot their businesses to survive. And I think you're going to have companies like Zeta that are creating intelligence, creating massive return on investment.

And once again, I don't see Fortune 500 companies turning over their first-party data to large language models. I just think that's going to be tough. The other thing, of course, is we're already partnered with OpenAI. We've already announced an enterprise partnership with them. We already work with Anthropic. We work with Google. We're already in that entire ecosystem.

You just teed up about 20 questions in that response. So thank you for that. So at CES, you did announce, you just mentioned it, the major partnership with OpenAI, which powers Athena. Tell us about that relationship, how it's evolved, where it's going?

Well, I'm super excited to mention today that we have now executed an agreement to partner with OpenAI and help them run their advertising. We're going to bring our enterprise clients into the OpenAI ecosystem, and we'll begin to serve ads there on behalf of our enterprise clients.

Anything more about where that's going and like what you can be doing generally with it?

Yes. I mean, listen, we think OpenAI is going to be one of the winners in the next generation. And the fact that now we've executed partnerships with them around Athena and we've executed partnerships with them around serving ads into the ecosystem. I think it's going to be game changing to our organization. If you think about it today, we are the only company I know of that is fully integrated into Meta, into Google, into the open web, into messaging, into connected TV and now connected into OpenAI, both through serving ads and through our GEO platform.

Incredible. We've mentioned Athena a bunch. Why don't we just up level for a second and give just a quick description of Athena. And then also like what is the workflow that it's changing for your customers?

So Athena is -- well, we'll step back a little bit. If you think about it, humanity is always communicated through voice, right? I mean I shouldn't say always, but for, call it, 400,000 years. In the 1950s, we created this thing called the keyboard, sits between most humans and technology. And I think most of us find it very, very frustrating. Athena was created to be a voice-enabled, fully conversational agent who helps our clients navigate our entire platform, not just by trying to figure out how to use different features and functions, but by literally asking for outcomes from the platform and Athena can change the screen in front of the client. So a client might say, I'd like to create 2 million incremental customers this quarter, and I'd like to do it in an environment where I can lower my marketing cost by an average of 7% per customer acquired. And Athena walked through how a client can get to those outcomes.

So the way I equate it, and I think many people in this room probably use Bloomberg terminals, right? What percentage of your Bloomberg terminals capabilities do you use on a daily basis? 1%. That's -- I've heard 1%, 3%, 5%. It's the same thing for most software, right? So we've built a fighter jet that our average client knows how to fly assess. And Athena becomes the copilot for how to get to those most valuable components of the platform that they don't know how to use on their own. And what we're seeing, once again, Athena rolled out in Q1. She was beta for much of it. She rolled out generally available in March. Even with that limited period, we saw a 700% uptick in Agentic workflow. And we saw Athena as most of it.

Now I mean, we did -- our business grew 50% top line in the first quarter, 42% EBITDA growth, 42% free cash flow growth. This will be on a 4-year average basis, this will be our fourth year of greater than 30% organic top line growth and greater than 50% organic EBITDA growth. So what we're doing is working because our clients are consuming more of it. They're growing with us. And as we show a greater and greater return on investment, we believe we'll continue to see that growth.

Yes. We'll come back to the metrics and let Chris brag about those in a minute. On the 700% increase in Agentic interactions, like in the 1% of the Bloomberg uses your analogy, what are you seeing about how customers want to use AI through that early signal?

We're seeing a lot of clients move right to how do I get to this outcome versus trying to navigate the platform to get to the outcome. And then Athena is able to control the entire experience and she actually changes the screen to show audience types, activation capabilities and all of the different return on investment in real time as you experience it. So that's a big one. Another big one, interestingly enough, has been analytics.

We're seeing a lot of clients ask for analytical outcomes that we haven't seen them ask for before. And for those of you who don't know our business well, we have 3 main use cases. it sounds complex, but it's pretty simple. Helping enterprises to create customers, maintain their existing customers and further monetize their existing customers. And we do this by activating across multiple channels. A channel might be connected TV, a channel might be online video. It might be online contextual. It might be now plugging into OpenAI.

It might be plugging and targeting into Meta. All of those things are sort of use cases versus channels. If you've looked at our business since our IPO, we've been public for 19 quarters, I will point out 19 consecutive quarters, we've beaten our guidance and raised guidance. But the way we've grown our business is by adding channels. And we've gone from an average of about one channel to an average of over 3 channels in that same period. What we found is when enterprises use multiple use cases so they do customer acquisition and customer retention and customer monetization. They spend 250% more on our platform. But the reason for that is because the flywheel for intelligence starts with one of them. So the data that informs acquisition further informs the data that's necessary for retention, which further informs the data for monetization back to acquisition. So the return on investment is substantially greater than our average of 600%. The single best tool to ultimately get our clients from an average of 1.4, I don't know the exact number, but sort of, call it, just about over 1 use case to 3 use cases is Athena. Because after you've asked Athena for outcomes, around acquisition, she might say to you, by the way, did you know that this 1.2 million of your existing customers began the process of churning off your platform and discovery for your competitors' products? Would you like to save them? And that's how it's already starting.

So you're not explicitly monetizing Athena yet. So talk about that decision of when does this become a line item in your P&L versus when is it just something that drives retention and ARPU?

Well, it's driving ARPU growth. I mean, we had a 21% ARPU growth in the first quarter, which -- and last year, our net retention rate was 120% as a company. We guide to 110% to 115%. We were actually well above that in the first quarter. But when you look at what Athena is doing, she is driving a massive uptick in our utilization fees. So if you think of our business, about 60% of our revenue is subscription and 40% is utilization.

If we were a large language model, we would simply be calling our utilization tokens instead of utilization because it's the exact same model. It's -- as we run messaging or we place an ad or we run a connected TV ad, we charge a fee for that. We've batted it around. There will be an opportunity at some point to build, I think, analytics products and extensions around Athena.

But today, if you look at it, our 189 global superscaled customers will spend approximately $110 billion on marketing this year. At the middle of our range, we have approximately 170 basis points of wallet share. Now we have some clients that we have 700 to 800 basis points of wallet share, and I don't see any reason we can't get all of our clients there at some point on average.

So if Athena can help us go from 170 basis points to 200, 300, 400 basis points, the return on investment to us is so much massively greater as you go from what I think last year, we were about $1.35 billion.

And then this year, we're projecting $1.75 billion. $1.78 billion. You're looking at sort of the business is not just growing at 40% or 50%, it's also dropping a disproportionate percentage of that to the bottom line. So we think Athena is better served today in driving that massive uptick in utilization.

Any plans for the future and how you'll monetize AI differently than you're doing today?

Yes. I mean there's a lot of different ways. And back to the original premise, as you think about Zeta, we think about ourselves as a business intelligence company that happens to focus on marketing. As we roll out business intelligence products, which is in our long-term road map, we'll begin to charge for those products, and that will be commensurate with other AI products.

And in terms of managing token costs, one of the sessions as of this morning, one of the companies said that they basically had no idea how this is going to evolve and they're learning in real time. Like how do you think about how.

We are not that. We are fully and completely aware as to, how we utilize tokens and how we program. What I would tell you is we built an internal platform called SPAD, and SPAD is an internal proprietary workflow management tool. Last quarter, we publicly announced 75% of our internal new code was generated automatically, 75%.

We're ahead of Google, which is even shocking to me. It works because of SPAD. So a programmer goes to SPAD and tells SPAD the type of code it wants to create. SPAD then looks at all of the available large language models, which include ChatGPT, Claude, Gemini, all the way through Cursor, and it makes the decision on which platform is right to create that piece of code and is utilizing the least tokens in its generation.

So for security, it might use Claude, for programming, it might use GPT, for publishing, it might use Gemini. Once it completes it, it sends it to another program called Zappi. I don't know where we come up with the names for these things, but Zappi then QAs the entire thing, sends it over to an architect who reviews it, pushes a button and it goes generally available.

So literally, we're doing stuff. We've talked about this, and I'll sort of mention today. We're going to be rolling out the next generation of Athena, which will be Athena for agencies. The agencies make up about 20%, call it, 25%, less than 25% of our revenue. And the product itself would have taken us 2 years to develop 2 years ago. We're going to have the entire product done in less than 4 months because the pace at which we're able to accelerate code generation and the way we've been able to control cost while doing it.

So I mean, by way of example, we've grown the business again on a compounded 4-year growth rate of 30% greater organically. We've grown headcount just about 10%. And I think we can even slow headcount growth even further, and we expect to be a 20-plus percent organic growth rate company for many years to come.

Speaking of the quarter. So great quarter, another great quarter. Rule of 67, growing 50% year-over-year and over 20% of that is organic.

29% was organic...

Which is over 20%...

Which is well over 20%...

It's well over 20%.

I mean, it's over 20%. It could be 20.02%.

It's approximately 30%. That sounds better. Chris, if you were to pick a couple of drivers of the quarter and then also talk about where the growth -- that organic growth is coming from.

Yes. I think what stood out to us as we even looked at it internally, certainly as we spoke to it externally was just how many parts of the growth ecosystem of Zeta were working in tandem. We talked about the 29 points of organic growth and the balance that we had, 14 came from existing customers, 15 from new.

If you look at the industries that rely upon Zeta's platform, we're in 15 different industry verticals. Our top 10 generate about 90%, 9 out of our top 10 verticals grew over 20%. When you think about the KPIs that power our growth, the customer additions and the customer spend expansion, we had 19% growth in super-scaled customer count. That's more than 3x greater than what we require from our model.

And then as David mentioned earlier, from an ARPU perspective, 21% growth, our model is 12% to 16%. David linked it back earlier to channel expansion and use case expansion. Two data points that we shared with investors in the quarter was those that are using more than one use case. And if we were sitting here a few years ago, that would have been less than 10% of our portfolio.

Today, that's double that. We're approaching 25%. And that metric, number of scaled customers using more than one use case grew 50% year-over-year. And those using 4 or more channels, could be any channels in tandem, grew over 40% year-over-year. So you had many different parts of the portfolio all working and executing really well that led to a much bigger beat than what we would typically have of, call it, 2 to 5 points on the top line.

The other thing really is Athena. We're seeing Athena out there. And we're taking meaningful market share from competitors. And one of the challenges we have as a public company, right, is are you a CRM platform? Are you an activation platform, or you an ad tech company? Are you a marketing technology company? Are you a data platform? The answer is yes. Because our goal is to displace all point solutions in the marketing space. And if you look at our prepared remarks from our most recent call, we announced what I think is the most marquee client win we've ever had.

It's a retailer with greater than 3,000 global locations and manufacture and sell their own apparel across multiple brands. This is a company based in San Francisco. It had been a total Salesforce shop, and we were able to rip and replace them out.

We also replaced 3 other vendors in that because Salesforce, can't provide everything a modern marketer needs outside of a very sort of narrow CRM and CDP capability, whereas we're able to bring CDP, data cloud, best-in-breed data activation to CRM, customer acquisition and customer retention.

We were told we were in the top 3 going into the end of the sort of ninth inning of the process. And we asked if we could come in and do an early demo of Athena. We did the demo of Athena and they called us the next day for pricing. So it's really -- I think Athena is going to be a major, major game changer for our company.

Sounds like it. On the bottom line, you did grow your EBITDA by 42% year-over-year and your free cash flow by 48% year-over-year, which is pretty remarkable. What are the biggest drivers of that leverage?

Yes. What we've done a really good job of, and David mentioned earlier, is automating more and more of what we have. We have a kind of a philosophy in the company of where is value created. And we're creating the world's best products, and we put resources and investment in engineering and the tools they use and then selling it as fast and efficiently as you can in the market. We put resources in quota carriers.

Everywhere else, we cut, we trim, we automate. So that's allowed us to invest and to have the best product in the market. Sell at what is a very productive rate in the market and expand adjusted EBITDA margins and free cash flow margins faster than the rate at which we're growing the top line. The rest of the year, we'll get back to very strong adjusted EBITDA and free cash flow margins as well.

It's also important to note that we built a lot of this stuff ourselves. So as everybody is now talking of the evolution of AI, right, it's starting with large language models, and it's moving to what's called inference models, right? And I don't want to bore everybody in the room with this.

But we've been building inference models for 5 years. The idea that one algorithm can focus on one task with the data set that is necessary to complete that task is really what inference is. We don't need to ingest the entire Internet to figure out what we're doing because we have so much proprietary data we can focus on.

We're not sort of trying to boil the ocean here. Now of course, we love our partner, OpenAI. We love what they're doing, and they're trying to do something on a very, very big basis for that.

Yes. So the quarters are often driven by shifts in the mix-shift. So last quarter, you talked about agency wins and social being a big driver. Why don't we spend just a minute on mix shift and how -- what that did for the quarter and how you think that's going to evolve?

Yes. We disaggregate revenue in a number of different ways, but one of which is what we call and report as direct revenue contribution and integrated platform revenue contribution. Direct is nothing more than when customers use Zeta data and Zeta channels to do their activation. And that regularly contributes 70% to 75% of our revenues. I'd call it a gross margin of 70% to 75% on average.

The integrated platform revenue is when customers rely on Zeta's data, but the ability to go market inside the walled gardens. Meta is a great example. Dave talked about others. That's about, call it, 25% of our revenue has a lower gross margin profile. A lot of the inventory gets passed through to the customer.

What we found empirically is that when agencies, which have been, call it, in the last 2 years, a new buyer of Zeta and they've grown and scaled to approaching 25% of revenue, they first test Zeta data and they first test our platform with social. But what we've seen is as they grow their spend, as they give Zeta more and more brands within their ecosystem, they do that by expanding on Zeta's channel.

So these 2 large wins, like patterns in the past, started in social, and it's our expectation that as they grow, they'll migrate to direct, which will then take some pressure off of the gross margin side. But it's really important from an investor's perspective, even though social has a lower gross margin profile, it's still accretive to adjusted EBITDA and free cash flow.

And it's important to note that we're really the only platform of our type that plugs into these walled gardens. So agencies start with us because there's nobody else who can actually do this. And then as they do it with us, they see the power of our data, and we're able to expand out into other use cases that are much higher margin.

So you've touched on this once before, maybe twice before, but you talk about, in your words, super-scaled customers, which is my favorite metric that any company displays.

We're going to move to super duper scale.

Even better. So on the super-scaled customers, you're at 189 of them, I believe, and you're scaling that ARPU pretty significantly in that cohort of customers. So one, how are you continuing to keep the momentum gaining those customers? And what is driving that ARPU expansion?

Yes, there's a -- for those that know our story well and for those that are new that want to pick up on it really quick, there's a slide in our investor deck that shows that the longer our customers are on our platform, the bigger they become. There's 5 years' worth of this slide that the vast majority of the time, we are not beholden to an RFP because we are proud to start with a $50,000 pilot or $150,000 proof of concept.

And what we found is that those very small pilots in the first 12 months almost get to $1 million in spend, which would then flip them over to that super-scaled category. But beyond that, our fastest-growing set of customers are those that have been with us 5 or more years.

So to David's point, it's taken some of those longer tenured customers to find out where are all the corners in the platform that I'm not using today that I should be using. Athena unlocks that to everybody. So it has the potential to take those that are earlier in their life cycle and have them climb to that much higher level of spend faster.

By way of example, I was at a conference just a couple of weeks ago, we were with a very large new partner. And I had 2 or 3 salespeople in the room, and they were all really nervous about getting this deal done. And the CMO of this very large company asked me how large I thought the test should be to really get to a statistical sample.

And I said, "Listen, I wouldn't start with any more than $10 million." If we do more than $10 million, it's really going to get us past the point of diminishing marginal return. But if we start with that, it will give us really good statistical data. And they were like, "Okay."

So we're not just taking existing clients and growing them, which has been our traditional business. To Chris' point, he's totally right. But the credibility that's now coming with our current size, scale and return on marketing spend is leading clients out of the box to start at bigger numbers than we've seen before.

And on that dynamic, your net revenue retention rate is remarkably consistent and considerably high, 110% to 115%...

Last year, it was 120%.

Right. It's the consistency of it, I think, that I would call out at a time when a lot of other companies had seen degradation in that metric. And then in some cases, a recent recovery. How have you been able to maintain such consistently high net revenue retention?

I think that goes back to what Chris was saying, right? When you start with a client -- and by the way, the client that spend -- we're asking for $10 million has a $4 billion annual budget, right? So it's still statistically similar. A lot of the companies we start with, we're starting with a small pilot new scale. That actually leads to a higher net retention rate, right, because they're growing and growing.

And I think that -- listen, we -- one of the things people don't understand is we build every one of our clients a consumer data platform. We ingest all of their data. We match it with all of our data. We match it greater than 92%. We then remove the personally identifiable information from a regulatory and keeping the consumers' data private. The algorithm then gets incredibly smart on how your customers came to be your customers.

What did they read, what did they search, what transactions did they do? We then go into our data cloud. Let's say, just in the U.S., we have 245 million opted-in people. And we'll say, "Okay, great." These 50 million people are already your customers, don't waste money marketing to them. Think about how often you get an ad for a product you already have.

Then what we do is say, "Okay, these 2 million people are in market for your product, but only 1 million of them would be credit approved by your criteria." So now you've gone from 245 million potential customers down to 1 million, you hyper target them. And as they buy, it feeds their data back into the CDP through the CRM integration and the algorithm gets smarter.

If a client were to fire us, they lose 100% of the learning. All of that data goes away. So what happens is the longer a client is with us, the smarter the algorithm gets, the better we can either lower their churn or help them create customers at a lower cost -- the higher the rate they move budget to us, the higher our net retention rate.

When you think about sort of AI disintermediation, I couldn't see an environment where a Fortune 500 company is going to feed all of their first-party data to a large language model. And then, of course, all of our data, all 555 million people multiplied by 5,000 to 7,000 data elements, multiplied by all of their web behaviors across trillions of active pages on the Internet has never been fed into a large language model ever, nor will it.

That's our proprietary data for training our models in partnership with our clients' data. So that's why our net retention rate is so high, and it's one of the biggest moats around our business.

On the guidance, I'm going to fold a few questions together here. So one, 19 consecutive beat and raise quarters, as David mentioned. And then after this last quarter, you did once again raise your guidance around revenue, EBITDA and free cash flow. What made you comfortable doing that? And how have you managed to achieve that level of, again, just remarkable consistency?

We are very transparent, and we give ourselves 2 to 5 points of growth cushion in our model. So it gives us doors A, B, C, D, E and F every quarter. So we know what those doors are in our model. We tend to put our guidance at the lower end of what our KPIs say we need to do.

This year, we added layers of conservatism for Athena. We wanted Athena to be pure upside. We wanted Marigold and the synergies that we drive to be upside. And then we wanted political, which we break out anyway to be upside. So the fact that we beat by $26 million in the first quarter, we felt comfortable rolling through the year.

We obviously felt comfortable rolling the next, or I should say, adding to the 2Q guidance by $4 million. Holding 3Q and 4Q, or holding out quarters consistent, is consistent with what we do as our model anyway. So I know we've gotten questions on going from 29% organic growth to, call it, low 20s in the 2Q, 3Q, 4Q.

That's totally consistent with how we've guided in the past and wasn't meant to infer anything related to a slowdown. It's just we are keeping our process and our practices consistent as our guidance.

And unlike other years, because of the Marigold acquisition, we actually gave our guidance for this year early. So if you take that raise for this year plus the first quarter raise for this year, we've already raised this year by $55 million on the top line.

So -- and about consistency, what a lot of people don't understand is, yes, 60% of our revenue is subscription. We've got a lot of visibility into that. But even in our utilization fees, we have 1-year contracts on most of that.

So we're not including it in subscription because it's only 1 year, but it gives us unbelievable visibility into our business. And quite frankly, even in what appears to be a tough economic environment, we continue to see our growth at the rates that we expect it to be at.

David, I'm going to ask you a broad question about the competitive environment. So you compete against legacy marketing clouds. You compete against potentially horizontal AI platforms. What do you want to highlight on what's happening?

What are the moats around Zeta? And then also this week, there was obviously the LiveRamp acquisition. Like how does that change that competitive dynamic? That's a whole lot in 1 minute.

Yes. Well, so let me start by saying we love LiveRamp. We've been partners with them for years. We love Publicis. We've been partners with them for years. I see this as a major win for Zeta, both with our existing client and our partner there. And I think a lot of the other agencies are going to be looking for new solutions, which Zeta can provide for them.

So I think we're in a very unique position to win both ways. And once again, we -- I will say I thought this was a brilliant acquisition by Publicis. This was a really good decision on their part. And we spoke to them at length yesterday. We're seeing them multiple times this week, and I think that's going to work out very well for us, once again, as I expressed.

We haven't seen any horizontal AI competitors at this point. Just to be very clear, we don't even see them moving into what we're doing. We're having lots of conversations with the horizontal AI platforms to integrate them into what we're doing and integrate them into our stack as we've already announced with OpenAI today on the ads side and had already announced working with them on the Athena side.

As it relates to the marketing clouds, listen, these are great companies. I sort of joke we compete with a few small companies, right, Salesforce, Oracle, Adobe, Trade Desk. The truth of the matter is most of their technology is built for where the market was, not for where the market is going. We're in the biggest replacement cycle I've ever seen for marketing clouds, and we are winning at a disproportionately higher rate, and we expect that trend to continue.

Incredibly exciting time at Zeta. Chris, David, thanks for being here.

Thank you, Brett.

Greetings, and welcome to the Zeta Q1 '26 Earnings Call. [Operator Instructions] As a reminder, this conference is being recorded. I would now like to turn the conference over to your host, Matt Pfau. You may begin.

Thank you, operator. Hello, everyone, and thank you for joining us for Zeta's First Quarter 2026 Conference Call. Today's presentation and earnings release are available on Zeta's Investor Relations website at investors.zetaglobal.com, where you will also find links to our SEC filings, along with other information about Zeta.

Joining me on the call today are David Steinberg, Zeta's Co-Founder, Chairman and Chief Executive Officer; and Chris Greiner, Zeta's Chief Financial Officer.

Before we begin, I'd like to remind everyone that statements made on this call as well as in the presentation and earnings release contain forward-looking statements regarding our financial outlook, business plans and objectives and other future events and developments, including statements about the market potential of our products, potential competition, revenues of our products and our goals and strategies. These statements are subject to risks and uncertainties that may cause actual results to differ materially from those projected. These risks and uncertainties include those described in the company's earnings release and other filings with the SEC and speak only as of today's date.

In addition, our discussion today will include references to certain supplemental non-GAAP financial measures, which should be considered in addition to, and not as a substitute for, our GAAP results. We use these non-GAAP measures in managing our business and believe they provide useful information for our investors. Reconciliations of the non-GAAP measures to the corresponding GAAP measures, where appropriate, can be found in the earnings presentation available on our website as well as our earnings release and our other filings with the SEC.

With that, I will now turn the call over to David.

Thank you, Matt. Good afternoon, everyone, and thank you for joining us today. We delivered our 19th consecutive beat and raise quarter. This consistency is not driven by a single product cycle or a short-term tailwind. It is the result of a structural shift in the market. AI is no longer a feature. It is driving a replacement cycle where enterprises are demanding fewer systems, measurable results and applied intelligence that works today. We are winning in this environment because of the system we have built, proprietary data that improves with every interaction, intelligence that compounds with every decision and a platform with AI at its core that allows customers to consolidate vendors into a single unified operating system. This differentiated approach has been recognized by Forrester, where Zeta was once again named a leader and also reflected in our customer advocacy with an NPS score in line with market leaders, up 23% from our assessment in the prior year. Both come on the heels of Forrester study showing Zeta returns an average of 600% on marketing spend for its customers.

Athena by Zeta is an accelerant. It is the user interface that brings AI directly into marketing workflows and removes the barriers to enterprise-wide adoption and impact. Signs of this were evident in Q1 with beta customers plus strong early adoption of Athena contributing to the revenue beat. Our first quarter performance, once again, shows we are the disruptor in the AI-driven marketing ecosystem.

First quarter revenue of $396 million, representing year-over-year growth of 50% and up 29% year-over-year ex Marigold, our fourth straight quarter of revenue growth acceleration, excluding acquisitions and political candidate revenue. And adjusted EBITDA was $66 million, up 42% year-over-year. 19 consecutive beat and raise quarters combined with a 4-year revenue CAGR of 30% reflect more than just consistency. They are evidence of sustained demand in a market consolidating around platforms that can deliver measurable outcomes at scale. And that visibility is reflected in our outlook. After raising the midpoint of our range for 2026 revenue guidance last quarter by $25 million, we are again raising it by $30 million, representing growth of 37%. These market share gains are evidence of a shift in the competitive landscape as AI moves from feature to a new way of doing business.

Athena is designed to accelerate our share gains by bringing intelligence directly into workflows, turning answers into actions and ultimately changing how marketing is planned, executed and optimized. Athena is currently available to all of our enterprise customers, and its impact is already evident in sales pursuits and results. The number of Athena demos to potential new clients increased dramatically throughout the quarter. The promise of Athena is influencing decision-makers and helping Zeta win deals as customers want to invest in applied AI, not road map AI.

One new customer we closed in the quarter commented, "Leapfrogging to the future requires thinking differently today and committing to execution. Interacting with Athena made it clear that Zeta has already made this leap, bringing its vision to life and positioning us to accelerate into a fully agentic marketing future."

Athena was a driver in one of the largest deals we have ever closed. The customer is a leading global apparel retailer operating across multiple brands, each with unique customers and over 3,000 locations worldwide. Zeta's platform was purpose-built to handle the complexity required by the largest enterprise companies, and this customer was able to consolidate down from 4 vendors to 1, Zeta. As the legacy Marketing Cloud replacement cycle begins to accelerate, this particular client was a marquee win.

We are also seeing rapid adoption among existing customers. Early feedback and usage shows that customers view Athena not as incremental functionality, but as transformational technology. As adoption increases, Athena learns from more data, outcomes improve and usage deepens, driving ARPU expansion and ultimately reinforcing the same flywheel that has powered our growth. That flywheel is powered by more than just Zeta's AI models. It's driven by the data and infrastructure behind them.

Zeta SuperGraph, our proprietary identity and intelligence graph, unifies data across the enterprise and enables a complete deterministic view of the consumer that we believe is difficult to replicate at scale. This is translating directly into wins where access to our data is a key driver for customer decisions. For example, our SuperGraph was instrumental in a win with a leading online retailer of pet products in the United States that serves millions of active customers with a highly personalized e-commerce experience, a broad assortment of over 100,000 products and a rapidly expanding ecosystem that includes autoship subscriptions, pharmacy services and pet health offerings. In addition, our proprietary data and the intelligence it generates was a key component in the expansion of a Fortune 100 telco client, expected to drive an 18x increase in spend with Zeta in 2026 versus 2025. As Athena brings that intelligence to our customers in real time, the impact of this data advantage only grows.

This foundation of data plus AI continues to power One Zeta. We are consistently seeing that the land, expand, extend model takes hold as customers begin with a single-use case and scale across the platform over time. That expansion is driven by the modern CMO mandate, do more with fewer partners, improve ROI and simplify execution across the organization. The result is larger commitments, deeper adoption and a growing role for Zeta as the marketing operating system and core infrastructure.

That momentum is showing up in the data. Super-scaled customer ARPU was up 21% year-over-year, well ahead of our target range. Net retention rate remained above our target range of 110% to 115%. And the number of super-scaled customers using more than one use case was up over 50% year-over-year at scale. It also creates a reinforcing cycle. Consolidation drives adoption, adoption drives results and results drive further expansion. This is the One Zeta model, and it continues to be a powerful driver of durable growth.

What stands out for me this quarter is the strength we are building across every part of the business. At the center of this is Athena, which is already beginning to change how our customers operate and how we compete. Together, our data, our platform and our leadership in AI are positioning Zeta not just to participate in this shift but to define it.

As always, I want to sincerely thank our customers, our partners and our shareholders for your continued support of our vision. And to team Zeta, thank you for everything you do. It was an honor to be recognized as a Great Places to Work for the third year in a row. This is a reflection of your hard work and collaboration.

Now let me turn it over to Chris to discuss our results in greater detail. Chris?

Thank you, David, and good afternoon, everyone. Our results, once again, demonstrated the durability, predictability and profitability of Zeta's growth. Revenue growth, excluding acquisitions and political candidate revenue accelerated for the fourth consecutive quarter to 29% in Q1, further cementing the durability of our growth and market share gains. Broad-based strength across the business is resulting in improved visibility, leading us to, once again, raise our 2026 outlook, underscoring the predictability of our growth. Even in doing so, we're maintaining our typical conservatism. And we also saw free cash flow conversion improved to 63%, generating $42 million in free cash flow, demonstrating the increasing profitability of our growth. These results surpassed even our internal stretch goals, coming in $26 million or 7 points above the midpoint of our revenue guidance for the quarter.

As I analyzed the strength of our quarter, what stood out was how balanced the upside contribution was. It was not 1 or 2 isolated benefits. Instead, in baseball parlance, it was a lot of singles and doubles, which in my opinion, is healthier. Here are some examples. In terms of revenue growth, excluding Marigold's contribution, approximately 14 points of growth came from existing customers and 15 points from new customers. From an industry lens, 9 out of our top 10 industries grew faster than 20%, with more discretionary industries continuing to be at the upper end, demonstrating why in tougher macro times, data-driven, lower marketing funnel, high ROI attributable marketing is paramount. And finally, as it relates to how customers use our platform, e-mail, connected TV, mobile and social all grew double digits, all while each use case, acquire, grow and retain also grew double digits.

Now let me dive deeper into our KPIs, income statement and balance sheet. Total super-scaled customer count grew to 189, up 19% year-over-year and an addition of 5 customers sequentially. This exceeds our Zeta 2028 model of 4% to 8% super-scaled customer count growth. Super-scaled customer additions were especially strong in advertising, marketing, travel and hospitality. Super-scaled customer ARPU was $1.7 million, up 21% year-over-year. This also exceeded our Zeta 2028 model of 12% to 16% ARPU growth. Strong ARPU growth in the quarter was driven by an increase in the number of customers using multiple use cases, which was up over 50% year-over-year, as well as customers using more than 3 channels, which increased 40% year-over-year. Both are great examples of the One Zeta sales motion working and how Athena can unlock more of the platform's capabilities for our customers to use.

The forward-looking sales pipeline is also robust, going into a season when Athena will be front and center at multiple industry conferences. In fact, Athena demos were a crucial differentiator versus incumbents and RFP competitors in each of our marquee enterprise and agency wins in Q1. And we expect Athena to play an even bigger role in adding to the sales pipeline, which is already up 40% year-over-year with a subset of discretionary industries up even more, those like retail, advertising, travel, restaurants, furniture and resorts to name a few. This outsized sales pipeline growth in discretionary industries is consistent with what we've seen in previous periods of macro volatility and is another proof point that in times of uncertainty, customers consolidate onto fewer platforms that can drive measurable ROI with AI-driven efficiency.

Now moving on to revenue mix. Direct revenue in the first quarter was 75%, above the 73% last year and in line with our target of 70% to 75%. Our GAAP cost of revenue in the quarter was 41%, a 190 basis point increase year-over-year and 50 basis points sequentially. The increase in cost of revenue was driven by new agency wins, driving a higher initial mix of social as a channel. This is consistent with the pattern of business we've seen and spoken to previously when new agencies platform on to Zeta. This is because we offer a substantially more efficient and effective solution for social and has become the first of many channels adopted by new agencies as they migrate. As new agencies scale over time, not only does their aggregate spend increase, but they do so by adding Zeta-owned channels like e-mail, display, video, mobile, CTV and others.

It also bears repeating, while social has a higher cost of revenue, it is still accretive to both adjusted EBITDA and free cash flow margins. Further, social drives high customer stickiness as well. In the first quarter, adjusted EBITDA was $66.1 million at a margin of 16.7%, 100 basis points lower year-over-year and $5 million better than the midpoint of our guidance. Marigold integration is progressing rapidly and tracking ahead of our expectations. We took aggressive steps in the quarter to execute operating synergies, which should begin to benefit our adjusted EBITDA margin in Q2 and into the back half of the year. At the same time, Marigold's revenue came in better than we anticipated, and we're seeing encouraging traction from the One Zeta approach of cross-selling Marigold's loyalty product along with Zeta's grow-and-acquire use cases to the combined customer base.

Another area we spoke about last quarter was becoming GAAP net income and EPS positive for the full year of 2026, specifically generating between $0.02 and $0.04 of GAAP earnings per share. Our first quarter results have us pacing towards the high end of that range. In Q1, our GAAP net loss was $13.2 million, an improvement from a net loss of $21.6 million in the first quarter of last year. GAAP loss per share was $0.06, coming in ahead of our expectations for the quarter with forecasted costs related to the integration of Marigold being the primary driver and not seen as recurring over the rest of the year. First quarter net cash provided by operating activities was $49.7 million, up 43% year-over-year, with free cash flow of $41.7 million, up 48% year-over-year and representing a margin of 10.5%. This represents a free cash flow conversion of 63%, a 270 basis point improvement from the first quarter of 2025. This also includes a roughly 13-point working capital headwind driven by longer agency payment cycles standard for their industry.

During the first quarter, we repurchased 1.5 million shares for $25.7 million and have approximately $138 million remaining on our share repurchase authorization. We expect to remain active buyers of our stock, especially at these price levels, subject to market conditions and other priorities. And we continue to make significant progress in reducing dilution and stock-based compensation expense. Excluding Marigold, our dilution in the first quarter was 0.1%, and we remain on track to achieve our normal course net dilution target of 3% to 4% in 2026.

Relatedly, with most of management's previously issued equity now fully vested post-IPO, Zeta's Board of Directors and Compensation Committee, in consultation with an independent compensation consultant, approved a new long-term equity incentive plan for management. This performance-based plan secures continuity of Zeta's named executive officers and management for 6 years and incentivizes management to achieve its long-term revenue and adjusted EBITDA margin objectives while adhering to its principles of lowering dilution, reducing stock-based compensation as a percentage of revenue and achieving GAAP positive earnings. Furthermore, named executive officers who received these incentives will not be rewarded any further equity for the next 6 years.

Now on to our increased guidance. For the full year 2026, we're increasing the midpoint of our revenue guidance by $30 million to $1.785 billion, representing a 37% growth rate or 22% year-over-year growth when excluding Marigold and political candidate revenue. None of our guidance increase is related to political candidate revenue, which we continue to assume will be $15 million in 2026 with $7 million in the third quarter and $8 million in the fourth quarter. Additionally, we continue to take a conservative view of Marigold, contributing $47.5 million per quarter to 2026 revenue for the remainder of the year. Our revenue guidance also includes minimal contribution from Athena. And as shared earlier, we have taken into account our typical conservatism of 2% to 5% in setting our outlook. For the second quarter, we now expect revenue of $420 million at the midpoint, $4 million higher than our previous guidance and representing year-over-year growth of 36% or 21% when excluding political candidate and Marigold revenue. For adjusted EBITDA, we're increasing the midpoint of our 2026 guidance to $397 million, up $6 million from our prior guidance and representing a year-over-year increase of 43% at a margin of 22.3%, an improvement of 90 basis points over 2025.

For the second quarter of 2026, we now expect adjusted EBITDA of $86.6 million at the midpoint, up from our previous expectation of $84.9 million and representing growth of 47% and a margin of 20.6%, up 155 basis points year-to-year. We are also increasing our 2026 free cash flow guidance to $235 million at the midpoint, up from $231 million, representing year-over-year growth of 43% and a conversion of 59% of adjusted EBITDA, which likely has upside.

And here's the broader point. A 19-quarter beat-and-raise track record is obviously something we're proud of and continues to demonstrate our consistency and strong execution. We also recognize the times we're in, specifically the need to underwrite investments in companies with strong free cash flow generation, durable revenue growth and share gains and demonstratable moats. Q1 was an excellent jumping off point for these emerging investor frameworks. Not only did free cash flow set a record in the first quarter, but we are also tracking to the high end of our 2026 GAAP EPS range of $0.02 to $0.04 and long-term 2028 targets. As it relates to durable growth, this was the fourth quarter in a row we accelerated revenue growth, excluding acquisitions and political candidate revenue. And in terms of exhibiting our moats, our marquee wins with enterprises and agencies this quarter came at the expense of legacy marketing clouds and legacy DSPs, where Zeta's proprietary data and Athena operating system were capabilities our competition could not match.

With that, I'll hand the call over to the operator for David and me to take your questions. Operator?

[Operator Instructions] And the first question comes from the line of DJ Hynes with Canaccord Genuity.

Congrats on a fantastic quarter. Nice start to the year. David, I want to ask you a competitive question. So obviously, there's been more public backlash against the Trade Desk and the agency ecosystem. But I think for those living in the marketing and ad tech world, like that's been going on for a while now, right? So 2 related questions here. Number one, like how much do you think Zeta has benefited from that dynamic? And then second, if the Trade Desk figures out how to get pricing right or at least make it more transparent, does this rebalance competitive dynamics at all? Or is the horse already out of the barn there?

Well, let's -- I mean, first of all, DJ, thank you. We appreciate it. Could not be happier with this quarter. And I think it really speaks to kicking off the year right and Athena really was a massive driver here. I want to separate the conversation about the agency and other technological platforms like the Trade Desk that are out there and struggling a bit because the agencies continue to thrive and they're not really having any issues from our vantage point.

And I just got back from 3 days at the POSSIBLE conference, where I did 54 meetings in 3 days, hosted 4 dinners and 3 cocktail parties, which is why I'm losing my voice going into this. I think that -- and I don't want to speak to any particular platform, but I think the horse is out of the barn. I think that organizations that have built workflow management tools that do not have proprietary data, they do not have proprietary native artificial intelligence are going to really struggle in this next evolution of where sort of marketing is going as it relates to intelligence. Because if you're not creating intelligence in today's world, you're not winning. And I think that we are a direct reason that a number of our competitors are either growing slower or shrinking as we take meaningful market share.

Chris, in his prepared remarks, was very clear about the fact that we had a number of meaningful agency wins in the quarter that will continue to run out through the rest of this year and into future years that are starting with social. We're starting to see those move over to programmatic and connected TV as well. So I think if you separate the agencies, which are doing well and thriving from the technological platforms that have based their business on workflow management, I think they are going to struggle, and we are going to continue to beat them handedly in the marketplace.

Yes. Perfect and helpful color. Chris, I want to follow up with you. So David gave a bunch of great anecdotal data points around Athena and the early success there. The product is not explicitly monetized, right? So what are the signs that we all, as investors, should be paying attention to from a financial perspective that will signal to us that Athena is moving the needle for Zeta?

Great question, DJ. I'm glad you asked. There's a couple of leading indicator data points that I think you can already begin to look at. So as part of the press release, one of the data points that was called out was a 7x increase, and this is just in the first week of Athena's general availability. We saw a 7x increase in the type of -- in the amount of agentic interactions on the platform, coupled by 60% of the AI usage on our platform being driven by Athena. How that should ultimately translate to the usage part of our revenue can be seen through ARPU expansion, some of which you already started to see. So if you look at ARPU in the quarter for super-scaled customers, it was $1.7 million. It was up 21% year-over-year. But if you look underneath that, what drove it are exactly the dynamics that Athena was engineered to be able to do, which is to make more of the platform available and visible for the customers to be able to exploit. If you look at multiple use case customers, it was up over 50% year-over-year. If you look at the customers that are using 4 or more channels, that's up over 40% year-over-year, which again are not just great examples of Athena as an unlock, but also Zeta working well.

And by the way, she's just getting started, DJ.

Yes, totally. Congrats, guys.

Thanks, DJ.

And the next question comes from the line of Gabriela Borges with Goldman Sachs.

David, I want to ask you about the people and process part of Athena, meaning the technology you've demoed, it clearly is able to do a huge amount of knowledge work. My question for you is, how do you then change the end user behavior? What does the training and enablement look like? How do you encourage more people to use it once your customers have already decided to adopt it?

First of all, Gabriela, what a great question. First, let me say that we were incredibly proud that we were able to make the product not just generally available on time, but available to 100% of our enterprise clients, which was not a small task. At the same time, to your exact point, we have a learning and development group that is literally purpose-built to train our clients and get them up and running on this new product. And they've already done. Our top 30 clients have been onboarded through that group, and we're going to be adding all the other clients as we continue to expand out.

The other thing that's really important is we're doing a weekly leaders -- I'm sorry, a weekly learning and training program to all of our clients that's virtual, recorded and they're able to then watch it at their convenience inside of the platform when they want to. But we're doing sort of a ask Athena question of the week. Every week, a new question that you could ask Athena goes out to all of our customers so that they can begin they process of using her. And I know I'm sure you've seen the demo, you know how incredibly intuitive she is to use. So what I would say is we're really focusing on it from a relationship management, learning, development, both in-person, virtually and weekly follow-ups. But the intuitive nature of her is, I think, one of the reasons you saw her so powerful. Just in the first week she was live, Athena drove 60% of all AI utilization across our platform. That is off the charts for a new product from an adoption perspective.

Very good. And Chris, the follow-up for you on inference cost. So Athena has pieces of Zeta proprietary technology. And then I believe you have some third-party technology in there, too. How do you think about managing those inference costs or optimizing those inference costs? And then same question for your R&D team, your engineering team. We're at the stage where we've been through more token usage is generally better, but also can sort of outrun budgets very quickly. How do you think about managing that internally?

So Gabriela, I'm going to take that one. Sorry, Chris. First and foremost, as the world moves from large language models to inference-based AI, our platform is purpose-built for that as the operating system and infrastructure for our clients. The vast majority of our queries, Gabriela, are done on our own platforms, on our own data. So we are not buying tokens as we roll this out to our customers. It's fully embedded, which is one of the reasons I think you're seeing us project substantially higher growth to profits and cash flow than we are even to revenue. We have put ourselves as sort of the perfect spot as the market moves to inference-based AI.

As it relates to our internal consumption, we have built a platform called SPADE. Don't ask me what it stands for. It is an anagram. But the reality is that SPADE is a tool that we custom built inside of Zeta and is being utilized by a very large percentage of our engineering team, where effectively, an engineer would go into SPADE, they would create the construct for the code they are trying to develop. SPADE would then automatically choose the most efficient and best large language model to do the coding itself. So if it's security-based, we might choose Claude. If it's general coding based, SPADE might choose ChatGPT. If it's complex publishing, SPADE might choose Gemini. Now of course, Cursor is sort of at the center of this as we think about where that's expanding.

The code is then auto generated by the LLM, which is the only time we utilize tokens. Everything else is sitting on our own platform, our own cloud. The LLM creates the code. It then goes to a program called Zippi because obviously, we have great nomenclature capabilities. And Zippi automatically QAs the code on our platform once again. Once it's done, it sends it to one of our senior architects. They review the code one more time, and they can make it generally available.

To put it in perspective, Gabriela, at the end of the first quarter, Zeta was already driving 75% automated new code creation. I believe that puts us even above Google as it relates to that. And the pods working on Athena today, I know for a fact are up from a productivity perspective between 400% and 600% year-over-year from an output and productivity perspective, all the while, the vast, vast majority of the compute and of the tokenization is on our own platform. So as you look at our growth, we will not experience some of the constriction of margin or additional CapEx. We've already allowed for everything in the projections that we've got, and we're very, very comfortable with where we are externally and from an engineering perspective.

And the next question comes from the line of Arjun Bhatia with William Blair.

Congrats guys on a very strong quarter here. David, I have 2 questions, maybe I'll just do them one at a time. The first on awareness. It seems like the customers that are using it are getting great value out of it. It's early, but for this to have a material impact, for the company as a whole, you have a fairly large revenue base. Like how do you roll this out to all your large customers? Where is it right now in terms of customers having awareness and knowing what Athena can do? And how do you sort of plan to progress that?

Yes. So great question, Arjun. First of all, from an awareness perspective, I would say that our marketing team today is doing the greatest job it's ever done in the history of our company. I just came back from the POSSIBLE conference where you couldn't walk 5 feet without seeing the brand Athena and without seeing Buy Zeta. And it was really exciting. We did an Athena Suite. We did a Zeta Cafe Powered by Athena. And we're starting to see that we're moving to that next evolution of our brand where it's sort of moved to it's getting the must-have data in our industry. And I didn't think I would say that this early.

As it relates to internal awareness, we have built an internal learning and development team, which is doing nothing but training and onboarding our clients. One of the things we're going to be rolling out in the next few months, which I'm super excited about, is an Athena certification. We're going to certify the individuals who work for our clients on Athena utilization. They'll get a full certification that they can put into their resume, and we're very excited about how that's going to be rolling out. So we're also doing sort of a hint of the week, tip of the week, question of the week. It's going out to all of our clients. I would tell you, in all of the years I've run this company, which is a long time now, I have never seen a faster uptake of a technological product that we've rolled out, and it's really been exciting, Arjun.

Awesome. That's great to hear. And then maybe switching gears from Athena for a second. Marigold, that also looks like it was off to a strong start. I think you beat your sort of Q1 target on that front. But where are we on the cross-sell there? And what's the early traction you're seeing on, I guess, the 2-sided cross-sell, both into your base and into Marigold's base?

Arjun, I'll take that, and David will wrap it up also. So a couple of places where you can see where it's evident that the cross-selling is working. So we talked about the number of multi-use cases. It's nicely contributing to the growth that we've seen across the base of super-scaled customers. But I think more broadly, if you look at the areas that we talked about being purposely conservative around Marigold, it was around the potential for their SMB and mid-market customers that were on the enterprise platform we anticipated churn. We're not seeing as much as we thought, which is good. There were products that -- and geographies that we thought we would have less growth on and would also see churn. That hasn't happened yet. And then just more broad normal churn at the enterprise level, and it stayed healthy. And by the way, a lot of that is being driven by Zeta's interactions with those customers and partnering with Marigold's people.

So it's been really interesting, Arjun. We've seen a meaningful uptick from existing Marigold clients with us integrating the data cloud into the platform. So the first thing we did and we had it done within 90 days was a full data cloud integration into their platforms, which allowed clients to begin to access data sets that they've never had access to before. So we've seen meaningful growth there.

As it relates to cross-selling, we're really -- we're making progress, but not a lot of that is in the numbers yet. These products are complicated, and they're very big. I think you'll see more of that as the year progresses. But I think -- I mean, to say we're very excited about how well we're performing with the asset would be an understatement. And a lot of that today is a result of the data cloud integration.

Now whether you want to consider that a cross-sell because we're bundling the Data Cloud in to drive additional utilization or not, that's up to you. But to us, as we're rolling out loyalty to all of our global clients, and we're starting to take sell-through and roll it out to the Live Intent clients and all of the different things we're doing, that's in the early stages, and I think will drive meaningful growth in the future.

And the next question comes from the line of Jack Nichols with KeyBanc Capital Markets.

Maybe pivoting back to Athena. I was wondering if you could walk us through the early adoption trends among the enterprise customer base, specifically around how they're deepening engagement with the platform and then existing use cases today? And then I've got a quick follow-up.

Well, first of all, welcome, Jack. It's great to have you on coverage. We really appreciate you. Second, we have been really blown away by the early adoption of Athena. We made it generally available to 100% of our enterprise clients, and we saw a 7x increase in agentic interactions from our clients in the first week of Athena alone. So we think of that as pretty good. 7x is always something we aspire to. But our long-term goal is for Athena to be the operating system of our clients' businesses, and we're just getting started on that. But early adoption has been very, very exciting.

That makes sense. And then pivoting quickly to Marigold and thinking about the recurring revenue mix, as those customers adopt the Zeta platform, should we expect that mix to trend down or up over time or kind of remain in line with the 2025 60% expectation disclosure?

Jack, it's Chris. I'll take this. And as David said, welcome. It should go up is the short answer. And I think a really interesting proof point that you'll see in the Q tomorrow is just how substantially RPOs went up quarter-to-quarter. They went up $66 million just from fourth quarter to the first quarter. Obviously, part of that is Marigold, which then helps with visibility. But I think an interesting thing for the audience here to understand is another large piece of that was not only these marquee wins that we talked about with the apparel retailer and the e-commerce pet retailer, but it was also agencies beginning to now also sign long-term committed contracts.

That is an exciting proof point for us. It adds to the recurring revenue, which then obviously adds to visibility, which both of those came into our confidence to be able to raise the guidance that we did on the top line by $30 million while continuing to keep to our 2% to 5% conservatism.

And the next question comes from the line of Clark Wright with D.A. Davidson.

Awesome. I wanted to maybe quickly touch on the consolidation story. You noted on one of the marquee wins this quarter that you consolidated 4. And I recognize over the course of the last few quarters, you mentioned consolidation being a key piece. Can you talk about the use cases that beta continues to solve for and how you see that expanding over time?

Yes. Thank you, Clark. Listen, when John and I founded this company, I don't know, 18, 19 years ago at this point, our vision was to put everything a marketer needed into one user interface with one reporting infrastructure. And I would tell you that because of Athena, I think we are finally there. And our ability to consolidate anywhere from 8 to 12 different vendors into one user interface and one reporting infrastructure has never been stronger. In the case of this global company because it's a retailer and a manufacturer of their clothing, we displaced what I think many people think to be certainly the longest serving of the marketing clouds. They made, I think, their acquisition first in the space as they built their marketing cloud. And in fact, this particular client used that company for everything. They consider themselves a you know what shop, so to speak. So decoupling their marketing cloud from everything else they were doing, I think, was a very difficult decision.

We also displaced another competitor of ours who tends to be more focused on mobile. They tend to be a little easier to displace because they're so singularly focused on mobile. And neither of those companies brought any data or any activation capabilities to task.

When you're working with one of the large marketing clouds and you displace them, you're almost always also displacing a professional service provider, who they have to then spend millions of dollars on to customize their platform versus our platform is pretty much ready to go from a cloud perspective. So that would be a really good example of a -- and we see this as one of the most important wins in our company's history, and it goes back to not just our ability to consolidate other vendors, but to do everything that each one of those point solution does better than they do while simultaneously putting everything into one place.

Got it. That's helpful. And then if I could just add one more. Over the long term, you talked about increasing wallet share with customers. Do you think AI accelerates the rate of share capture, increases the total wallet share or both?

I think both. I mean, remember, the single greatest way, Clark, to get market share is drive meaningful return on investment to your clients. The Forrester study that came out that said we have a 600% return on marketing spend, we're seeing early adopters of Athena at a materially higher return on investment than even that. The higher we drive return on investment, the more wallet share we're naturally going to get. And as you know, our existing global super-scaled customers will spend well over $100 billion to $110 billion on marketing this year. And at the middle of our range, we'll have, call it, 150 to 170 basis points of wallet share. I believe we can get that to 700% to 1,000% of their wallet share in the years to come. The key will be driving better return on investment. Artificial intelligence, specifically Athena, plus our data as a moat into our business is going to drive return on marketing spend up meaningfully, which we think will then drive wallet share.

Our next question comes from Jason Kreyer with Craig-Hallum.

Great job. So I wanted to stick with the point on wallet share because you announced some major wins and you've announced some major wins over recent quarters. But I'm curious, when you look at the aggregate data representing somewhere less than 2% of wallet share, how big of deals are you winning today? And how big a deal do you think you can win over time just in terms of the wallet share of those customers?

It's interesting, Jason. I would say the last few wins we've had have been at a comparable wallet share to our current wallet share, but the clients are spending 4 or 5x as much per year on marketing and CRM. So they represent some of the largest deals we've ever done right out of the gate. Does that make sense just mathematically?

At the same time, what we're starting to see is some of our clients who have been on the platform for 2, 3, 4, 5 years are getting to that 7% to 10% of wallet share and higher. And we're using that as a road map for how do we take new clients there. So the wins are much bigger than they've ever been, but I'm not sure they're much bigger wallet share only because the companies are so big that we're winning. Now that will give us meaningful upside as they're on the platform, and Chris does a much better job than I do, talking about how ARPU grows the longer a client is with us, and these clients are starting at probably the highest ARPU we've ever seen clients starting.

That also drives, Jason, with our sales pipeline. So we talked about its growth. But if you look at deal sizes and particularly the annual contract value of deals are up pretty substantially year-over-year.

Perfect. Maybe one quick follow-up, David. You've been doing AI for a long time, but it seems like the release of Athena has certainly put you in a different conversation within the AI industry. I'm curious, how has that translated to conversations with customers? And like do you feel like Zeta is becoming more of an AI thought leader in the marketing ecosystem and that's driving that engagement?

It's interesting, Jason. In some ways, being a native AI company has been complex for us over the last few years because everybody is rolling out shiny new products, most of which are not real, but most of the people are rolling them out. And we've always been seen as sort of like AI is under the engine.

Athena is the hood ornament to what we're doing as a company. She is now us announcing ourselves with authority that we are not just an AI company, we are the leader and the disruptor in the AI space. And with the launch of Athena as a marquee product, it has changed the game for the way people are seeing us.

And I will tell you, the 2 client wins we talked about in the prepared remarks, there is 0 chance we would have been in the room if we had not launched Athena or started talking about her at Zeta Live. And there's -- I don't think a chance we would have won these accounts without Athena showing that we are the leader in artificial intelligence as it relates to marketing.

From an internal perspective, we're also one of the best users of AI. I mean back to what I was saying around the SPADE internal platform we've built. If you had told me a year ago, we'd be auto generating 75% of our own code while simultaneously driving the type of quality products we're driving, I would have said that's just not possible. SPADE has made that possible. And it's really been very interesting how we've done that in an environment where we're still using a very de minimis percentage of tokens versus what many of our competitors are doing, which is going to allow us to continue expanding our operating margin as we've done over the years.

Our next question is from Matt Swanson with RBC.

I have my congratulations for the quarter. I think the metric that really jumped out to me was the increase in multi-use case. And I know that's something we had kind of talked about with Athena and its ability to kind of create this organic expansion motion. Given that, that 50% increase was for the full quarter, like is Athena a real part of that? Is there other parts of your go-to-market driving that? If you could just kind of touch a little more there.

The great news is Athena is just getting started. So we had a great trajectory going into our launch. Now I will tell you, every client that was on the beta became multi-use case. So it was -- but that was not a lot of clients, right? So as she rolled out to generally available, we saw an uptick there. But I think that's continued upside to growth in multi-use case. And the One Zeta team continues to just do an exceptional job. I'll remind you, Matt, we really started on the One Zeta mission just 18 months ago. So you've got a massive tailwind coming out of the work we've been doing there. And then I think Athena is going to supercharge that.

And Matt, I think the reason why you picked up on it, but for others, empirically, what we know is that when customers use more than one use case, their ARPU is 3 to 5x greater. So I think you're right on that being an exciting data point.

Yes. No, I appreciate that. And we'll make sure to take note that 100% of Athena users will become multiuse case. That's what I heard.

I wouldn't go quite there. I mean we -- obviously, that's the goal, Matt, but we certainly didn't say that just yet.

Yes. The other one I want to talk about is the independent agencies. I know you called out advertising as a key vertical for you guys. I think your willingness to kind of share the credit with agencies and allow them to white label some of your technology has been part of the reason you've been so successful there. I guess with Athena, how much more can that help you in those deal environments as a lot of these independent agencies are trying to compete with the big holdcos and so on?

One of the key wins we had, Matt, in the quarter was with a large independent. If you look at business done a year ago with them was 0. Business done within this quarter was 8 figures with Athena being, again, something that was visible to them as something they could also exploit for their benefit. The same was true with a very large new agency that began piloting Zeta in 2025. The spend was material, call it, a little less than $2 million, but that new agreement that was signed is more than 10x that size. So both the independent as well as the large agency continues to have a lot of runway. In fact, amongst the 5 large holdcos, the number of brands we're working with year-over-year grew by 50%.

And I just want to say, Matt, we're actually big fans of the agencies. They provide incredible services to their clients. And we've had clients approach us to go direct. And we always try to bring the agency back into it because we think it's a very healthy relationship when it's the 3 of us.

And listen, we're good if the agencies make their money because they're providing meaningful services. But as it relates to our business, I'll remind you, none of the agencies really focus on the retain, which, as of last quarter, is about 60% of our business. So we have real greenfield opportunity there as it relates to the activation, which sort of create customers, monetize customers. We're very, very happy to partner and give the credit to the agencies because they've built incredible businesses, and we're very excited now to be working with pretty much all of the large holdcos. I think now it's all. And well, certainly the biggest ones. And then to be partnering with a select number of independent agencies. There's a lot of them out there, but we want to work with only the best.

Our next question comes from Naved Khan with B. Riley.

This is Ethan Widell calling in for Naved. To start, can we talk about the ideal customer profile for Athena. I'd imagine there are 2 kind of distinct value propositions there, a, where Athena can drive efficiency gains for your larger enterprises that already have sophisticated marketing teams and whatnot; b, more small and mid-market players where Athena creates access to capabilities that these customers don't necessarily have in-house. So like which of these is management really seeing more of early traction-wise? And what's kind of the ideal customer size that you're leaning into with your early sales motion?

Well, it's interesting you put it that way. I mean, today, to be honest, Ethan, we don't focus on midsize. We're really just focused on very large enterprise, although Athena opens up the midsized market to us at some point because you're very intuitive to understand that the cost of layering Athena out to midsized companies is so de minimis to us that would allow us to move into those -- that vertical -- or I'm sorry, into that sort of category without having to meaningfully hire people to do it. But today, we focus solely on very large enterprise.

So I would tell you the 2 things very large enterprises have really focused on is, a, and you're totally right, efficiency. What they're finding is it takes 70% less labor to manage the Zeta marketing platform with Athena than it did with hands-on keyboard. So you're effectively able to take 70% of your marketing workforce and retask them into other functions where they can be more valuable to your organization. We're also seeing that because -- and this is something I talk about a lot, Ethan, but when you buy software, whether it's us or it's Bloomberg or somebody else, you're buying a stealth fighter, right? We're all spending to build a stealth fighter of a platform. And most of our clients know how to fly assessment with -- I mean think about a Bloomberg terminal, the vast majority of their customers only use 5% to 10% of the capabilities. As you look at our platform, being able to fly that Cessna, we're still delivering a 600% return on marketing spend. As clients are able to use Athena as their copilot, they can get right into the cockpit of that stealth fighter, and they can then fly the entire platform, which is driving meaningfully higher return on marketing spend than even that 600%.

Got it. That makes a lot of sense. And then coming out of first quarter, I think you mentioned 9 out of 10 top industries grew more than 20%. I know you spoke to some customer consolidation being a benefit there. But are there any verticals that you see showing any signs of softening, particularly anything sensitive to the macro and geopolitical risk going on right now on the discretion?

Yes. Short answer, no, Ethan. The 9 out of the 10 were effectively say 9 out of 10 that ended last year. The 1 out of 10 that wasn't growing over 20% is 4% of revenue. So it really gives you a sense for the vast, vast majority of revenues on all of the verticals we support are performing in a very healthy way.

Our next question is from Terry Tillman with Truist.

I'll just keep it to one question because I know we're running over time. And maybe I'm getting too far ahead of myself, but I like hearing about 40% increase -- 40% plus increase in the sales pipeline. And I think you said your discretionary markets where you have a lot of activity is even higher. Is it too early to start to say because of the emphasis on agentic AI in general that's in the market, plus you have Athena that's now credibly in the market and in production, could it start to tip the scales and move in some of this funnel activity faster and you actually close new deals quicker? Or is it just too early or I'm just way too optimistic?

I don't think you're too optimistic. But I do think it's -- from an expectation setting perspective and frankly, from a data-driven perspective, and this is a multi-quarter statement I'm about to make. Our deal cycles in good times and in less good times have stayed consistent. What we're seeing is more opportunities in RFPs, many more at-bats than we were given a year ago and certainly 2 years ago. Those by nature take longer. But again, our strategy many times is to work around those processes through pilots and proof of concepts. Those deals are getting bigger, as David said. So yesterday's $100,000 pilot is today is $1 million. But I wouldn't say right now, it's an accelerant, but it's in addition to the pipeline.

And I would concur. But I do want to be clear, Terry, we're getting at bats that we would have never gotten a few years ago. So it's sort of -- it's working really, really well.

Thank you. This concludes the Q&A session and our call. You may disconnect your lines at this time, and have a wonderful day.

Awesome. All right. Thanks, everyone, for joining us at day 1 of the Morgan Stanley TMT Conference. My name is Katie Kuser. I'm on the software research team here at Morgan Stanley. Super excited to be joined by the Zeta Global team, David Steinberg, CEO; Chris Greiner, CFO. Hey, guys, great to see you. Thank you.

Great to see you, Katie. Thank you for having us.

Thanks for being here.

Yes. It's great to be here.

Awesome. A quick disclosure statement before we get started. For important disclosures, please see the Morgan Stanley research disclosure website, morganstanley.com/researchdisclosures. Awesome. So with that, thanks, guys, for being here. Great to see you.

Great to see you.

Maybe for investors that are newer to the Zeta story, just provide a quick overview of the business. relatively complex. So maybe talk to who the end customer is. What about the Zeta portfolio lets you kind of uniquely straddle both marketing and advertising? And maybe just why the business model is differentiated relative to some of the legacy martech players that we all know. we only have 34 minutes.

So let me start by saying Zeta has built a software and proprietary data cloud platform that helps very large enterprises more cost efficiently manage their customer acquisition, customer retention, customer monetization. 51% of the Fortune 100 and 24% of the Fortune 500 use the Zeta Marketing platform today. That is not an aspirational number. That is the number that we work with. And -- what we traditionally do is by combining everything a marketer needs into one user interface with one reporting infrastructure, we're able to deliver a substantially superior return on investment. A recent Forrester survey or report, I should say, showed that for every dollar spent on the Zeta marketing platform, we return 600% on their ad spend as it relates to returns. So I think that's 100% to 200% better than our next closest competitor.

Awesome. And maybe just to hit on kind of the AI debate at the top, right? This is a question that's on all of investors' minds, whether AI is representing a threat to the industry, a transformational opportunity for legacy kind of vendors here. So maybe Zeta has been building AI into its platform for a number of years. You're doing a lot on the innovation front with Athena, which we'll get into. But maybe just high level, like where do you see Zeta positioned on the AI threat versus opportunity spectrum? And I think kind of the key question is what gives you confidence in the durability of the moat going forward, just given how fast the kind of tech?

I mean, obviously, there's this new, what I would call, silly narrative that large language models are going to disintermediate all enterprise software. And I guess I joke at sort of the silly Wall Street narrative du jour. There tends to be one every year or 2. As it relates to Zeta, we have 3 massive moats in our business. First and foremost, we have 552 million active people who are opted in our data cloud today with an average of 5,000 to 7,000 data elements per person our first-party tracking pixel sits on 1 trillion pages of content and ingest trillions and trillions of proprietary marketing signals that synthesize to a deterministic individual that we have never and would never share with any large language model.

Second, in order for our clients to operate with us, which include some of the largest companies in the world, as I've said, 51% of the Fortune 100, we take 100% of their first-party data. We ingest it into a consumer data platform. We then merge our data with it to enrich it. I don't see any of the Fortune 500 companies delivering their first-party data to large language models anytime in years to come.

And then three, we have a 600% return on investment today. Our clients don't look at us as an expense to be disintermediated. They look at us as a revenue source. We are a revenue center for their businesses, and we are driving meaningful growth into their businesses.

And then fourth and final answer is working with a Fortune 500 customer, Katie, very difficult from an onboarding and management perspective, you have to get through their data security groups, data privacy, procurement, legal, accounting, CIO, CTO, CMO. That is a very difficult skill set to build that we have really become experts at over the years. And it took us a very, very long time to get there. So data, return on investment and the ability to operate inside of very large enterprises is a massive moat to our business.

I'll finish by saying we do believe that the large language models are going to massively benefit our business. So -- as I like to say, I started my first company at 21 years old in 1991. I was the youngest person in the room for the first 20 years I ran businesses. I am now universally the oldest guy in any room I walk into. There are some exceptions. But the reality is that teasing a friend.

The reality is that when you think about it, I lived through the mobile era that was going to destroy technology. I lived through the dot-com area where the Internet was going to destroy Walmart and JPMorgan Chase. I lived through the beginning of cloud computing, which everybody the difference between the winners and the losers from my vantage point, has always been the ability to create intelligence Companies that create intelligence and outcomes that adopt these new technologies.

And as you said, we adopted artificial intelligence in 2017. We started working with it back then. When we went public in June of 2021, our banner on the side of the New York Stock Exchange said data plus AI equals intent. Everybody was asking me, who's Al and why is he in charge of our data strategy. That's how sort of far back we go in AI. But we've announced a major partnership with OpenAI, where we're using them to be the voice foundation and the conversational super agent inside of athena, but it's all our models. It's all our data that's training it. We use Anthropic inside of our engineering team. In fact, our engineering team today is 125% more productive than it was just 12 months ago. Now it delivers 150% increment, but 25% of it, you have to Q&A out, right? So -- but the net 125 is very, very strong. We use Microsoft tools. We use Git. We're sort of using everybody across the board to drive productivity. And I think that this is going to be a renaissance for Zeta.

Yes. Yes. Great context. I guess, Chris, I want to kind of bring you in and think about how this translates to the model. Q4 results, very strong last week, growing 28% on a normalized organic basis, guiding to 26% kind of sustaining that 20% growth again. I wanted to ask in the context of how you kind of laid out a framework at your Analyst Day late last year, durability, predictability and profitability of your growth. I thought that was a very thoughtful framework.

It's kind of the quality that investors are looking for. So maybe just talk through how you kind of exemplified that in '25 and how you're thinking about it going forward?

Yes. We used to have a metric of how many straight years we were growing over 20%. We've now added the 3 straight years of growing over 30% on the top line. It's actually 28% even organically on a compound basis over a multiyear period. So I think the ability to show that our market is growing, call it, roughly 10%, we're growing 2 to 3x that consistently. So that puts us in a durable take share position. On the predictability of our business, I mean, it's one thing to beat and raise because you could do that through setting low expectations and or low, low expectations and doing kind of okay. We set growth every year at least 20%. And as you said, we surpassed it by giving ourselves that typical, which we disclosed a typical 2 to 5 points of buffer. So we try to demonstrate through our track record, how predictable our business is. But we also give the metrics that allow us to be predictive in our models to investors. So over 90% of our revenue comes from customers that have been with us over a year. We show investors how those cohorts behave over almost now 5-year period so that you can do the same level of modeling that we do internally.

And then on the profitability side, it was record adjusted EBITDA, which is great. But as a company, we've more and more anchored to free cash flow. It was a record free cash flow margins and a turning point in the company getting to positive GAAP EPS, not just for the quarter but then being able to project it forward for '26 is getting to at least $0.02 to $0.04 of positive EPS. And I think that's just kind of us running from here.

At some point, people will start to give us credit for visibility, right? We've been public for 18 quarters, we've beat our guidance and raised guidance 18 consecutive quarters. So we're obviously -- we have at least some level of visibility into the business.

Yes. Definitely, we'll dig into some of those points that you brought up, Chris. But 1 of the other ways we kind of look at the share gain is by wallet share within your customers, often talk about kind of addressing 1% of the available marketing, advertising, wallet today with potential to kind of drive that up. What are the key strategic initiatives we kind of talked to the impressive ROAs, but anything else that you can kind of highlight on the strategic initiative side to drive that out.

Yes. So to be clear, our 603 global enterprise clients spent $100 million in marketing last year, and we had 1.3% of that wallet share, put us to about $1.3 billion in revenue last year. We're projecting $1.755 billion this year, up from the 1.3% last year, which would -- and our clients are growing about 10% a year. So you would say that grows to about 1.6% to 1.7% of wallet share. Our long-term goal is to get to 10% of wallet share or build a $10 billion a year business with a 30% operating margin and 75-plus percent of that flow into free cash flow. We're not going to do that over the next few weeks, but we do think we're going to do that over the next number of years.

What we're seeing is that the higher we drive the return on investment, the greater the percentage of budget that our clients move to us. And I think the next step function in return on investment is going to be the launch of Athena. Athena, which is our conversational super intelligent agent, say that 3x fast, is really a conversational voice platform that allows you to manage the Zeta marketing platform. So if you think about it, we've built an F-22 fighter jet at Zeta but our average client knows how to fly Ascena. And they're flying that testament they're returning 600%, but they're not using anywhere near the capabilities of the fighter jet. Athena is going to be our clients' copilot in managing the fighter jet. So you'll be able to say to Athena, Athena, I'd like to create 2 million incremental customers this quarter. I'd like to simultaneously lower my cost to create a customer by an average of 7%. What new data sets am I not accessing that I should access to do that or what new channels can we experiment to get there.

Not only will Athena speak back to the client, it will change the entire user interface to show the answers. By the way, there's great demos of this on our website if you want to see it.

The clients that are already using it in beta are seeing a substantially higher return on ad spend than the 600% we're showing, and the best quote I was given that it is totally and completely revolutionized their workflow. So the ability to speak in a conversational way with the platform have it answer you, have that interface then change the platform, be able to say, yes, Athena, I like those new data sets. I like that channel, let's start the activation, but I don't want to start with $10 million, I'd like to start with $500,000. And I have to be out of the office for the rest of the day. Could you e-mail me hourly with the return on investment, so I can track it remotely, and we can make sure it's staying on track before I expand this. That's all available in version 1 of Athena, which will be generally available by the end of this quarter.

Awesome. Maybe taking a step back and thinking about the data asset that feeds a lot of this roast goodness. Very robust proprietary database. Maybe talk us through what having this database does for you? How is it compiled? And then when we think about the breadth of the data set, definitely very wide. But when we think about the depth of it, right? How do you guys think about the need to kind of go out and acquire more data? Do you feel like you have enough to keep delivering that insight?

Well, so first of all, our data cloud which has 552 million globally, people opted in, 242 million in the United States. We touched 2 billion people a quarter. We just don't track them because they're not opted in. We do get there -- we do see some of their data from a modeling perspective. We have 20 different platforms that plug in to publishers that we partner with the publishers. We give them software that makes them more profitable, allows them better interaction with their end users, allows their end users to share their data out and drive large volumes of traffic to the publishers, and in exchange, they put our first-party tracking pixel on every page they host. They host our Java script on every page and then a host of other things that we do.

So what I would tell you is today, we have pretty much every credit card transaction, we have all of their psychographic, all of their demographic. All of their web behaviors, searches are all synthesizing in for those 552 million people. As it relates to, is it enough? Listen, some data isn't valuable until 7 years later. Some data is worthless in 10 seconds. So the more data we can ingest, the more powerful the models can be and because we never share our data with any large language model ever, it's proprietary to us and it's a major moat to our business.

What I would say as well is, whenever we look at an acquisition, when we think about buying companies, we bought 18 companies in 18 years. I'd say it's highly probable there will be in 19. We look at data sets and we look at what's there. And when you think about the most recent acquisition of Marigold, where we picked up some unbelievable enterprise assets, you picked up Geodigital, you picked up Selligent, you picked up sale through. But I'd say the most valuable is the loyalty program, where many Fortune 500 customers are currently using us for loyalty. That is now at giving a SKU-level transaction data to train our models on. And my entire goal is to continue to drive a greater return on investment. My goal is to get to an order of magnitude, return on investment for our clients, 1,000%, and I believe we can do that over the next couple of years as it relates to our data sets, the evolution of our internal AI, partnering with third-party AI partners, and I think Athena will be the tip of the spear.

And maybe talk a little bit about the 2 platforms that you have to activate this data, direct integrated. Maybe talk a little bit about channel expansion.

So I want to be clear. We have 1 platform. So you asked the right question, but we have 1 platform. We have 1 user interface, 1 reporting infrastructure. The SEC mandated that we reported in 2 separate segments. One we call on our platform. One is our integrated platform. Our integrated platform is mostly our partnership with Meta and others where we match the Zeta ID to the Meta ID. I don't know really anybody else in our industry who does that. And listen, Meta takes a disproportionate percentage of the revenue as they should, which makes us even more valuable to them. As it relates to how we sell it, I would tell you that when we started with our agency holdco clients, they didn't have a solution for seamlessly managing their social media marketing. Most of the competitors in the programmatic space, they're just focused on the open web, and they're all trying to figure out -- they're all trying to figure out connected TV, whereas we came at it with a fully integrated solution that included social, mobile, display, online video, messaging and connected TV. When a Client activates through us using our data and our setup tools to a third-party walled garden that we partner with, we count that as integrated. Whereas on platform, it's going directly through us to the publisher.

Right. And I think the kind of next set up for why Athena can be so interesting is when we start to think about the cohort progression right that Chris were talking about early. So maybe when you are thinking about the use case expansion with your customers, what are you seeing there? You talked to an 80% kind of increase in incremental use case expansion on Q4. So maybe what's driving that strength in the use case adoption?

Yes, it's interesting. Outcomes, better outcomes, but we just conducted our most recent NPS survey. And what the survey comes out almost indisputably is the more our customers use what's available on the platform, whether that's more channels on or use cases or more of our data, the happier they are. Our ability, and I think it was seen through our net revenue retention rate of 120%, which was coming off a prior year record 114% is a good indication reflection of that usage that happiness that loyalty of the customer. So what's been driving that, to your point, for most part, up until 2024 was channel expansion. So we're getting an average of, call it, 3 channels per skilled customer. This year, 2025, I should say, was the year in which we saw an inflection point in use case adoption. That's important to our financial model because when customers use more than 1 of our use cases, they spend roughly 5x more. And that could be going from retention to grow or retention to acquire or any different direction.

We are now at a point where in the most recent quarter, 80% -- so 80% growth in number of use cases, greater than 1, which reflects almost 1/4 of our total customer base, and that's up from, call it, 13% of our customer base using more than 1 use case a year ago. I think for us, the 1 Zeta sales motion, which we're organized, all sellers can sell any channel, if you will, on the truck. But we do have them organized by use cases, that's how our customers, for the most part, organized. They have existing customer set of technologies and people and new customer acquisition set of technologies and people focused on that. We have a thin layer of -- think about it as fighter pilots that sit above all of those use cases that are very strategically going at existing customers and then pro-market to where we see we can add immediate value by getting them to use more than 1 use case.

And if you think about it, when a client uses us for customer acquisition and then chooses to add retention, the data from acquisition informs retention. Then the data from retention informs monetization, which then both of those inform acquisition and the return on investment, not just return on ad spend, the return on investment goes up exponentially when you use us for all 3, which is why they spend 500% more. We actually discovered this almost by accident. When we looked inside of the NPS score a year ago, and we said, wow, we better get behind this. And we brought in a gentleman named Ed C, who ran the Chief Marketing Officer practice for McKinsey, very difficult to get a practice leader out of McKinsey, but we brought him in his technical title as Chief Growth Officer, but I call him Chief One Zeta Officer.

And he's doing 2 things. One, they're going in and they're doing this. This 80% lift in customers who use us for multiple use cases with not an accident. But what's more important than that, Katy, is, I believe, Athena is going to be the tip of the spear for multiuse case.

Let's go back to what we were talking about earlier. So now we've completed how we're going to add 2 million customers at a 7% discount, Yada yada, athena can then literally pivot and say, by the way, did you know 1 million of your existing customers are currently doing research with your competitors' products and thinking about churning. Would you like to save them? And that's how you go from 1 use case to automatically because we're tracking all the data.

Awesome. Yes, that's helpful. Maybe for a little bit of context around the actual technology of athena, right? How would you characterize the evolution from ZOE, which was previously the kind of innovation engine here and then into what's kind of fundamentally different about Athena? And then started to get at what's really interesting from a use case perspective. Maybe, Chris, if you could kind of just talk to monetization, if you kind of look at historical precedents, there was a pretty material uplift for low usage. And so kind of how are you thinking about it?

Why don't I start with the technology and how it works, and I'll turn it over to you, Greg, give the percentages on Zoe return. What I would say first and foremost is when you look at the fighter jet that we bought, it is so complex. Like it's not just us, it's tech companies, we get so excited about building our platform, and we put every feature in it and every function at it. We think it's amazing and then clients get in front of them, like, what the hell do I do with this? And we're a product of that, right? So we found that clients are using a small percentage of what our platform can do because that's what they know how to do. And -- the concept of sending out a learning and development group to train these people how to use the entire platform. When this is what they do an hour a day. They're not doing it 100 hours a day, right? Not possible.

But somebody will tease me later for that. The bottom line is that by adding the voice enablement that can also control the platform -- it's going to open up all of the data sets and use cases and channels that they don't currently use. Today, all of our AI is internally built -- you've got large language models out there. You've got small language models out there. I sort of jokingly say we build midsized language model, where we're -- we're looking at trillions of data points, but we don't need to ingest the entire Internet to decide if this individual is going to get a credit card and will credit approved for our clients' credit card, right?

So when you think about Athena, she is native to the application layer for the Zeta marketing platform, if she wasn't she couldn't control it. Like you couldn't have an API in and out and have that work. It has to be native. But we're using OpenAI's voice enablement platform, which is the best in the world to make her truly conversational -- the other thing that's going to happen in V2 is you'll be able to access her as a client inside of your chat app inside of your phone. So it's going to be native going both ways. And I think that's going to be an incredible uplift to return on investment to get from that 600% to 1,000%.

Chris, the intent from the very first version, if you will, of athena, which was a Z opportunity engine or so. It was to make life easier for our customers to use more of the platform. There was so much data and intelligence to be extracted, but it was sometimes hard to navigate. So though we made that discovery process faster and easier, athena now kind of hypercharges that. And we wanted to understand -- our intent was to make life easier, which met you use more channels, more use cases, -- was that actually happening on the platform. So then we took a sample of customers in the dozens that had Zoe's capabilities.

And then we looked at it over a month, 6 months, 9 months, 12 months, beyond a year of what was their change in ARPU over that period of time, those that had Zoe but weren't using it and those that had Zolan were using. We found that it was a 2 to 3x greater ARPU on those earliest adopters of Zoi then those were not using it. So as we begin to kind of have the fun with numbers on what athena could generate, it's -- you just kind of start at a base level 2, and you can really model up because athena has really made it multiplier easier to navigate the platform.

And to be clear, at this point, we've included a de minimis amount of Athena increment into the projections for this year because it goes generally available by definition, we're saying the end of the quarter, but it's now by the end of the month, right? We're in March. And we're very, very much on track for that. I feel highly confident.

And the reality is that we'll have to see. What we're doing is we're going to launch it, we're actually birthing athena sort of like the birth of venous we're going up the birth of athena -- we'll see if we can pull off about a Chilean event. But the reality is that when she comes out, we've got a full learning and development package that we're going to be rolling out with it to all of our clients and we'll start with our top 30 customers, and we'll physically go visit them with the learning and development group to start getting everybody up to speed.

So listen, if they adopt it quickly and they see higher return on investment, I think it's highly probable that they will spend more than we're budgeting.

Wanted to zoom out a little bit to some of the bigger picture kind of industry buying patterns that you're seeing from customers. The RFP sets that you guys throw out continue to be very, very interesting...

Only up 100%.

Maybe like anything particular in the competitive dynamic that's driving that? Any differences in kind of win rates that you're seeing over the past few quarters? And then not just kind of more RFP wins, but larger ones. So kind of what's kind of driving that?

You know what's been interesting is, for many years, we got RFPs. But you could tell, they were literally written by the incumbent, right? Like the incumbent sitting in the room, writing the NFE, so they cannot lose it, right? Because this might be a Salesforce shopper, it might be an Adobe shop or it might be an Oracle shop, and they're not going to not be those shops. And by writing the RP, those large enterprises probably have a rule, they have to go out every 3 years or every 5 years or so on and so forth. That's changed.

For the first time, I would say the vast majority of the RFPs we're receiving, the companies are willing to bifurcate Marketing Cloud, from the core products of the larger software companies. And I think a lot of that is because their architectures at this point go back, in most cases, 15 years. You're still talking about exact target response oseneolane here. And what happens is you can't integrate AI into the platform. You can talk about Agent Force from now until you're blue in the face, but it doesn't make any difference if it doesn't really work, right? And Salesforce is marketing cloud shrunk last quarter. That was their results. we're not interpreting them. That's what they said. Adobe and Oracle don't break it out, but I don't know what they're doing.

What I would tell you is the architecture that we have built has data and AI is native to the application layer. When our competitors put AI on their platform, you have to step out of the platform to an AI algorithm, do a query. The algorithm has to do a data dip into a data repository back to the algorithm to create intelligence and then it forms the Marketing Cloud what to do. That latency destroys return on investment. Because AI and data, we launched a whole new platform in 2021 that literally, we can process thousands of data points in milliseconds, and decide, should this person see this ad, get this message or get this connected TV ad, that is creating this 600% return on investment.

So I want to be very clear guys like Salesforce, Oracle Adobe are some of the greatest companies in the world, their core products are best of breed. I don't even think they have meaningful competitors yet in their core products. But their marketing clouds are now the side hustle to their side hustle, and they're just not getting the investment. They would have to re-architect the entire thing, which they could, at some point, choose to do, but then none of them own any first-party data. They're just using their clients' data to train the algorithms. We are very, very focused on the sort of 1 plus 1 equals 4 as it relates to our clients' data plus our data -- and so not only are you seeing 100% increment in RFP volume, which we talked about. I think we're seeing RFPs we're going to win at a greater percentage than we've ever won before.

Yes. And I think 1 of the most compelling data points from the print was how balanced from a vertical perspective it was 9 out of the top 10 kind of growing over 20%. I guess are there any key areas from a vertical perspective that you're thinking could be delivering outside share gains? Anywhere specifically you're thinking about for '26?

It's continued to strike us positively that the verticals that are closest to consumer discretionary, which are the brands that have to make the most -- kind of get the most ROI for their dollars invested were our best-performing verticals again. They grew over very strong comps in the year prior. One vertical that I'd call out because we've been intentional on incremental investment, not just in people but healthcare is 1 that you absolutely cannot have a general son. He must have a domain expertise in health care. By the way, across health plans, across health systems, et cetera. But we've also been intentional in finding partnerships around data there. So that was a vertical that did not grow 20% in 2024, that did grow over 20% in 2025 that we're optimistic about.

And I would just say, 1 of the things we decided when we sort of pivoted this business in 2017 into what it is today, was we wanted to operate across every vertical, right? We effectively operate against 15 different verticals that I'm not sure what percentage of GDP, those 15 make up, but I know the top 3 make up half. So it's got to be a disproportionate percentage. What I would say is we're very well balanced. We usually, there's a year where a couple of the verticals are flat. A couple of the verticals are growing a little bit. A couple of the verticals are skyrocketing growth. The last couple of years, we've seen really solid growth from over 10 of our verticals in pretty much every quarter. And -- it's been interesting, even some of the verticals that their industries have been challenged. They're moving more budget to us than ever before because they need the higher return on investment. And then the guys who are skyrocketing are doing the same thing because they want to supercharge the growth. So it's been great.

I would tell you, Katy, I believe, based on the business we've built, the assets we control, we have the people, the technology and the data to continue to be a 20-plus percent organic growth company for many, many years to come. Yes. And you're not just growing well, but you're expanding margins as well.

So maybe with the last few minutes, just talk about kind of the key leverage drivers and how you're thinking about balancing AI investment was still expanding I'll start and what's you turn.

But let me just start by saying a lot of the investments we made in AI, we made from 2017 to 2021. So everybody is now trying to catch up at 3,000% more cost per item. So we were able to get in before the price is really skyrocketed. A lot of people after our call said, well, if you're really delivering 600% return on investment, why are you not raising price? And to me, what a lot of people don't understand is the 40% approximate of our business, that's utilization fees. We effectively buy the marketing for our clients, and it transitions through our platform. So we decide what the margin is there. Do we want to manage it to growth or do we want to manage it to profitability? I believe that over the next few years, we will surpass 1,000% return on investment to our clients. And I believe we'll be able to keep all of the margin that exists above that, which will start to drive meaningful increment to gross margin.

Chris, I didn't leave you much time, but I'm sorry.

I'll go super fast. We've created a model to where we don't have to sacrifice growth or profitability or vice versa. We give as much investment we can to the innovation team. We try to be smart in how many people and who we hire on the marketing and sales side. The seeker sauce is everything else in the middle should be 0. And we're not there, but that allows us to really refine get efficiency in the middle over invest in the end, and that's resulted in great growth and profitability.

And by the way, we've grown the business, I think, on a 3 or this will be the fourth year of a compounded 30-plus percent growth rate greater than the 50% EBITDA. And last year, we grew free cash flow by 78%. So, yes, I feel like we're doing a good job managing to that.

Very impressive. Awesome. We'll leave it there. Thanks so much.

Thank you, Katie. Appreciate it.

Greetings, and welcome to the Zeta Q4 2025 Earnings Conference Call. [Operator Instructions] Please note this conference is being recorded.

I will now turn the conference over to your host, Matt Pfau. Thank you. You may begin.

Thank you, operator. Hello, everyone, and thank you for joining us for Zeta's Fourth Quarter 2025 Conference Call. Today's presentation and earnings release are available on Zeta's Investor Relations website at investors.zetaglobal.com, where you will also find links to our SEC filings, along with other information about Zeta.

Joining me on the call today are David Steinberg, Zeta's Co-Founder, Chairman and Chief Executive Officer; and Chris Greiner, Zeta's Chief Financial Officer.

Before we begin, I'd like to remind everyone that statements made on this call as well as in the presentation and earnings release contain forward-looking statements regarding our financial outlook, business plans and objectives and other future events and developments, including statements about the market potential of our products, potential competition, revenues of our products and our goals and strategies. These statements are subject to risks and uncertainties that may cause actual results to differ materially from those projected. These risks and uncertainties include those described in the company's earnings release and other filings with the SEC and speak only as of today's date.

In addition, our discussions today will include references to certain supplemental non-GAAP financial measures, which should be considered in addition to and not as a substitute for our GAAP results. We use these non-GAAP measures in managing our business and believe they provide useful information for our investors. Reconciliations of the non-GAAP measures to the corresponding GAAP measures, where appropriate, can be found in the earnings presentation available on our website as well as our earnings release and our other filings with the SEC.

With that, I will now turn the call over to David.

Thank you, Matt. Good afternoon, everyone, and thank you for joining us today. We delivered our 18th consecutive beat and raise quarter. And I want to be clear about why this keeps happening. It is not a single product cycle or a favorable compare. It is the compounding effect of a system, proprietary data that improves with every customer interaction, intelligence that sharpens with every decision and now an interface in Athena that lowers the barriers to enterprise-wide adoption.

The flywheel is what drives durable, predictable and profitable growth. Fourth quarter revenue was $395 million, up 28% year-over-year ex acquisition and political candidate, an acceleration from the third quarter.

Adjusted EBITDA was $95.1 million, up 35% year-over-year, and we had positive GAAP earnings. With these multiyear rates of revenue growth, we are taking market share. This is evidence Zeta is the AI disruptor in marketing.

After providing initial 2026 outlook that was already ahead of consensus, we are once again raising the midpoint of our 2026 revenue guidance by $25 million to $1.755 billion, reflecting year-over-year growth of 35%.

Our momentum is driven by AI shift from feature to infrastructure across the enterprise, and Zeta is built for this transformation. Our AI investments, which began 8 years ago, are yielding better and better results. Marketers are recognizing the strong return on investment delivered by Zeta and increasingly view us as a revenue center for their business, not a cost center.

A recent Total Economic Impact study by Forrester confirmed a 600% return on ad spend, which we believe is contributing to the wallet share gains from our competitors in an already quickly growing market segment. This is a reflection of what happens when proprietary data, intelligence and activation work as one operating system, not three separate tools. Zeta is our client's marketing operating system, and we expect these returns to grow as our AI capabilities advance and Athena fully launches. The impact is already visible in our performance.

Net revenue retention hit a record high of 120% and in 2025, up from 114% in 2024. And RFP volume more than doubled year-over-year to a new record. Customers are spending more and new prospects are showing up faster, both signals of the same thing, the Zeta operating system is working, and working at scale.

Building on this momentum, at Zeta Live last October, we introduced Athena, our super intelligent agent built specifically for enterprise marketing. And since then, the pace of interest, engagement and opportunity has continued to increase.

At CES last month, Athena had a significant presence and customer engagement was exceptional. Feedback was overwhelmingly positive, with customers consistently recognizing Athena represents a fundamentally new way of working.

Early Athena users are reporting significant time savings in segmentation, production, analysis and substantially better return on investment. This is the kind of workflow transformation that drives deeper platform adoption and greater utilization. Athena enhances the Zeta Marketing Platform that is an intelligent operating system for growth, one that can listen, reason and act on behalf of marketers in real time. We are very encouraged by this early customer feedback and remain on track to make Athena generally available by the end of the first quarter.

At CES, we also announced our partnership with OpenAI. We view large language models much like cloud infrastructure, foundational technologies that enable innovation with real differentiation coming from the tools, workflows, data and operating systems built on top. Our partnership makes OpenAI's technology foundational to Athena, but powerful models are only part of the equation. AI is only as effective as the data that fuels it.

As personalization moves to true one-to-one, identity and intent become critical. That's where Zeta SuperGraph comes in, a proprietary deterministic identity and relationship graph within our Data Cloud that unifies data across multiple sources. This SuperGraph creates a moat that widens with every improvement in AI models across the market. Built over the past decade, Zeta SuperGraph operates at scale across more than 245 million U.S. adults and 535 million globally, with more than 1 trillion signals, the vast majority of which are available only to Zeta.

As AI demands higher quality deterministic data to deliver real personalization, this asset becomes more valuable, not less. Our AI and data advantage also helped to fuel One Zeta. One Zeta is no longer just a strategy. It is a repeatable sales model. In the fourth quarter, the number of scaled customers using more than one use case was up over 80% year-over-year, and the opportunity in front of us continues to expand.

Today, we serve 51 of the Fortune 100, up from just 44, 1 year ago and over 120 of the Fortune 500. Collectively, these clients alone represent well over $100 billion in annual marketing spend, significantly expanding the long-term One Zeta opportunity.

Athena further amplifies this strategy by removing the friction across the Zeta Marketing Platform, making it easier for customers to adopt, expand and scale of multiple use cases.

And as I will discuss in a moment, the Marigold acquisition adds another important accelerant to One Zeta by expanding the data, use cases and value we can deliver to customers.

Taken together, the combination of our AI leadership, the continued maturation of One Zeta and the momentum coming out of Zeta Live and CES, these are reinforcing our powerful growth flywheel. This momentum pushed our pipeline to record levels coming out of Zeta Live, and we have already closed $39 million of business directly attributable to the event, putting us well on our way to our goal of $100 million total.

I will close with an update on Marigold. The integration is progressing well, and we continue to anticipate Marigold being accretive to free cash flow and adjusted EBITDA in year 1. We are actively engaging with Marigold's enterprise clients through a One Zeta lens, identifying opportunities to add value, expand use cases and deepen those relationships over time. We are also seeing strong interest from Zeta customers in adopting Marigold's loyalty product.

As I reflect on what Zeta accomplished in 2025, I am so incredibly proud of this team. We exceeded our initial revenue guidance by 5% and our free cash flow guidance by 27%. We expanded existing partnerships and forged new ones, increasing our leadership in the marketing ecosystem. And we developed the most important product in our company's history with Athena. Together, we expect these achievements to extend Zeta's position as the defining AI disruptor in the marketing ecosystem. As always, I would sincerely like to thank our customers, our partners, team Zeta and all of our shareholders for the ongoing support of our vision.

Now let me turn it over to Chris to discuss our results in greater detail. Chris?

Thank you, David, and good afternoon, everyone. Our results once again demonstrate the durability, predictability and profitability of Zeta's growth, which we expect to continue as seen in our increased 2026 guidance.

Revenue growth, excluding LiveIntent, Marigold and political candidate was 28.2% in the fourth quarter, up from 28.0% in Q3 and up from 27.4% in Q2 and 25.9% in Q1. And 2025 was the sixth straight year in which revenue grew greater than 20%, underscoring the durability of our growth and the sustained market share gains we are taking. Results once again exceeded guidance. And just 2 months into the year, we are raising our 2026 outlook, reflecting the visibility and predictability of our business.

For the full year 2025, we expanded adjusted EBITDA margins by over 200 basis points, achieved the highest free cash flow margin in our history, generated $199 million in net cash provided by operating activities and turned GAAP net income positive in Q4, demonstrating the profitability of our growth.

Now I'll discuss our results in more detail. In Q4, delivered revenue of $395 million, exceeding the midpoint of guidance by $14 million or 4 percentage points higher than our forecast, solidly within the 2 to 5 points of cushion we typically leave ourselves. The full year's revenue was $1.305 billion, up 30% year-over-year or 27% when excluding LiveIntent, Marigold and prior year political candidate revenue. This exceeded the midpoint of our initial 2025 guidance by $65 million or 5%.

Our platform is relied upon across virtually all industry verticals. For the first time as a public company, 9 out of our top 10 verticals in 2025 grew over 20% year-to-year, quite a testament to our broad-based leadership. Some of our fastest-growing verticals in 2025 were travel and hospitality up 105%, advertising and marketing up 70%, automotive up 60% and consumer retail up 46%. And worth noting health care, an area of new investment, grew over 20% and is showing strong momentum.

Total scale of customer count grew to 602, up 14% year-over-year and an addition of 30 customers sequentially. We ended the quarter with 184 super-scaled customer customers, up 24% year-over-year, well above our target of 4% to 8%. Super-scaled customer additions were broad-based across industry verticals, including travel and hospitality, services, technology and media and consumer and retail and were driven by continued momentum of our One Zeta initiative. Scaled customer quarterly ARPU of $625,000 increased 8% year-over-year and over 15% when normalizing for political candidate revenue in the year ago period. Super-scaled customer quarterly ARPU of $1.8 million was up 5% year-over-year and also up mid-teens when normalizing for political candidate revenue last year. Both growth rates are in line with our ARPU target of 12% to 16%.

Now I want to double click on the importance of super-scaled customers for a moment. Since our IPO, Zeta's growth has been fueled by super-scaled customers whose spend has grown to represent a larger and larger portion of total revenue. Back in 2020, customers spending at least $1 million annually, represented approximately 70% of total revenue. By 2025, that figure is now approaching 90%. And over that same period, more than 90% of total revenue growth has come from the at least $1 million super-scaled customer cohort. This dynamic is leading to a natural evolution in the reporting of KPIs. In 2026, we will exclusively focus quarterly reporting on super-scaled customer count and ARPU.

In many ways, today's $1 million-plus customer is 2020's $100,000 customer. In fact, one could imagine a new cohort of $10 million-plus customers emerging down the road. The growth and prominence of super-scaled customers is by design. It reflects how we manage the business internally, shows the efficacy of our land, expand, extend, hunter-farmer sales motion, along with the power of One Zeta working in unison.

Our customer-centric flywheel propels the progression from pilot to broad-based platform adoption, powering our very strong net revenue retention rates. First, we allow customers to start small with pilots and proof of concepts ranging from $50,000 to $150,000, which can begin with Zeta Data usage, a CDP or channel activation. Second, we provide these pilot customers with transparency into measurement and ROI. Third, our software and AI learn from past programs and form recommendations to continuously improve return on ad spend, which all leads to creating new audiences, adding more channels and branching into new use cases, each incremental to ARPU.

This is best brought to life by Slide 10 in our earnings supplemental. Customers on the platform in their first year quickly scaled to $709,000 in 2025, representing 111 scaled customers or 6% of total revenue. These customers often start with 1 channel and 1 use case.

Customers on the platform in years 1 to 3 spent an average of $1.1 million in 2025, representing 217 scaled customers or 19% of revenue. These customers begin to scale beyond 1 channel, but remain generally on 1 use case.

Customers in years 3 through 5 spent an average of $2.1 million in 2025, representing 65 scaled customers or 11% of revenue. Customers in this cohort are moving into omnichannel experiences.

And lastly, customers on the platform 5 or more years, the earliest adopters of the ZMP spent an average of $3.9 million in 2025, representing 209 customers or 64% of total revenue. This cohort makes up the largest percentage of revenue and the fastest-growing ARPU, up 39% year-to-year.

Shifting to revenue mix, direct revenue in the fourth quarter was 74%, in line with the year-ago quarter and our target of 70% to 75%. Our GAAP cost of revenue in the quarter was 40.4%, a 50-basis point increase year-over-year and 100 basis points sequentially. The increase in cost of revenue was driven by strong sequential and year-over-year growth in social and connected TV.

In the fourth quarter, we generated $95.1 million of adjusted EBITDA at a margin of 24.1%, 174 basis points higher year-over-year and $4 million better than the midpoint of our guidance. This marks the 20th straight quarter of expanding adjusted EBITDA margins year-over-year. For 2025, adjusted EBITDA was $279 million, representing a margin of 21.4% and 44% year-over-year increase.

We also generated positive GAAP net income. For the fourth quarter, our GAAP net income was $6.5 million, an improvement from a net loss of $3.6 million last quarter.

Fourth quarter net cash provided by operating activities was $64.1 million, up 47% year-over-year, with free cash flow of $55.8 million, up 76% year-over-year and representing a margin of 14%. This represents a free cash flow conversion of 59%, a significant improvement from 45% in the fourth quarter of 2024. This also includes a roughly 9-point working capital headwind driven by longer agency payment cycles common to their industry.

The improvement in both adjusted EBITDA margin and free cash flow margin conversion in the fourth quarter exhibits the strong operating leverage of our model, which we believe puts us firmly on track to achieve our Investor Day target of a 30% plus adjusted EBITDA margin and greater than 70% free cash flow conversion in 2030.

For 2025, our free cash flow was $165 million, a margin of 12.6% and up 78% year-over-year.

During the fourth quarter, we repurchased 1.9 million shares for $35 million. And for the full year 2025, we repurchased 7.9 million shares for $120 million. Since January 1, 2026, and up until mid-February, we have repurchased an additional 1.5 million shares for $25 million and have roughly $139 million remaining on our share repurchase authorization. We expect to remain active buyers of our stock, especially at these levels.

We continue to make significant progress in reducing dilution and stock-based compensation expense, just as we said we would. We ended 2025 at the low end of our guidance range with total net dilution of 4.3% or 2.2% excluding Marigold. Additionally, we improved the ratio of stock-based compensation to revenue from 19% in 2024 to 14% in 2025. And we remain on track to achieve our normal course 3% to 4% net dilution target in 2026.

Now on to guidance. We are raising first quarter and full year revenue, adjusted EBITDA and free cash flow guidance. Details can be found starting on Slide 19 in our earnings supplemental.

But before discussing the numbers, I'd like to highlight a few key aspects of our business model. First, our revenue is tied to the volume decisions made, not seats, whether those decisions are made by a human or an agent. This foundation and flexibility to adapt to the rapid pace of AI innovation provides durability to Zeta's growth. Second, strong pipeline visibility and sales productivity support our confidence in the year ahead, and we continue to guide with planned conservatism of 2% to 5%. And lastly, as we integrate Marigold, we expect to realize further operating leverage.

For the full year 2026, we are increasing the midpoint of revenue guidance by $25 million to $1.755 billion, representing a 35% growth rate or 21% year-over-year when excluding Marigold and political candidate revenue. None of our guidance raise is related to political candidate revenue, which we continue to assume will be $15 million in 2026 with $7 million in the third quarter and $8 million in the fourth quarter. Additionally, we continue to take a conservative view of Marigold, contributing at least $190 million in 2026 revenue. And lastly, our revenue guidance includes minimal contribution from Athena-driven revenue with its broad-based adoption representing incremental consumption revenue upside.

For the first quarter, we now expect revenue of $370 million at the midpoint, $8 million higher than our previous guidance and representing year-over-year growth of 40% or 22% when excluding political candidate and Marigold revenue. The linearity of revenue is it spans each quarter of the year aligns with historical averages, so there is no front or back-end loading of revenues or growth rates.

For adjusted EBITDA, we are increasing the midpoint of our 2026 guidance to $391 million, up $6 million from our prior guidance and representing year-over-year increase of 40% at a margin of 22.3% and an improvement of 92 basis points over 2025. For the first quarter of 2026, we now expect adjusted EBITDA of $61.5 million at the midpoint, up from our previous expectation of $60 million and representing growth of 32% and a margin of 16.6%.

We are also increasing the midpoint of our 2026 free cash flow guidance to $231 million, up $7 million from our previous guidance and representing year-over-year growth of 40% at a conversion of 59% of adjusted EBITDA, which likely has upside.

Additionally, we believe our fourth quarter positive net income on a GAAP basis represents an inflection point, and we expect to generate positive GAAP net income for the full year of 2026, a significant milestone for the company.

Today, we would also like to provide updated Zeta 2028 targets to account for the acquisition of Marigold. We're raising our revenue target from $2.1 billion to $2.3 billion, representing a CAGR of 23%. We are also increasing adjusted EBITDA target to $573 million, which implies a margin of 25% and a free cash flow target of $371 million, which implies an adjusted EBITDA conversion of 65%.

I'll conclude with this. In environments like today, it is more important than ever to control the controllable. For us, this boils down to hiring and retaining the industry's best talent. This is how you continue to lead. Delivering customer outcomes with unmatched industry ROIs. This is how you garner loyalty. Generate best-in-class retention rates and win market share, and doing what we say we're going to do for investors. This is how you earn trust and show durable, predictable and profitable growth.

Now let me hand the call back over to the operator for David and me to take your questions. Operator?

[Operator Instructions] And our first question will come from Terry Tillman with Truist Securities.

I had a question and a follow-up. I must ask about Athena. And again, I know that it's not generally available yet, but when you all put out a press release a while back, it did actually have a custom already quoted in there, which I thought was interesting. But you talked about a couple of agents at that point, Insights and Adviser. Can you remind us, is there going to be kind of a whole slew of agents that you will release? Or are these going to be the 2 primary wins and there is a monetization structure around that?

And the last part of this Athena long-winded question is, with the business that you've signed year-to-date, has it had an influence in some of these deals getting across the line, even if you're not monetizing? And then I had a follow-up.

So thank you, Terry. Let me start by saying that those 2 agents are first because they will drive probably the greatest benefit to our customers. So when you think about Athena and you think about large language models and how we are using them to win in the marketplace, today, the Zeta Marketing Platform is like a 747. Most of our clients know how to fly a Cessna. The beauty of Athena is the ability to fly the entire 747 just by narrating and speaking to Athena who can automatically do it.

So to answer your question, these will be the first 2 agents. We will have it generally available by the end of this quarter. We have a number of clients as early users today. The initial feedback has been, it is game changing from a workflow management perspective, and it is driving substantially higher return on investment than the existing 600% return on ad spend that the platform is generating.

As we roll out additional agent function built into Athena. She'll be one agent, but with different feature sets, if you know what I'm saying. It won't be different agents sitting under her. Everything will be driven by Athena. We're going to continue to drive out functionality based on things that we believe will drive the highest utilization rates, the highest move to One Zeta. And I think you'll see that really start very quickly out of the gate soon.

That's great to hear. And I guess, Chris, maybe a follow-up. You framed it well in terms of maintaining that 2 to 5-point cushion. But I think for the year, sometimes -- you've talked about maybe your top 5 kind of spending verticals and maybe the assumptions you're assuming for the rest of the year off of your top 5 verticals. Can you maybe share kind of another way of looking at conservatism, looking at some of your biggest verticals and what you're assuming the rest of the year like consumer retail and travel and hospitality?

Yes, Terry. I mean what we found was that those verticals that have been -- are closest in proximity to consumer discretionary, you saw through the prepared remarks, were and have continued to be throughout the year, our top performing verticals. This was a first for us in our history to have 9 out of our top 10. And that's, by the way, on a trailing 12-month basis. That's not cherry-picking in a particular quarter, grow over 20%. Our guidance does not assume that. Our guidance is probably closer to half, which is even below what we've been historically.

The other way I'd encourage you to think out the conservatism in our guide is we've reiterated that continued 2 to 5 points of cushion. We have also kept what we believe is a conservative view of political candidate revenue at $15 million in the guide. So of the raise that we put through, none of it was a change in our assumption of that $15 million. So that should be conservative. We continue to be conservative around Marigold.

And to the extent, as David talked about, we get really strong continued adoption from Athena and that adoption has proven to generate increased ARPUs and usage, we're assuming minimal contribution right now on the guide. So that should also be incremental upside. So I feel like this is a very nicely derisked outlook to start the year.

We'll go next to Zach Cummins with B. Riley Securities.

Congrats on the strong end of the year. David, I just wanted to ask about the deals that you've already closed coming out of Zeta Live, I think almost nearly $40 million in business. I mean any particular trend that you can highlight, whether it's customers in a particular vertical or a particular solution set that's driving the early momentum. And then just curious on how you're thinking about that continued progression through those pipeline opportunities in the coming quarters?

The one consistent, Zach, is they all really love The Chainsmokers. No, in all seriousness, it was across multiple verticals. We saw a very big win in telecom, which I think will continue to get bigger. But I would tell you that the $39 million is sort of a just getting started number, and it was really amplified by the Consumer Electronics Show. I've been running this company now for just over 18 years, and I have never experienced the type of experience we had at the Consumer Electronics Show this year. It was everybody knew who we were, the move from Zeta who to why Zeta to Zeta now has really begun to take shape.

And when you look at a 600% return on investment, you're really seeing us as the AI disruptor in the marketing space. As I say, we are the disruptor, not the disruptee in this space. And I think that first $40 million against what I think will be over $100 million. Now of course, I've got to make sure I get Chris comfortable with that as we look at what we're going to spend on this year's Zeta Live, which might be a bit more than last year, we have some really cool stuff planned.

But the company is really re-architecting to make the vast majority of our annual time, energy and capital investment as it relates to events, not all, but the vast majority around the Consumer Electronics Show, the possible conference, Cannes Lion, and Zeta Live. And I think that if you look at our record pipeline in addition to the ways that is at this point a bit conservative, I think you're going to see us continue to win in the marketplace.

Exactly. What's interesting about that Zeta Live pipeline, with the $40 million that's already been closed, there's still another 200 opportunities, distinct opportunities tied just to Zeta Live valued at over $130 million in to go pipelines to get that extra $60 million from. So as David said, that's looking like a very achievable number.

Understood. And my one follow-up, Chris, is just around the gross margin numbers that we saw in Q4. Any onetime impacts here in the fourth quarter. And now with Marigold in place, how should we think about the right gross margin expectation through 2026?

Yes. Look, I even zoom out a little bit more, Zach. When you look at our 2028 model, each year, we should be getting between 100 and 300 basis points of gross margin improvement. Marigold is a tailwind to that. When you look at the fourth quarter's gross margin profile, you had our integrated platform revenue growing 25% as well as our direct revenue mix growing 25% year-over-year. We had very strong channel quarters in social and very strong channel quarter in connected TV, both of those below the overall corporate average, but good indications for multichannel, omnichannel usage.

Understood. Best of luck with the rest of the quarter.

Thanks, Zach.

Our next question comes from Jason Kreyer with Craig-Hallum Capital Group.

Congrats on 18%. I'm excited to hear about 19% next quarter. Wanted to just ask the evolution on One Zeta. I think you're integrating some of that sales functionality into Athena. So what does that mean for customers? Or what does that mean for the cross-sell experience when you combine One Zeta with Athena?

Let me start by saying thank you, Jason. Appreciate it. And our goal, as always, when we start a year is to finish the year 4 additional beat-and-raise quarters by the end of the year. So we're at 18%. Our hope is to be sitting here with you guys next year talking about 22%. The number of enterprise clients that use more than one use case in the fourth quarter of 2025 was up 80%. That's 80%. And that is a massive testament to One Zeta.

You're seeing the team headed by Ed See, and of course, Steve Gerber, that are really, really getting traction here. Now that's before the next level of uplift, which will come from Athena. So I think that as you see customers moving from one use case to multiple use cases around the One Zeta strategy to remind you, we see an average of a 200% to 300% revenue uplift from those clients from the past.

Now I don't know if every client is going to do that going forward but we do continue to see a meaningfully higher spend from customers who are moving from one use case to two. I think also one of the things I was most proud of last year. And this was not a cherry-picked quarter. For 2025, our net retention rate was 120%, and I was always happy at the 110% to 115%. So when you look at 120%, that means that One Zeta is really working, and our clients are scaling very, very quickly. Chris?

Yes. David, you said it perfectly. We had -- if you look at the total percentage of scaled customers, Jason, that are now on more than one use case, we're almost at 25% compared to, call it, 13% a year ago. So just really exciting progress made this year.

Awesome. Appreciate that. One follow-up for me on Marigold. So now that you got that closed, curious what the international expansion plan looks like and how you go after international from kind of a pull versus push mentality?

Yes. I mean what we're seeing now, Jason, is international is really happening very naturally, as our clients are mostly multinational enterprises. The adding of the Marigold international assets should accelerate that, but at the same time, I want to point out, the vast majority of our revenue is in the United States. This is the largest advertising market in the world by dollars and we are taking meaningful market share.

Last year, the average growth rate of the marketing ecosystem was about 10%, we grew 30%. So as we are disrupting the marketplace, we're taking greater market share in the United States, and we're seeing a natural progression and a very nice growth rate internationally, which is a reverse from prior years where we had struggled there. So I'm hopeful for international, but I would tell you that we certainly are not projecting it to be a massive component of this business for many years to come.

We'll go next to Arjun Bhatia with William Blair.

Congrats on a strong Q4 here. Maybe I'll continue on the kind of Athena line of questioning. David, you're clearly having success already with One Zeta, right? The rise in multi-use case customers is increasing. I'm curious, just as you think about '26, is it possible that Athena can have a meaningful impact of this year? Or does it take customers some time to kind of use it and ramp up on additional use cases? Like how are you thinking about the timing of when the sort of indirect revenue impact of Athena might come through?

I think it could be' '26. We're not counting on it, and we have not put that into our projections. And certainly, you don't know. But what I can tell you is if you look at the early access clients, they are spending materially more with Athena than they were without her.

They are telling us that they're seeing a game-changing workflow environment, which is great, and they are seeing a substantially higher return on investment, which at the end of the day, when you think of our biggest moats as a company, data is number one. Number two is our ability to drive superior return on investment, call it, right now, 600% return on ad spend. And then, of course, the ability to work with very large enterprises through their data security group, their data privacy groups, their legal groups, their procurement groups, so on and so forth. I think Athena helps us continue to drive greater return on investment both from a workflow management perspective and from a return on ad spend, which will cause our clients to drive even more of their existing marketing dollars to us.

All right. Perfect. That's helpful. And then Chris, one for you. In the back half of '25, you kind of ended the year on a strong note in terms of profitability GAAP profitability, GAAP net income and in Q4, you had kind of net income positive as well. How are you thinking about how that shapes up in 2026? And what does that sort of imply for stock comp outlook next year and beyond?

Yes. Thanks, Arjun. It was an area that we had just very constructive investor feedback that was important for the company to make strides towards that goal, turning the corner this year in 2025 towards positive and then seeing ourselves kind of this being now an inflection point. I think it from a GAAP EPS perspective, call it $0.02 to $0.04 in that range. There's upside to that and obviously depends on a number of factors.

But when you think about the ingredients that went into that inflection point and turning positive, it was progress on dilution, it was progress on stock-based compensation and then more and more yield off of adjusted EBITDA dropping to free cash flow. So we're really excited about that being a turning point, and it's onward and upward from here.

And we expect to be net income positive this calendar year forward.

Our next question comes from DJ Hynes with Canaccord Genuity.

Congrats on the excellent quarter. David, I want to ask about the OpenAI partnership. I think you quoted saying, this is going to be the most instrumental partnership we've ever embarked upon. As you look out over multiple years, like can you see the potential for how that relationship may evolve over time? Like what excites you the most about that opportunity?

Well, first of all, they're an incredible -- I'm sorry, I'm getting back feedback. Can you hear me, DJ?

I can hear you, yes.

Right. So what I would say is, first of all, OpenAI is an unbelievable organization. And when we think about the large language models, we think about them much like we would think about AWS or Snowflake, where they are all at some point going to be a part of our stack. In fact, we work with most all of them, if not all, already.

The partnership with OpenAI is different because it's foundational to Athena. We're also working with them on other components of their business where we are actively talking about doing things to help them with their business while we are talking about them doing more things to help us with our business.

So I was really referring to sort of the organizational partnership when I was talking about how I think this will be one of the most important partnerships we've ever made. And as we're looking at Athena, so once again, this whole narrative that large language models are going to disintermediate enterprise software, in our opinion, is silly. We think that large language models are going to be a component of what we do. And of course, we will pay them for their products and services. At the same time, they'll drive efficiency and accelerated revenue growth into our business, which will more than make up for that.

And when you think about what we're doing here, the whole goal is to get our clients to be able to more seamlessly use our platform, drive higher return on investment and make easier workflows for them around flying a 747, which is our platform versus the Cessna they currently know how to fly. OpenAI being foundational to Athena is helping us do that, and helping us do that in a very impactful and very meaningful way. Does that make sense, DJ?

It does make sense, yes. Maybe a follow-up on the data side. I'm curious, does the ability for Disqus to collect data or intent signals change in any way with the emergence of AI answer engines? I'm just feeling like people are landing less on owned media and now just reading more summaries. Have you seen any change in the volume of comments or authenticated site visits? And does that impact your ability to collect data at all?

So it's a great question. The answer is no. We have not seen any of that. In fact, because right now, the publishers, a lot of them have a challenge, right? If you look at Google, by way of example, it used to be that 90-plus percent of all queries were directed off to a publisher, a brand or an e-commerce platform. Today, according to them, greater than 60% of all queries are being answered on their platform. That's creating a massive tailwind for Zeta.

First, it is massively driving up the cost per click, which is driving advertisers to look for new methodologies for cost-efficient management of their marketing. Second, we're seeing that publishers are more anxious for traffic than ever before. And if you look at our e-mail platform around LiveIntent and other things we're doing, we are one of the biggest drivers of traffic and then you put Sailthru in, which was one of the assets we acquired through Marigold, which is one of the larger ESPs for publishers, our Publisher Cloud is driving massive volume of traffic back to publishers at a time when they need it, and we're helping to monetize them as a part of it.

So even though they're seeing less traffic today, DJ, from Google directly, we're actually helping them to drive incremental traffic. I'll also remind you that Disqus is one of, call it, 20 different platforms we now control that are generating real-time signals on a day-by-day, moment-by-moment basis. To date, we have not seen any fall off there.

Our next question comes from Richard Baldry with ROTH Capital Partners.

It looks like quota carriers are up about 10% sequentially. I assume some of that has to do with the Marigold acquisition. Can you talk about any cross-training efforts that are needed and how we should think about more additions to the quota carriers throughout the year ahead?

Yes, Rich, we added, call it, 15-ish in that range from Marigold in terms of quota carriers sequentially. So you're right, that was a driver there. I'll let David take the next one.

Yes. What we're doing, Rich, is we're sort of teaming their salespeople up with ours. So rather than taking all of the time to train them on everything we're doing, for their clients, we've sort of segmented it to the top 30, which are, I'm pretty sure, all Fortune 500 companies. But the reality is that we're going in and we're seeing really interesting cross-sell opportunities already because of that.

Got it. And lastly maybe sort of will be gentle and call it an unusual environment for software valuations. So I'm sort of curious, your own internal preferences to allocate capital between either M&A because you've done some meaningful strategic M&A versus buybacks over sort of the near term, intermediate term?

Yes. So let me start by saying we are buying back stock very rapidly. I think we have $130 million left, give or take, on our existing buyback. When we get through that one, we will most likely announce the next one. Every time we've announced a buyback, it has been 100% greater than the prior buyback. So I think right now, the single best use of our capital is to buy back our shares.

Now that being said, we've been around for 18 years, I just did a CNBC interview earlier. And it's sort of -- we figured out we've been around for 18 years. We've done 18 acquisitions and we beat and raised 18 quarters in a row. So this is sort of the 18 cubed results as it relates to that. It is highly probable we'll do a 19th acquisition. And this is obviously a good environment to buy what I think are high-quality assets at a lower price than you would have had to pay.

We have a very, very solid balance sheet. We have a lot of cash. We are generating meaningful free cash flow at almost a 60% conversion rate of cash to EBITDA. And I think that will continue to go up as we've talked about. And we have de minimis debt. Our debt ratio was below 0. I don't want to come below 0, but it is 0 at this point. So I think we have the opportunity to do something, although there's nothing on the radar right now. Right now, we're operating our business. We've obviously given as reported guidance to a 40% growth rate in the first quarter, a 35% growth rate for the year and feeling like we're in a very good place.

Rich, we've really stepped up the repurchase program in '25. And as David said, especially at these levels, I would expect it to sustain. As a percentage of free cash flow, we did 45% repurchase to free cash flow ratio in 2024. We did 73% in 2025. So our model has always been at least 50% of the free cash flow we generate. But as David said, we're going to be aggressive in this environment.

And Rich, I don't know if you've been able to dig out of the snow but just to show the nimbleness of our organization, I woke up in Los Angeles yesterday with a 50% probability of going to New York to do our earnings, a 50% probability of the team coming to L.A. to do earnings, and we are now all in Miami doing our earnings because it was the only place we could all get to. So we tend to be on the more nimble side as it relates to this stuff.

Got it. Maybe one last one for me. The net retention number of $120 million was a pretty strong number. To keep it a little bit apart, was it more driven by volume usage or the -- more by the number of use cases sort of climbing? And a little struck that it's that strong ahead of Athena being GA because it seems like that lowers the friction to usage. So is there anything we should think about on that number and it's sort of onetime orientedness or sustainability or extensibility?

No, I mean, if you look at -- you can go into each of the Qs and get a pretty good indication throughout the year of the net revenue retention rate, you can get pretty close to it, not exact because that's an annual metric. But you'll see that it was really kind of a -- we're going in with a running start into 2026. It was a very strong end of the year.

A few dynamics to think about. First, we benefited from a lot of new customers that were added late in 2024 that very nicely scaled throughout 2025. What's also, I think, evident in the results is not just the addition of use cases and channels, Rich, but growth within brands in the agency ecosystem. If you look at brands within the holdcos on a year-over-year basis, they're up 80%. That's a big change that drives growth within just, call it, 1 scaled customer, but can have some pretty dramatic ARPU expansion outcomes.

Yes. I don't see it as an anomaly, Rich. I mean we're not going to guide to that. But the reality is that what we're seeing is we're seeing, bringing Ed See last year and building the systems around One Zeta has been game-changing for moving from one use case to multiple. And as we've mentioned before, when a client moves from 1 use case to 2 use cases, their spend goes up materially as evidenced by the 80% growth in multi-use case customers for Q4 over Q4 of the prior year. So I think that Athena will help us with that number, and I think we're going to continue to run hot there.

Moving next to Elizabeth Porter with Morgan Stanley.

Awesome. This is Katie Keyser on for Elizabeth. I just had a quick one, hoping for an update on the political and advocacy side of the business, really just in the context of what you've seen during previous elections. You guys clearly expanded the size and scale of the platform since prior midterm election cycle. So wondering what you're seeing early in '26 as it relates to advocacy.

And then maybe just for Chris, if you could comment on how that spend is expected to phase through your guidance, kind of what scenario would cause that to prove conservative. Any thoughts there would be great.

Sure, I think, Katie, and give our best to Elizabeth. From 2020 to 2022, the contribution in political candidate revenue halved. It was, call it, $20 million in 2020 -- sorry, $15 million in 2020, and it was $7.5 million in 2022. In 2024, total political candidate revenue was right around $40 million. So starting this year's guide at $15 million is probably conservative. What we've said in terms of the cadence of that spend that we expect to realize is, call it, $7 million in the third quarter and $8 million in the fourth quarter.

Advocacy is an always on industry for us now. It's obviously bigger in political candidate cycles, but we've actually made some really exciting new hires in 2025 into that area in advance of building momentum for 2026. So I expect that to continue to be an always on industry for us. It will benefit in the candidate year, but it's not driving any outsized contribution in our current guide right now, though.

Yes. And it could be upside, Katie.

Moving next to Matt Swanson with RBC.

Great. A really impressive number when you're talking about the 600% ROI from the Forrester study. Can you just talk a little bit about kind of the macro resiliency that, that gives you a business just as we're dealing with all the headlines around tariffs and everything else?

So thank you, Matt. We actually think it doesn't just insulate us from the macro environment. We think it accelerates in this macro environment. What we see is, as clients are dealing with different sort of variables in their businesses, they want to maximize their return on investment in every component of their business, with marketing being one of their largest expenses as organizations. So I think it's helped us over the last year, and I think it will help us over the next few years.

And then if I could just double-click on one aspect of Marigold, I know Loyalty was something that we talked a lot about when the acquisition was first announced. I think in the prepared remarks, you mentioned that you're seeing some early interest from customers. I was wondering if you could just expand on that a bit.

Yes. So we're -- first of all, we're very excited to take their customers and move them into the One Zeta solution. To remind you, when we bought Marigold, they were effectively 100% retention business. They didn't have anything around new customer acquisition and their monetization was very limited. So we're very excited to take their customers and move them into multiple use cases, particularly around customer acquisition. We're also seeing real interest from a large number of our existing clients to use our new Loyalty solution, and we're starting to see meaningful traction there.

We're also doing something really interesting, which is in sort of the next release, not the first release, but we'll probably be doing an Athena release a quarter over the next few years with it being generally available as we expect it to be this quarter. We're very on track for that. But we're going to be integrating Athena into the Loyalty program as well. So I'm very excited about that and its ability to seamlessly integrate them into all of our existing 603 scaled customers.

And we'll go next to Scott Berg with Needham & Company.

This is [ Lucas Metcalf ] on for Scott Berg. Just in terms of 2026 marketing budgets, what are you guys hearing from customers about overall kind of spend growth and how AI is shaping kind of their allocation decisions?

And then I guess, specifically, are you seeing AI driving incremental budget expansion, more platform consolidation? Or are you just kind of seeing a reallocation within existing spend?

Well, it's a lot to answer in one fell swoop. What I would start with is, yes, we're seeing platform consolidation. We're starting to see that our entire strategy around disintermediating point solutions into one platform is really taking hold. And Lucas, I think our 120% net retention rate last year really evidences that.

What you're also seeing is you're seeing marketing budgets from our vantage point in the United States in their entirety going up into 2026. We think we'll see marketing budgets up and to the right. And we think we will continue to take a multiple of that growth in our growth rate as a company.

Moving on to Jackson Ader with KeyBanc Capital Markets.

This is Jack Nichols on for Jackson Ader. With RFP volumes more than doubling, who are you mainly seeing in deals from a competitive standpoint? And can you talk about Zeta's right to win there? And kind of set it in a way, who are you taking budget dollars from? And then I've got a follow-up.

Yes. I mean we continue to see a whole host of point solutions depending on how the RFP is drafted, and we moved the narrative from individual point solutions to our platform solution, which is how we're winning. What I would tell you is we continue to see Salesforce, Adobe, to a less extent, Oracle and a few other smaller players in the CRM RFPs. And then in the acquisition RFPs, we're seeing companies like the Trade Desk continue to be challenged as we continue to take market share from them and others continue to take market share from them. I'm sure they'll have their viewpoint on that at some point.

But what I would tell you is that we see the different point solutions in these RFPs. And what I would tell you is we continue to win greater than 50% of the engagements and RFPs we get invited to participate in. And what you're seeing in the numbers, which obviously are growing faster than we even expected and we expected to grow fast is we're seeing far more RFPs than we've ever seen before.

So we're seeing more RFPs and we're still winning greater than half. So you're starting to see that ripple into the numbers. I'm pretty sure this will be our third consecutive 30% growth year based on our existing projections. You're talking about 3 years in a row of 30-plus percent growth and a 4- or 5-year 30% compounded growth rate, you're seeing that come in through the growth of the RFPs.

That's helpful to understand. And then maybe as a follow-up, how specifically are agencies thinking about their AI marketing strategies, maybe splitting the difference between Athena and then third-party LLMs, how are the marketing agencies kind of going about the testing and then the use case testing and deployments there?

The LLMs have no capabilities around activating marketing. I mean to be very clear. Today, the only thing the LLMs can do, it can help more efficiently code, which, by the way, our entire engineering staff is using every tool available around efficiency of coding, whether it's Anthropic or it's OpenAI or other products in Guild and we continue to use all of them, which is one of the ways we're staying ahead of our competitors as it relates to our engineering and innovation capability.

So we're not seeing any of the agencies at this point looking to move activation to an LLM because they have no activation capabilities. Even the LLMs that are driving -- rolling out their own marketing are not doing it themselves. So I think what you're going to see is you're going to see the agencies continue to consolidate platforms.

As Chris said, I think we grew our brands with the agencies we work with by 80% last year over the year before. That's not an accident, right? They're not looking to split that up with LLMs. Now I have had conversations with the heads of all the agency holdcos as of late, and everybody is looking to figure out how do they use large language models to be more efficient inside their businesses just like we're doing. And I think they're going to continue to look to do that.

But from an activation perspective, our data which is one of the biggest moats in our business, which is never fed into large language models, it stays behind our cloud, is invaluable to our enterprise and agency clients as it relates to our models being able to train on our data exclusively and the ability to better target and create better return on investment. So I'm not seeing any of that being split up at this point.

We'll go next to Koji Ikeda with Bank of America.

This is George McGreehan on for Koji Ikeda. I wanted to ask on the strength you're seeing in terms of Fortune 100 and Fortune 500, these large enterprises and the new customers coming online from those areas. What are conversations like with these large enterprise customers that presumably have a lot more room to grow with the platform over time? What are they excited about when it comes to the Zeta platform?

So thank you, George. Great question. First of all, as we announced, we are now working with 51% of the Fortune 100 and 24% of the Fortune 500. But you're right, we have a very small wallet share there with a massive headroom to grow.

Everybody that we're talking to in the Fortune 500 is focused on return on investment. How do they get the highest possible return on their marketing spend to drive efficiency into their business because for most Fortune 500 customers, especially the ones that are consumer-facing, I would say that their second or third largest global expense is marketing. And as they think about that, they're thinking about how do they invest that in a way that they can get the highest possible return.

I would tell you, even 5 years ago, Fortune 500 companies were focused not on return on spend. They were focused on the percentage of their revenue that sales and marketing represented. So if they were spending $100 -- I'm sorry, if they were generating $100 in revenue, how do they spend $20 or $22 in marketing?

As it relates to today, it's how do we spend $1 and return 500%, 700% or 1,000% against that dollar? And the attribution capabilities compiled with our proprietary data, compiled with our activation capabilities are creating a true return on investment analysis that has not been available to Fortune 500 companies in the past.

And we'll go on to our next question, Callie Valenti with Goldman Sachs.

Just one for me. I wanted to ask -- I know part of your strategy over time has been acquiring assets to add to your Data Cloud. Curious, as consumers interact more with LLMs and that ecosystem continues to mature, how do you think about the potential to capture data from these new channels through M&A or other means?

It's a great question. And yes, we, Callie, have always looked at how do we build on our Data Cloud. What I would tell you is, you hate to plant a flag and say you're done, but I would tell you that today, our Data Cloud is really the best data cloud in the world. We've got better access to information than at any point ever. We're ingesting trillions of signals. And by the way, we've rolled out our own generative optimization platform, the GEO platform where we are helping our clients to better get their information and their businesses fed into the large language models. It's something that allows us to learn a tremendous amount about how the LLMs are acting by building that GEO product.

So in many cases, we bought businesses, in many cases, we've built different platforms. In this case, we see GEO as strategic, not just helping our clients get to the next generation of marketing, which we're doing, but also the ability to learn how those models are thinking, how they're ingesting information and how do we get information back from them.

This now concludes our question-and-answer session. I would like to turn the floor back over to David Steinberg for closing comments.

I will close simply by saying I have never been prouder of running this company. We have the right people at the right time with the right technology, not just to win today, but to win for many, many years to come. We're incredibly excited about the innovations around artificial intelligence and how they are willing to fit into our platform and how we are going to be the disruptor of marketing over the next generation, not the disruptee. I hope everybody has an incredible day and an incredible week. Thank you for listening.

Ladies and gentlemen, thank you for your participation. This does conclude today's teleconference. You may disconnect your lines, and have a wonderful day.

Greetings, and welcome to the Zeta 3Q '25 Earnings Conference Call. [Operator Instructions] As a reminder, this conference is being recorded. I would now like to turn the conference over to your host, Matt Pfau, SVP of Investor Relations. You may begin.

Thank you, operator. Hello, everyone, and thank you for joining us for Zeta's Third Quarter 2025 Conference Call. Today's presentation and earnings release are available on Zeta's Investor Relations website at investors.zetaglobal.com, where you will also find links to our SEC filings, along with other information about Zeta. Joining me on the call today are David Steinberg, Zeta's Co-Founder, Chairman and Chief Executive Officer; and Chris Greiner, Zeta's Chief Financial Officer.

Before we begin, I'd like to remind everyone that statements made on this call as well as in the presentation and earnings release contain forward-looking statements regarding our financial outlook, business plans and objectives and other future events and developments, including statements about the market potential of our products, potential competition, revenues of our products and our goals and strategies. These statements are subject to risks and uncertainties that may cause actual results to differ materially from those projected.

These risks and uncertainties include those described in the company's earnings release and other filings with the SEC and speak only as of today's date. In addition, our discussion today will include references to certain supplemental non-GAAP financial measures, which should be considered in addition to and not as a substitute for our GAAP results. We use these non-GAAP measures in managing our business and believe they provide useful information for our investors. Reconciliations of the non-GAAP measures to the corresponding GAAP measures, where appropriate, can be found in the earnings presentation available on our website as well as our earnings release and our other filings with the SEC.

With that, I will now turn the call over to David.

Thank you, Matt. Good afternoon, everyone, and thank you for joining us today. For the 17th quarter in a row, we once again delivered a beat and raise quarter, driven by our leadership in AI-powered marketing. In Q3, revenue was $337 million, up 28% year-over-year ex political and LiveIntent. This is an acceleration in growth from Q2. Adjusted EBITDA was $78 million, up 46% year-over-year. And free cash flow was $47 million, up 83% year-over-year, representing a margin of 14%. This is the highest free cash flow margin we have ever achieved, and we did it while accelerating our revenue growth ex political and LiveIntent.

This demonstrates our focus on driving growth and improved profitability while investing to extend our AI leadership. Based on our year-to-date momentum and our record pipeline exiting Zeta Live, we are raising our 2025 revenue guidance by $11 million at the midpoint and providing an initial 2026 outlook well ahead of consensus. In October, we hosted our fifth annual Zeta Live, our most successful event yet with max capacity audience. Attendance was up 35%. And unfortunately, we had to turn away a large number of people.

For next year, we are currently looking for a bigger venue. We had strong executive participation, representing more than $100 billion in annual marketing spend decision-makers in attendance. At Zeta Live, we hosted 38 sessions, featured 95 speakers, delivered nearly 120 product demos and shockingly served 7,600 coffees to the 1,500 attendees. Customer feedback was overwhelmingly positive with many attendees commenting that it was one of the best events they have ever attended. Our goal is to close over $100 million in incremental business coming out of Zeta Live. At Zeta Live, we launched Athena, our next step in leading the AI revolution in marketing.

Athena is our AI conversational, superintelligent agent that becomes the intelligent operating system for our clients' businesses and ultimately for their lives. Athena marks a major breakthrough in human AI collaboration, removing the friction between the human and artificial intelligence and acting as a real-time voice-activated command center for the Zeta marketing platform. One workspace to plan, execute, analyze and optimize in plain-spoken English. AI is the new UI and Athena proves it. You speak your objectives, it builds the experience, launches the program and delivers insights on one screen, making it easier to adopt more channels, more use cases and ultimately drive greater ROI and spend on Zeta's platform.

The business impact of using Zeta is already proven. Independent analysis shows Zeta stands up 50% faster than our peers and delivers a 6:1 return on investment. And with Athena making the platform radically easier and more intuitive, we believe these numbers will only get stronger. This is how AI becomes a habit, not a headline. Adoption scales, usage deepens and the platform becomes harder to leave. We believe Zeta is uniquely positioned to develop Athena for 3 key reasons: First, data advantage. Our Zeta Data Cloud gives Athena rich real-time signals for personalization and prediction that generic AI just cannot match.

Second, native integration. Athena is embedded in the Zeta Marketing Platform, connecting answers to actions and insights to activation and measurement. Unlike our competitors who have legacy tech debt and cannot natively embed AI into their marketing clouds. Third, AI track record. AI is foundational to what we do at Zeta. We have natively built AI into our platform since 2017, and we believe this AI leadership is the reason we are winning today. At Zeta, artificial intelligence is foundational to our business, not an add-on like our competitors are building. The reception from customers, prospects and partners has been incredible.

If you did not attend the standing room-only Athena demo at Zeta Live, I encourage you to watch it in the Investor Relations section of Zeta's website. It is truly game changing. Athena is in internal beta now, and we expect it to be in client beta by the end of Q4 and fully production ready by the end of the first quarter of 2026. OneZeta is a key growth engine for us and a growth flywheel for our customers as they consolidate more data and use cases into the Zeta Marketing Platform. Customers who adopt 2 or more use cases generate greater than 3x the annual revenue of a single use case customer, have our highest NPS score and see the highest return on marketing spend.

We have accelerated this focus under Ed See, our Chief Growth Officer, and the results are meaningful. For example, a leading big box retailer consolidated acquire, grow and retain onto the ZMP at the start of our relationship. That agreement was greater than 3.5x the size of a standard deal with similarly sized enterprises. Second, one of the fastest-growing specialty retailers started with the retain use case and recently added a grow use case. As a result, the customer is expected to spend over $2 million with us in the fourth quarter compared to only $700,000 in the first quarter, a threefold increase, and we expect this customer to continue to grow into next year.

We expect the strong pipeline generated from Zeta Live, combined with the acquisition of Marigold’s enterprise software business, which includes over 100 enterprises, 20 of the top 100 advertisers in North America and more than 40 Fortune 500 companies who are all currently only on one use case, will further accelerate our OneZeta momentum into 2026 and beyond. I'll close with an update on our agreement to acquire Marigold's enterprise software business. We remain on track to complete the acquisition by the end of the year.

After spending the past several weeks getting to know the business and the team better during the closed process, I am even more enthusiastic about the opportunity this acquisition represents. Strategically, the data that we pick up, including the loyalty program, will be game-changing to training our proprietary algorithms, including our Athena, answers and generative engine optimization products and widens our data cloud moat. We hosted several of their employees and customers at Zeta Live and the 1 plus 1 equals 4 opportunity is more clear than ever.

Great numbers are the output. The inputs are great execution, products and people. The reason we are growing at an accelerated pace is simple. We have superior artificial intelligence and data to our competitors that we started developing 8 years ago, not 8 months ago. Our consistent execution over the past 17 quarters as a public company is a credit to our artificial intelligence, our people and our data. Quarter after quarter, we have raised the bar. As always, I would like to sincerely thank our customers, our partners, team Zeta and all of our shareholders for the ongoing support of our vision.

Now let me turn it over to Chris to discuss our results in greater detail. Chris?

Thank you, David, and good afternoon, everyone. The theme of our Investor Day in October was durable, predictable and profitable growth, and our third quarter results are a perfect illustration of this. Our revenue growth, excluding political and LiveIntent, accelerated to 28% in Q3 from 27% in Q2 and 26% in Q1, showing the durability of our growth. Our third quarter results once again exceeded our guidance for both revenue and adjusted EBITDA, highlighting the predictability of our growth.

And we achieved the highest free cash flow margin in our history, achieving the Rule of 40 on a free cash flow margin basis, demonstrating the profitability of our growth. With that, let's dive into the details of the quarter. In Q3, we delivered revenue of $337 million, up 26% year-over-year or 28% when excluding the contribution from LiveIntent and political candidate revenue in the year ago period. We exceeded the midpoint of our guidance by $9 million or 3 percentage points higher than our forecast, solidly within the 2 to 5 points of cushion we typically leave ourselves.

Total scaled customer count grew to 572, up 20% year-over-year and an addition of 5 customers sequentially. We ended the quarter with 180 super-scaled customers, up 25% year-over-year and an addition of 12 customers sequentially. The strong super-scaled customer additions were broad-based across industry verticals and driven by cross-sell of LiveIntent customers and our OneZeta initiative. Scaled customer quarterly ARPU of $579,000 increased 4% year-over-year or 13% when adjusting for political candidate revenue.

Super-scaled customer quarterly ARPU of $1.6 million was up 1% year-over-year or 12%, excluding prior year political candidate revenue. From an industry perspective, 7 of our top 10 verticals in the quarter grew faster than 20% year-over-year on a trailing 12-month basis, an improvement from 6 in the first and second quarters. The additional 20% plus growth industry was telecom, where we have had multiple significant wins over the past year and has been a focus of ours this year. It's also worth noting growth in consumer discretionary verticals like retail, travel and hospitality and automotive remained strong in the quarter.

And finally, all 3 of the non-20% growth industries were up year-over-year between 7% and 17%. Our direct mix in the third quarter was 75%, consistent with the second quarter and an increase from 70% in the year ago quarter, demonstrating continued success of our agency direct-to-channel adoption. Our GAAP cost of revenue in the quarter was 39.5%, a 13 basis point increase year-over-year and 160 basis points sequentially. The increase in cost of revenue was driven by strong sequential and year-over-year growth in display and video, channels where we continue to see customers investing and which remain highly effective channels for customer acquisition and growth.

In the third quarter, we generated $78.1 million of adjusted EBITDA at a margin of 23.2%, 320 basis points higher year-over-year and $7.4 million better than the midpoint of our guidance. This marks the 19th quarter of expanding adjusted EBITDA margins year-over-year. Our GAAP net loss for the third quarter was $3.6 million, an improvement from a loss of $17.4 million in the third quarter of 2024. There were $6.5 million of acquisition-related expenses in the third quarter, which absent these costs, we would have been GAAP profitable.

Third quarter net cash provided by operating activities was $57.9 million, up 68% year-over-year with free cash flow of $47.1 million, up 83% year-over-year and representing a margin of 14%. This represents a free cash flow conversion of 60%, a significant improvement from 48% in the third quarter of 2024 and 57% in the second quarter of 2025. This also includes a roughly 18-point working capital headwind driven by longer agency payment cycles. The improvement in both adjusted EBITDA margin and free cash flow conversion in the third quarter exhibit the strong operating leverage of our model and put us firmly on track to achieve our Investor Day targets of a 30% plus adjusted EBITDA margin and greater than 70% free cash flow conversion in 2030.

During the third quarter, we repurchased 1.7 million shares for $28 million and have repurchased 6 million shares for $85 million year-to-date. We also continue to make significant progress in reducing dilution and stock-based compensation expense. Just like the second quarter, in the third quarter, we had 0 net dilution and year-to-date, our dilution is 1.6% as of September 30. We remain on track to achieve both our 4% to 6% normal course dilution target in 2025 and our $190 million equity compensation expense target even when factoring in the equity we anticipate issuing for the Marigold acquisition.

Before diving into our updated fourth quarter and 2025 guidance, I want to reiterate what I said on the recent Marigold acquisition call regarding forward-looking estimates. Given there could be variability in the close date, which we continue to anticipate will happen in the fourth quarter of 2025, we have not included any Marigold-related contributions in our 2025 guidance and continue to guide analysts to not yet include Marigold in their 2025 or 2026 estimates until the transaction closes. Upon closing, we will provide guidance on Marigold's contribution for 2025 and 2026.

We want to make sure that consensus estimates do not become a mixed bag of organic and acquisition-related revenue. As we have done with prior acquisitions, we plan to clearly break out the organic versus acquired revenue for the first year post transaction upon announcement of closing. With that in mind, we're raising fourth quarter and full year revenue, adjusted EBITDA and free cash flow guidance. Details can be found starting on Slide 16 of our earnings supplemental. For the full year 2025, we are increasing the midpoint of our revenue guidance by $11 million to $1.275 billion, representing a 26% year-over-year growth when excluding political and LiveIntent, which is 5 points higher than our starting point for the year at 21%.

For the fourth quarter, we now expect revenue of $364.5 million at the midpoint, $2 million higher than our previous guidance and representing year-over-year growth of 16% or 23% when excluding political candidate and LiveIntent revenue, which is consistent with our Zeta 2028 plan to grow 20% or greater organically. For adjusted EBITDA, we're increasing the midpoint of our 2025 guidance to $273.7 million, up $9 million from our prior guidance and representing a year-over-year increase of 42% at a margin of 21.5%, an improvement of 230 basis points over 2024.

For the fourth quarter of 2025, we now expect adjusted EBITDA of $90 million at the midpoint, up from our previous expectation of $88.4 million and representing growth of 28% and a margin of 24.7%. We are also increasing the midpoint of our 2025 free cash flow guidance to $157.4 million, up $15 million from the midpoint of our previous guidance and representing year-over-year growth of 71% and a conversion of 57% of adjusted EBITDA. This conversion is up 10 points from 2024. For context, since our initial 2025 guidance back in February, we have increased revenue by $35 million and free cash flow by $28 million.

Now let me transition to looking beyond 2025 and setting our initial organic guidance for 2026. While providing out-year guidance in Q3 is not intended to become standard practice, we're doing so this year because we want to establish a clean organic baseline for 2026 before Marigold is incorporated into our guidance. At our recent Investor Day, we spent time demonstrating our track record of 5 straight years of at least 20% revenue growth and free cash flow margin expansion. The punchline is, we see another year ahead of us with each at substantially higher scale.

In terms of revenue, we're guiding 2026 to be $1.54 billion or 21% growth on 2025 guidance of $1.275 billion. Importantly, this is an organic-only view and does not include Marigold. Our guidance assumes $15 million of political candidate revenue, which we would expect to evolve and is 2x what the midterms were in 2022. We expect $354 million of adjusted EBITDA in 2026 or a 23% margin, up 150 basis points year-to-year. We see an initial view of 59% free cash flow conversion, yielding $209 million in free cash flow at a margin of 14%.

And lastly, we continue to plan for a guidance model with 2% to 5% top line buffer. From a seasonality perspective, we expect revenue in the first quarter to be $314.5 million, up 19% year-to-year and accounting for roughly the same percentage of full year revenue in the first quarter as 2025 and with an adjusted EBITDA margin of 17.8%. I'll conclude where I began. Our third quarter results, updated 2025 guidance and initial outlook for 2026 underscore the durability, predictability and profitability of our growth and reflect the confidence and momentum we have in the business.

Now let me hand the call back over to the operator for David and myself to take your questions. Operator?

[Operator Instructions] Our first question comes from the line of Arjun Bhatia with William Blair & Company.

Perfect. Congrats on another great quarter, guys, very nicely done. One question for you, David. Just at a high level, I'm curious like as you look at the next kind of pocket of spend that's out there, I imagine a lot of it is going to come from media budgets. How do you think kind of Zeta's ROI or ROAS compares to that of the walled gardens? Are you hearing more customers come to you and say, you're getting to parity? Are you already there? Because -- how do you go after that kind of large pool of budget dollars on spend?

Thank you, Arjun. I'm obviously very proud of the team for the quarter. Let me start by saying that if you look at our collective clients, you've got 572 clients that spend over $100 billion a year in marketing today. If you look at the global marketing spend, it's about 75% media and about 25% CRMS revenues. When we look at the breakdown of those 2, we continue to be substantially more profitable than anybody else in the media space. In fact, a number of our clients use our platform, which allows our data to inform the way they market into the walled gardens today, and we already partner with most all of the walled gardens.

So when you think about it, every dollar that is spent through the Zeta Marketing platform returns a 6x return in revenue to our clients. That puts us on par with pretty much any walled garden. And what we're starting to see in a post-Gemini and post-OpenAI world, marketers are looking for new methodologies to create customers and maintain the customers they have. It's been challenging as the vast majority of the questions that are now asked on the Google platform and certainly all that are asked on the OpenAI platform, ChatGPT, are answered on platform.

So what used to be sent to our clients or to other publishers is now being consumed there. So clients are very much looking for new methodologies. We continue to be at the forefront of that. And I think that was a big part of what you saw us talk about at Zeta Live, and I think it's a big part of what you're seeing in the tailwind that we're currently experiencing.

All right. Perfect. Very helpful. And then maybe one just on customer count and me nitpicking a little bit here, but it seems like in Q3, I think you added 5 scaled customers. And if I look at just the last 2 quarters, it's been hovering around 20. Is there anything sort of one-off that we need to consider there, just maybe agencies and us not having brand count visibility? And just how should we think about that metric sort of evolving over the next couple of quarters?

Yes, I'm glad you asked, Arjun. Three data points for you. First, on a year-over-year basis, that 20% growth in total scaled customer count is, a, consistent with where we've been this year and obviously north of our model of 4% to 5%. But to your point around sequentially, we had a really strong progression from scaled to super-scaled customers. We increased by 12% sequentially, which is, if you look back at our history, certainly at the higher end.

And then to your point around agencies, what's also being masked in the total-scaled customer count is we were up 23 brands quarter-to-quarter. So as we continue to have success scaling within and adding new agencies, that doesn't necessarily add to scaled customer count. But in this case, it certainly translates to higher brand expansion. So we're really happy with the scaled customer count expansion this quarter.

Our next question comes from the line of Elizabeth Porter with Morgan Stanley.

I wanted to follow up, David, on your target for the $100 million incremental business after Zeta Live. So could you provide some context around how that target compares to what you've achieved in prior years? And how you'd characterize the momentum coming out of Zeta Live relative to prior years? And then just lastly, how should we think about the conversion time line from that event into bookings and revenue? And is that already included in fiscal '26 guidance?

Thank you, Elizabeth. So first of all, last year, we closed about $57 million in business coming out of Zeta Live, which I think is one of the reasons we were able to grow 500 basis points greater through the year than we gave original guidance for thus far. This year, we're trying to get that to $100 million. I would tell you that as of today, the pipeline is already full enough to get us to that number, and we might see even more meaningful numbers than that. So as you know, we try to be consistent with our beat and raise methodology.

We don't usually give guidance for the next year at the end of the third quarter. We felt because of the Marigold deal, it was important to make it clear that we were going to grow organically 20% again into next year from a top line perspective. I do think that Zeta Live will be a part of that, but I also think it's a part of the buffer that we continue to leave ourselves where we think we can continue to do better than that.

To answer the momentum question, I would tell you my biggest challenge today, Elizabeth, is how do I top Zeta Live next year. It was just so incredibly well received. We had multiple clients just going crazy for Athena, and I just continue to see the most momentum I've ever seen coming out of any event we have ever hosted ever. It's a very exciting time for Zeta right now.

Great. And then just as a quick follow-up. On the LiveIntent piece, understanding it's a smaller portion of the business, but it looks like it was a little bit weaker in Q3 and in Q4 guidance. So wondering if there's any trends to kind of call out there on how that integration is going?

Yes. Thanks, Elizabeth. I'll take that. Look, in short, we're really happy with how LiveIntent is performing. We are accruing at 100% of their earn-out. I think if we were to do things over again, remember, we set that initial guidance skew for every quarter of 2025, about a month after we owned the asset. We've learned a lot since. I think we're also realizing a substantial amount of new product synergies that is flowing organically to the business. But overall, I couldn't be happier with how the integration has gone and the execution of the team.

And what you're not seeing in the numbers is all of the cross-sales from Zeta clients into their products and their products into ours. So we're -- I would tell you, Elizabeth, we think the LiveIntent deal was a grand slam home run, and we're looking forward to having a similar experience with Marigold.

Our next question comes from the line of Matt Swanson with RBC.

David, we've seen the compounding value from an ARPU perspective when customers take multiple products. You talked about Athena and AI being the new UI. Can you just talk a little bit about how maybe that will help with the cross-sell and for people to see the full value of your platform?

Thank you, Matt. I would tell you that I think Athena will be amongst the single biggest drivers to the OneZeta methodology we've ever had. To point out, it is, of course, fully voice activated and fully conversational. So any client by the end of the first quarter should have this fully embedded into their platform. Not only will they be able to work through the existing use case they have, Athena will already be programmed to help them with secondary use case expansion from production level launch.

By way of example, if a client is using us actively for acquisition, they'll literally be able to say to Athena, "Tell me which of my clients are most likely to churn and how do you recommend that we save them." That removal of the friction between the human and the platform is going to allow, I think, for an accelerated growth of OneZeta.

One point where that Matt shows up also in the metrics is one of the areas that as we were preparing post close that stood out to me is not only did each of our use cases grow double digits year-over-year, which has been consistent, but our 2 or more use case count grew over 100% year-over-year. So we're going into capabilities like Athena with really interesting go-to-market momentum.

Yes. And once again, with 100 global enterprises in Marigold that are all on one use case, we see that as a very unique opportunity for the specialty team we've set up under Ed See to get in there and focus on it. But I think that the integration and production capabilities of Athena are going to be really an accelerant to platform utilization.

That's really helpful. And then I'm sure the pipeline has a big -- a lot to do with this. But David, you mentioned that the '26 guide was a quarter early. So Chris, could you just kind of talk us through being one of the first people to give us an outlook into 2026? Just what's kind of building all the confidence and the visibility that you have?

Yes. We talked about at Investor Day, Matt, you'll recall that so much of our installed base not only has been with us 3-plus years, almost 60%, 5 or more years, but there's now a demonstrated history of there, on average, expanding their spend with us 15 points a year. So by starting our guide at 21% year-over-year, which, by the way, is consistent with really the last 2 years of where we started our guidance, we feel like we've left even some conservatism there. The pipeline says a lot.

And then with more and more of our revenue under the curve from really strong signings throughout the year, it just -- it felt like today was the right time. Again, wanted to be clean with our organic baseline before we added Marigold. And I wouldn't want to overlook the really strong addition, not just to revenue, but how much of that revenue for 2026 out of the gate is flowing towards increasing adjusted EBITDA and free cash flow. In fact, this year, from our initial guide of revenue, which was around 21%, so we've obviously added to that since, but that translates to $35 million of revenue and $28 million of free cash flow that's been added to the guide since the beginning of the year as well.

Our next question comes from the line of DJ Hynes with Canaccord Genuity.

Congrats on a really nice quarter here. David, Chris, I want to ask how you're thinking about sales and marketing investment and capacity build-out there. I mean, obviously, the operating leverage is great to see, but sales and marketing actually went down sequentially. And you shared some really powerful pipeline statistics around the growth there and the strength coming out of Zeta Live. So I'm wondering how you're thinking about whether it's time to lean in on growth. I mean, obviously, I guess you're going to get some sales reps with Marigold. But any thoughts there, maybe kind of plan for 2026 would be helpful.

Yes. I mean it went down a little bit by accident. We didn't mean it to. Quite frankly, we're trying to hire every great salesperson we can possibly get, DJ. The challenge is that our existing sales reps have been so incredibly productive that we've been able to continue to grow at a much faster pace than we expected to while simultaneously trying to find more salespeople. We will pick up an incredible sales team with Marigold, both in the United States and Europe and EMEA.

So it feels like we're sort of very well positioned for where we want to go, although -- once again, we did grow 28% top line, 43% EBITDA line -- I'm sorry, 46% don't want to screw us out of that last 3%, but 46% growth on EBITDA and 83% free cash flow growth, while simultaneously, DJ, making some of the largest investments we have ever made into our artificial intelligence and innovation. So feeling very good about where we are organizationally.

You'll see a pretty material tick up 3Q to 4Q with Zeta Live occurring in October versus September like last year.

Yes. Yes. Okay. Makes sense. And then, Chris, while I have you, maybe can you talk about gross margins in the quarter? I mean, direct revenue mix held pretty stable at that 75%. We saw a little bit of degradation in gross margin. Just anything we should be thinking about there as we model the numbers going forward?

Yes, mix was up nicely year-over-year. But to your point, it was -- stayed at that higher end of our range, 75% quarter-to-quarter. What we wrestle with on occasion is mix within the mix. And frankly, this quarter, we had really strong display video channel usage. That display video channel usage is lower than what we average on our total direct revenue mix profile.

But to give you a sense of just how much channel usage we're seeing, our greater than 4 cohorts, so those scaled customers using 4 or more channels was up 44% year-over-year and our greater than 5 or more channels is up over 60% year-to-year. So mix within the mix, but consistent with our model, our long-term model that each year, we want to get between 100 basis points and 300 basis points of efficiency on the cost of revenue line.

Our next question comes from the line of Clark Wright with...

Awesome. It was great to see a strong quarter of organic growth. I was wondering if you could talk a little bit more about the contributions from the agency. You talked about 23 brands being added. How should we think about the growth of the agency business and independent agencies relative to the direct enterprise relationships as we head into 2026?

Yes. We break out our business in a lot of different ways and give you a lot of metrics. One of them we're going to keep to is, keep the disaggregation of revenue down to direct and integrated. But what I will point to is as a proxy for how healthy our agencies are growing. You would see the direct mix was up over 30% on a year-over-year revenue growth basis. And then mix within the agencies, let me just look at my notes here, was up pretty substantially as well from a direct perspective. Let me just get the exact data point here for you. Matt, if you have it. let's say, direct -- agency direct mix was up from 52% direct to almost 60% this quarter.

I mean direct to enterprise -- yes, I'm sorry, Clark, I was just going to say direct to enterprise continues to be the vast majority of our business, and I think will be for many years to come. But we love our agency clients, and we continue to expand with them very nicely. So it's been a really good blend to have both.

Our next question comes from the line of Jason Kreyer.

All right. Great. So first on Athena. When you think about your 572 scale customers, are there specific groups or segments of that where you think Athena resonates better than others?

So Jason, I would start by saying I think our direct enterprise clients will probably adopt it in a more meaningful way first, which is not to say we don't think it really plays very well with the agency clients. From a vertical perspective, I don't really think it's going to be that differentiated.

I think if you have not seen the demo yet, which was standing-room only, I say standing-room only, there were people sitting on the floor who physically asked me to move so they could see the demo. We have a recording of it on our Investor Relations site. But I would tell you that when you put that type of power in the hands of a client, they're going to really adopt it very, very quickly. And we're excited about that.

And just going back to the momentum topic. At the Investor Day, you had talked about 80% faster onboarding. There's some operational streamlining you've been doing. So you just hosted Zeta Live, biggest events for building the pipeline. I'm just curious, is there a scenario where that pipeline of potentially $100 million can transition to revenue at a faster pace than we've seen in the past?

Let me start by saying our goal is to close $100 million in business, not just get the pipeline to $100 million, Jason. So we're on the same page. When you look at the fact that we've given guidance early to next year, we've now raised the fourth quarter this year, it's our 17th quarter of raising in a row. We feel like we've got the wind at our back or we wouldn't be in a position to do both of those things.

So I think that our confidence level is very, very high based on where the record pipeline is, what's coming out of Zeta Live. And yes, we are closing deals faster than we have in the past, and we are onboarding them substantially faster than we have in the past by automation and AI internally.

Our next question comes from the line of Terry Tillman with Truist...

The first question is, I was just hoping to double-click on the replacement cycle opportunity. I think there was a stat that was provided at the Analyst Day about the last couple of quarters, the RFP activity had been up quite a bit. And I don't know if that's independent of the Zeta Live and the pipeline that you built out of that.

But just maybe you could comment a little bit more around where we are in this replacement cycle opportunity and maybe Athena helps with that. And kind of related to that, and hopefully, this doesn't become a 5-part question is like maybe there's pricing and packaging and other things you could drive to kind of minimize the inertia for those folks to move to your platform? And then I have a follow-up.

Yes. So let me start by saying that the replacement cycle continues to be at full scale. And we are not just seeing more RFPs in our company's history. We are seeing the largest RFPs we have ever seen. And if you look at the legacy marketing clouds, the guys like Salesforce, Oracle, Adobe, one of them is leading the industry. The other 2 are legacy. They're great companies with legacy technology. We are the next generation of Marketing Cloud.

And we're really focused on how do we continue to win in what is an even faster accelerating replacement cycle. As it relates to Zeta Live, we came -- we went in with a record pipeline. We came out with a meaningfully larger record pipeline. It's just -- right now, we are firing on 11 of 12 cylinders. I don't say 12 of 12 because I don't want to jinx us, but we're feeling very, very good about it.

That's great to hear. And I guess I won't ask for more cylinders past 12. Maybe that's for another conversation. But in terms of the independents, I think you added 3 last quarter. I was impressed at the Analyst Day, one of the -- your folks that was on stage was an independent, and it was pretty impressive their kind of passion for the platform. Maybe you could just give us an update on the independent side in terms of agencies.

Yes. So there -- it's growing very rapidly. And when you look at the different agencies that we're now platforming, even though we call them independent agencies, each one of them is representing between $1 billion and $2-plus billion a year in marketing revenue. So very excited about what's happening there, Terry.

We've built out a sales force that's now solely focusing on independent agencies, and they are really, really rocking. I would tell you, we had -- I can't give you the count, but so many independent agencies attended Zeta Live, we had a separate breakout to spend time with them, and it seems to be going very, very well.

Our next question comes from the line of Gabriela Borges with Goldman Sachs.

David, my question is on Athena and more specifically on the process for implementation and deployment within customer environments.

Yes. So Gabriela, I don't know if I lost you -- I'm sorry, I lost you for a second there. I heard the Athena and then you got into deployment?

Yes, the process of deployment and the learning curve on deterministic versus nondeterministic outcomes when you work with customers to deploy Athena.

So first of all, great question as usual. All of our deterministic -- all of our actions at Zeta are deterministic. So if you think about the Data Cloud, you've got the 242 million deterministic individuals in the United States, over 550 million globally. Athena is going to be built right into the Zeta Marketing Platform.

So literally, anybody who's using the ZMP, which, as you know, has a common user interface for setup and a common user interface for reporting, will be able to use Athena seamlessly to activate and learn. It's almost like a data scientist and then an execution capability in one voice-enabled conversational platform. So everything that Athena does will be fully deterministic and will allow for deterministic attribution capabilities.

Our next question comes from the line of Richard Baldry with ROTH Capital.

Can you talk about sort of the architecture around Athena? And another thing about is, how easy or challenging would it be to extend that to cover new platforms? Obviously, something like Marigold would be a place to look at.

Yes. So I mean, Athena's architecture is fully internally built. We are partnering with OpenAI as it relates to the voice interface, and we're excited about that. As it relates to what we can layer it on top of, we can easily layer it on top of any platform that has an open API. And when you think about where we're trying to go long term, yes, Athena is native to the application layer at the Zeta Marketing Platform, but as we integrate other platforms, it can easily be layered on top initially through an API integration. And then as we fully integrate them into the platform long term, it will become native to their application layer as well.

So last 2 for me. Does having Athena make you likely to be more acquisitive maybe as tuck-ins because you can bring it under that umbrella kind of easier? And then maybe for Chris, do you think long term or even short term about the buybacks as a percent of free cash flow? Where is your thinking lately on that?

So as it relates to being acquisitive, as you've heard me joke, Rich, we've been in business now for 17 years. We've bought 17 companies. It's highly probable that there'll be an 18th at some point. I don't know if Athena makes us more acquisitive, but it certainly becomes a bridge into anything we do going forward. And as we think about today, being the #1 marketing cloud using artificial intelligence and data native to the application layer, Athena gives us the opportunity to expand and increase our TAM and our addressable market by moving into other business intelligence and other opportunities. Chris -- As it relates to the buyback, Chris was sort of jumping on something for the second.

We continue to focus on using greater than half of our free cash flow for retiring shares and repurchasing shares. Quite frankly, the only reason we didn't buy more over the last quarter was because once we signed the agreement to do Marigold before we announced it, we were an internal quiet period. We weren't able to buy stock back. So I believe we were in the mid-70s as a percentage of free cash flow for share repurchasing year-to-date. I could see us continuing at those.

We've done about 85% year-to-date. We have a lot of dry powder in the next 200 program.

Sounds good. Congrats on a great quarter.

Our next question comes from the line of Zach Cummins with B. Riley Securities.

And congrats on a strong quarter. David, I thought it was notable to call out that you've seen some strong momentum in the telecom vertical. So just curious, what's going so well on that front in terms of building that momentum with telecom customers? And is a lot of that success really coming as a displacement for other solutions with these major customers?

Yes. I mean you've got a lot of different telecom players out there really, really struggling for growth. And our platform allows them to grow at an accelerated pace at a lower cost than our competitors' platform. So what I would tell you in almost all cases, we're displacing one of the major marketing clouds at this point. There's very few companies that are sort of doing this stuff internally. So we're very excited about telecom. It's growing at an accelerated pace, and it's something we think will continue. Chris?

Yes. A couple of other points, I think, Zach, that are relevant on the industry verticals. As you know, we report the industry verticals on a trailing 12-month basis, and this was the first quarter that telecom made it to be over 20%, but it's actually been growing really strongly in the last 2 quarters. So that was good to see. The 7 out of 10 growing over 20% is a marked improvement from the -- what's traditionally been 6 for us, obviously, telecom being that new entrant.

But even those not growing at 20%, we're growing between 7% and 17%, which is great. But with so much focus in the investor community on what's happening in the macro, I think it's also worth highlighting that verticals that we've seen to be the most consumer discretionary, retail, travel and hospitality, even automotive have continued at their very strong growth rates. What we're seeing is even when there's difficult times out there, clients are moving to us in an accelerated pace because of our substantially better return on investment than most of our competitors.

Understood. And a follow-up for Chris, just around the free cash flow conversion. It's nice to see the strong execution here in Q3 even despite the working capital headwinds. As we think about modeling out into future years, do you assume those working capital headwinds regarding collections with agencies will start to ease? Or how are you thinking about that as we move forward from here?

If you adjust, Zach, for the pure timing of the agency's longer payment cycles, we would have been again at 80% and better free cash flow conversion. And if I then go backwards to -- I should say, forwards to the Zeta 2030 conversion target of at least 70%, you could argue we've even built in for a continued headwind from the agencies and not needing that to be fully neutral for us to get to that at least 70%.

Our next question comes from the line of Jackson Ader with KeyBanc...

First one is on the, I guess, visibility into 2026. David, you mentioned, normally, we don't get this kind of forward guidance a quarter early. But I'm curious like is it more than just the pipeline? Do the large customers you're doing business with actually -- do they have commitments that give you more confidence or that the spend level is going to go up in the future that might not have existed in years passed?

Yes. Yes. We're seeing much larger contracts from our larger clients, and it's giving us far more visibility and comfort in the numbers.

Right. So it's -- okay, pipeline bigger, but also visibility also bigger?

Yes, Jackson, to be specific, large clients are giving us larger contracts than we've ever had before and far more visibility into our forward numbers than we've had in the past.

And tactically, Jackson, this time of year, frankly, August, September, we're in our kind of next year planning process anyway, not just internally, but with our customers. So even though historically and what we would normally expect under absent a Marigold-type transaction giving guidance in February, a lot of that work is effectively already done.

Got it. Okay. Okay. And then a quick follow-up. You mentioned the political candidate revenue expectations for last year. But curious whether you have any initial expectations for advocacy and how that works in that in the, call it, like the off-cycle election years?

It's followed, Jackson, a similar pattern as candidate spend, meaning if you go back to the midterms in 2022, where we had political candidate revenue of around $7.5 million. This year, we're planning for effectively double that. I would think along similar lines for advocacy from kind of midterm to midterm.

The tricky part for that for us and why I specifically said in the prepared remarks, I think this number will evolve is those deals can come into the pipeline very rapidly, much faster or I should say, later in the process than what a typical enterprise or an agency deal would come in. So it tends to be something that happens on a quicker time line for us. So hence, why I think that number is going to continue to evolve.

Our last question comes from the line of Koji Ikeda with Bank of America.

I wanted to ask a question on Marigold for 2026. And I know it hasn't closed yet, but really wanted to ask around -- because you've had such success in the past with acquisitions, I think about acquisitions where you guys -- for you guys with like more around 1 plus 1 equals more than 2. And so with your guys giving out a '26 guide out there, thank you very much for that. And previously, you've kind of given a guide for, I think, $190 million for Marigold for 2026.

I mean, I guess where I'm going with this is that -- it sounds like just stacking $190 million on the $1.54 billion guide for 2026 could be understating the opportunity with Marigold. Of course, I don't want to get over my skis here, but just given your track record with acquisitions, it doesn't seem like that's out of the realm.

Yes. So let me start by saying we do not want to have the guidance combined for the two yet. The reason we put the organic guidance out was because the last time we did this with LiveIntent, half of the analysts added it, half did not, and it created a tremendous amount of confusion. So when we do close that deal, Koji, which we expect to do this year, we will 100% update what we believe it will do on top of the $1.54 billion. And I just wanted to get that out there.

Second, we started this year at a 21% guide, and we're going to -- we're already at 26%. So we've added 500 basis points from where we expected to be at the beginning of the year. As you know, we've known you now for a very long time. For 17 quarters in a row, we've beaten our guidance and raised our guidance. Our goal is to be sitting here at the end of next year and saying we've done that 22x, right?

So we are very good at M&A. We have our pillars. We believe that Marigold fits every one of our pillars, and we believe that it's going to create a really nice tailwind to the growth of the combined company, specifically around taking their 100 global enterprise clients and making them from one use case to multiple use cases. As you point out, we always want 1 plus 1 to equal 4. When you look at moving from a single use case to multiple use cases around the Zeta opportunity, those clients generate between 3 and 3.5x more revenue than clients that are just using one use case. So I do think that the Marigold acquisition will lead to a really nice tailwind into next year, if that makes sense.

Yes, totally does. And looking forward to that press release on the closing of Marigold, absolutely. And maybe just a follow-up for you, David. I did want to -- now that on the back of Zeta Live, I did want to ask how Zeta's brand image is evolving with your customer base? Maybe compare and contrast how customers are looking at Zeta today versus how they looked at you 3 years ago?

Well, I'm not even sure you could put the way they looked at us 3 years ago to the day in the same conversation. It is so advanced, Koji. What I would tell you is we started this journey and 3 years ago, we were at Zeta who, which really meant when we walked into a sales call, we would have to spend 50 minutes of the first hour explaining who we were and why we were in the room. Our goal was to get to why Zeta, meaning we know you're here. We know why you're here. Why should we pick you over your competitors?

The next evolution really is Zeta now. I need Zeta, how do I get you into my stack? And the final is must-have Zeta. We're still a ways off from that. That's sort of like Microsoft. But what I would say is we are very solidly in the why Zeta. We get into the room and people know who we are. We are the advanced player in our space. We are looked at as cutting edge. We are looked at by marketers as a very important component of their tech stack, and they're really looking at us as a sort of game-changing company as it relates to AI data and their ability to deploy it organizationally.

Ladies and gentlemen, there are no additional questions at this time. Thank you for your participation. This does conclude today's teleconference. You may disconnect your lines, and have a wonderful day.

Good morning, and thank you for joining us today, obviously, in person as well as those virtually. We have an exciting and informative day planned for you. We have new product releases, new members of management, customers and marketing experts you'll be able to hear from and engage with.

New structural views of where we believe we can take our adjusted EBITDA margins and free cash flow margins while sustaining our organic at least 20% revenue growth rate and new financial metrics that both underpin past performance as well as our future expectations, all intended to demonstrate the theme of today's Investor Day, a theme that's been entirely generated from your feedback.

They can be boiled down to three areas: First, durability, the durability of Zeta's proprietary data, our competitive advantages and our revenue growth rates, the predictability of our business around the ROI that we generate for our customers as well as the consistency of our results and profitability. You'll hear today how we help our customers make more money and what sustains our margin expansion. So with that, let me kick things off with a few slides, and then we'll dive into the agenda and the rest of the day.

With 16 quarters of track record as a public company under our belt, we have enough of a sample set now to draw some conclusions and compare ourselves to cohorts. One of those cohorts is through revenue growth and free cash flow margin expansion. And there's a misperception in the market that there's a trade-off believed to exist between driving high growth and increasing your profitability, maybe because so few public companies have been able to do both.

As you're familiar with, Zeta's model is to grow revenue each year at least 20% on an organic basis while investing principally in sales, marketing, R&D and extracting savings everywhere else. Case in point, over 500 public technology companies, that's a lot. No one knows that more than you as investors and analysts.

However, there have been 22 public technology companies that from 2021, the year in which Zeta went public to what's expected of them this year that have grown revenue at 20% or greater every single year during that period. That's not a lot. And that's frankly an accomplishment in and of itself. But there have been 8 that have been able to do that and that's the operative word, and expanded free cash flow margins every single year over that period as well. Zeta is one of those 8. It's rarefied air, and I would argue it's the epitome of durability. Now as an investor, you're not just looking for durability, you're looking to underwrite predictability. In every year, Zeta sets growth and margin expansion goals. And in the period in which we've been public, we've exceeded those goals, but not to be overlooked. We're the economic conditions that existed over that span of time. In fact, most of which were known for their headwinds.

For example, in the aftermath of COVID, in 2021 and 2022 with global supply chain disruption, many growth rates stepped back, Zeta's compound growth rate over that period of time was 27%. In 2022 and 2023, amidst rising inflation, Fed rate hikes certainly impacted the consumer, you would think marketing and advertising budgets as well, Zeta's compound growth rate over that period was 26%. And as we sit here today, through 2024 and the beginning of 2025 with new U.S. tariffs shifting monetary policy, federal workforce reductions, broader workforce reductions, each of which causing their own recessionary fears, based upon our guidance, our growth rate over that 2-year period is expected to be 32%.

The point is Zeta's growth has been durable and predictable throughout, but not just durable and predictable, increasingly more and more profitable. Since going public in 2021, we've increased our annual free cash flow generation by more than 8x and on a compound growth rate basis over that period, 70%. We've taken our free cash flow margins from 4% to 11% and have effectively doubled our free cash flow conversion over that time period as well. Not only do we see these types of rates of improvement as sustainable, but what I'll talk through later today to carry us even beyond Zeta 2028. So with our agenda of durable, predictable, profitable growth in front of us, let's dive into what we have in store for the rest of the day. In a moment, I'll hand the baton off to Steve Gerber, our President, to talk about Zeta's competitive edge.

You'll then have a chance to hear from our Chief Operating Officer, Matt Mobley, talking about the drivers that have contributed towards our margin expansion to this point. But I think more interestingly, what are we doing today to leverage automation and AI to further bend the curve down. We'll then shift gears a bit. You'll hear from Chris Monberg, our CTO; and Neej Gore, our Chief Data Officer, who will dive into the platform and talk about many of the new products being announced today in even more detail tomorrow at Zeta Live.

We'll take a break. And then after that, we'll hear from external stakeholders through the form of panel discussions, first, hosted by Ed See, our Chief Growth Officer; and then by Jed Hartman, our President of Activation. I'll jump into the financials, and then David will come on stage, wrap things up, pull it all together, and we'll have an extended Q&A session with the entire group. So with that, let's kick things off and join me in welcoming Steve Gerber, our President to the stage. Steve?

Good morning. Thank you, Chris, and thanks to all of you for being here. So let me start with a question. How many of you saw the Yankee game last night? Thought there'd be more sports fans. So if you didn't see it, Aaron Judge launched a moonshot that clinged off the foul pole. It changed the course of the game and quite possibly the Yankees playoff run. The announcer said for the last 10 years that ball would have landed foul. Last night, it was fair. Same swing, new conditions, better outcome, new story.

After 16 years, at Zeta in '26 at the intersection of data, technology and marketing and is a true believer in the power of parable, I can't help but see the parallel with us. We're taking the same swings but in better conditions and more are landing fair. But greatness, as you know, isn't just about [ goudy ] stats. It's doing it again and again and again. It's meeting the moment. So today, I'll show you why we are meeting the moment and how we're making growth predictable for our customers and for Zeta.

Now let's go way back to two years ago, the last time that we met in this setting. Since that time, we put up some [ goudy ] stats. Zeta has outperformed on every single dimension. Growth metrics, customer metrics and innovation that moves the needle for our customers and for Zeta. Most importantly, we believe this is outperformance with headroom. At our town hall yesterday with our entire company, we said something that we truly believe. We are just getting started.

But we know that it's more than just putting up big numbers. Investors value what endures. Durable growth, predictable profits, defensible advantage. That's the standard and that's meeting the moment. Our model delivers on each of these. And today, I'm going to go deeper on that through the form of answering the questions that matter. I will talk about why now is the moment, why Zeta is built to meet it, why acceleration is structural and why growth is profitable and predictable. So first, why now? Why have conditions changed?

So the market is at an inflection point. These forces, which I will detail further are converging. That's the setup for category change, because when forces converge, markets reset, and that's what we're seeing. The replacement cycle I talked about two years ago is accelerating. We're seeing cracks in legacy stacks. Only 33% of MarTech tools are currently used by enterprises overbuilt and underused as the recipe for change.

At Zeta, we've seen a 70% increase in RFP volume. And this tailwind isn't felt just by us. The whole cohort of scaled insurgence is growing 3x faster than the incumbents. The conditions are changing. This is the changing of the guard. And that's what we're seeing. So it starts with AI, but it's not just AI. AI is the spark, but what we need to recognize is that AI is a catalyst for replacement, but capitalizing on the promise of AI beyond polishing memos and generating [ CAT ] creative images is hard. A recent report that many of you saw from MIT showed that 95% of AI pilots fail. And here's a big reason why? AI is fueled by data and data pipes at most enterprises are leaking. That's why as enterprises rethink their approach to technology in the AI era, they are starting from the ground up not from the shiny presentation layer down.

Now that's just one consequence of a change in tech strategy. From the beginning of the digital era, CIOs would pick from one of two approaches, best-of-breed products or single-sourced vendor, usually implemented by an SI. That's why you may have heard a CIO say something like, we're a Salesforce shop, even though Salesforce is 17 different companies. This approach has led to the overbuilt underused stack of today. But the old ways are changing. Rather than getting locked into a cloud as container, enterprises are constructing cohesive consoles that are comprised of components, modularity, not monoliths. Fully 77% of the enterprise RFPs that we see are focused on one thing, unbundling clouds. Right. I got through 6 without a problem.

The modularity isn't just cleaner, it's faster to value. 68% of replacements are evaluated within six months. So proof is the gate to scale. That's why the CFO is now in the room. 79% of MarTech purchase decisions have CFO decision power. That's a change. Enterprises are now buying the business case, not the bundle. And I'll finish this with this statement, Replacement cycles turn when buyer standards change and boy, are they changing?

The other big change is the elevation of the CMO. Along with the CFO, they are at the table making AI-powered tech decisions. Today, CEOs have put CMOs on the front line of growth. CMOs overwhelmingly see AI as a game changer. 5 and 6 -- AI is a game changer, but the same 5 of 6 believe that their infrastructure is too rigid and fragmented to capitalize on the power of AI. So the gap is not ambition, it's architecture and under the hype most programs stall on a shaky data foundation. And that's happened even after massive investment in getting their data house in order driven by a fight for fidelity after the changes in ID and new consent rules. And a demand for data control because in the last era, enterprises gave that up to the walled gardens.

You raised that to the power of AI and first-party data at enterprises has become the center of gravity. It's become a strategic asset. Now the investment in Snowflake and Databricks more than 1,300 enterprises are at scale with those companies and the like. Getting that done was necessary, but it's not sufficient. The question remains, once that is in place, what runs on them? And the winners won't just have the data to run where the data lives and turn that into sharper, faster decisions and measurably better performance.

Better performance comes from a better system, a new system that is modeled off of what the Walled Gardens didn't, with first-party data at the core of an enterprise's ecosystem, authenticated identity is the connective tissue. It's how to get precision and scale. One brain coordinating both paid and owned channels just like the Walled Gardens. But again, ambition is ahead of architecture. Marketers want personalization across the journey, but fewer than one in three can actually do this at scale. That's the personalization gap that we've talked about before, and it won't close with channel-centric tools. It needs one decision engine across every touch point, which is why convergence is identity-led and outcome-driven.

Convergence is driving the birth of a new category, what we call AI-powered marketing. This is an answer driven system, not another stack. It's a smart system that gets smarter over time, and delivers better results over time. It requires three things: authenticated identity, a central decision engine and closed-loop measurement. It delivers precision at scale, faster time to value and compounding returns. Bringing this to life is the catalyst for the industry shift from disconnected stacks to a cohesive system. So why is this the moment?

The switch is underway with three shifts in the marketplace. The replacement cycle is accelerating because buyer standards are changing. It's not just AI. Buyer standards are changing. And because of that, a new category is emerging. So the market as it moves from stacks to systems and systems that prove outcomes faster and more predictably, those are the ones that will win this cycle. So why Zeta? Because we are purpose-built for this exact switch. This is what we've been doing for the last 8 years is preparing for now.

Our job is to make it simple for enterprises to transition to AI-powered marketing and turn measurable results into a growth engine. A growth engine for enterprises and a flywheel for Zeta. But why Zeta begins with our reason for being? Our promise is simple, compelling and provable, more value with Zeta than without. It starts with speed on ramps and weeks, outcomes in a quarter. Simplicity, the easy button, on to AI-powered marketing we are consolidating stacks, which is shrinking the time to value and driving material savings. Lastly, certainty.

Forrester's TEI shows the 6x return on ad spend. That combination makes it hard to compete with Zeta, and it also showcases Zeta's Edge. The Zeta Edge is foundational. We run where the data lives. When people hear Zeta data, they think super graph, which Neej will go much deeper on today, that's our fused identity and intelligence system. And that's true, but it's only one part.

Our data foundation also includes low- and no-code connectors that ingest data from all corners of an enterprise and outside of their four walls, and it pushes it back out as actionable intelligence. And it runs inside a container with a robust yet flexible data model. So it can serve as the system of truth to drive the business from. That is durable infrastructure. It is not episodic activation, and it's the base for everything that follows.

On that foundation sits one decision engine, answer driven coordinating painted own channels. We built this system to answer the fundamental questions of marketing, who to reach, what to say, how and where to execute, decided in context, not channel by channel. That's how you close the personalization gap and get precision at scale, but advanced AI tools let us go a step further, it allows us to answer the hardest question of all, why?

Why is what unlocks a flywheel for our customers and it locks Zeta in. And when we think about our data foundation, it exists to do one thing. To create an enterprise decision standard. Now standards is something you're going to hear a lot about today. Another area where we've done it is to create a proof standard. Along with my co-author Ed See, who you will hear from later on today, we developed a new index called the true value of marketing, which was launched last week in the Harvard Business Review. It is one number to value -- to measure value creation. Think about NPS for marketing. So if NPS changed how companies listen, TVM changes how marketers decide. The core idea is that one standard, one truth beats 1,000 dashboards. It's the core of My Zeta Live panel tomorrow, 9:15, I hope you all get there early, and it will receive more support in the ecosystem later this quarter and into next year because our goal is to make this ubiquitous, ubiquitous like AI.

AI is ubiquitous, but it has to live where users actually work, not a separate screen. So think of a Bloomberg's dial command center, one screen where work and answers live side by side. Ask and play in English, see the answer and execute with approvals. That's how AI becomes the new UI across the enterprise. And that creates an enterprise interface standard that my partner, Chris Monberg will go much, much deeper on today and tomorrow at Zeta live. So I know what you're thinking. How did I miss the Yankee game last night.

You may be thinking that couldn't others do this too. And the short answer is that design is destiny. Not all platforms are built for this era. Workflow first tools, optimize point-and-click journeys. They're great for manual teams, but the lift is still human powered. Channel-first tools optimize individual lanes. They sure are strong in silos, but they're weak across the whole. This is an era where the whole is greater than the sum of the parts.

Zeta is data and intelligence first, composed on the data foundation, learning in place and judged by outcomes. Workflow-heavy suites, especially those aimed at SMBs moreover, are the most exposed as general AI Copilots compressed the UI, and in that context, it's data quality, decisioning and measurable outcomes that are the differentiators. The bottom line, AI is only as powerful as the data that fuels it and the outcomes it drives and not every platform is built for that. So why Zeta? Why are we meeting this moment?

I talked before, why now buyer standards have changed. We are the ones aligned with buyers' needs. The Zeta promise is showing, not telling our incremental value. We have a warehouse native core that's easy to adopt, hard to leave. We establish enterprise standards across decisioning, proof, interface. And most importantly, we are optimized for AI. That is why we are positioned to meet the moment. So why are we accelerating?

Well, the standards are getting set. The flywheel is starting to turn, but we know we need to speed up. The window of opportunity is open, but we know it's not open forever. So we have three drivers of outsized growth that we are pulling the levers in parallel. First, AI-powered operations, expand capacity and capability at a lower cost per unit, that's how we hit that 25% plus adjusted EBITDA margin. Second, what I've come to call impossible products so that we could seize the leadership position in the AI race, leading to a doubling of our scaled customer base. Third, which I will go much deeper on and then my partner, Ed See, will have a panel today and tomorrow talking about, which is packaging and paving that make it simple to start and obvious to expand. That's how we get to a 4x ARPU over time.

These are individually important, but collectively, these are transformational. Together their speed to scale and a repeatable path to accelerated growth. I'll go through in more detail, but each of the speakers after me are focused on each of these topics. So first, I'll talk about AI-powered operations. This is Zeta-on-Zeta. We run our own operations on agents, not on tickets.

So what does that mean? It means on-boarding is 80% faster. Cost of revenue was 31% lower and productivity is tremendously higher. Same team, same global footprint, new tools to deliver more throughput and less variance. That's how we scale execution without scaling headcount. You're going to see a lot about impossible products, impossible products, raise our trajectory. Neej and Chris today and tomorrow will talk about our incredible, I mean, impossible road map. But I'm going to spotlight on these four to bring it to life for you.

Vertical clouds, think about health care or commerce or advocacy. Verticals in which the right data at the right time is the difference between success and setbacks. Zeta Media Engine in partnership with Snowflake is the easy button for the world's largest enterprises to capitalize on AI-powered marketing full stop. Prospect CDP is one of one to disrupt customer acquisition. And lastly, Zeta Answers, that's what is fueling AI-powered marketing.

Now the reason I spotlighted these four is that they blend both owned and paid channels, one brain, every channel. They're practical innovations. They move the numbers for customers and for Zeta, and their Blue Ocean. Others cannot play here, without our data foundation without our capabilities. Now I just want to come back to why impossible, and we've even got the TM against it.

To me, these are products that make our customers say wow and CFOs say yes. But it's about OneZeta of how we bring this all together. OneZeta is how we make it simple to scale AI-powered marketing. We build on a win. We take the first on-ramp, capture what works and then make it a repeatable model. We always show and we don't tell. Every expand and extend step comes with a business case tied to the numbers that matter. And then lastly, it's what I call Growth-as-a-Service. We add the next use case without any rewiring still aimed at the same North Star metrics.

So for customers, this means fewer vendors, one brain, faster wins. For Zeta, each win raises our value and makes the next win easier, more predictable. It's the conversation mover from tactics to predictable results. And with OneZeta, we are simple to start, obvious to grow and super hard to leave.

Now many of you asked why Marigold, the hidden question. We really think of Marigold as an accelerant for the OneZeta model impact. It's a bigger top of funnel, more enterprise doors and new regions. It's deeper signals, loyalty and first-party data at scale. And it's a new distribution option. It's a clear path to a bigger and more impactful publisher cloud.

And the category play is compelling. AI-powered loyalty is a better offering where there is no sales force, there is no Adobe to rip and replace. As we scale the same standards across a larger base the unit economics improve, that's operating leverage that we can count on in the quarters and years to come. So when some acceleration is happening because OneZeta ignites a growth flywheel for us and a performance engine for our customers. Here's how it turns.

We embed the Zeta data foundation. We set the decision standard across all of the components that I talked about. We power decisioning and orchestration through both paid and owned channels and then we closed the loop to prove our value. Proof, unlocks scale, scale unlocks profitability, profitability unlocks predictability. Each cycle raises our share of wallet while lowering our cost to serve. That is acceleration that could be measured and repeated, and that's what makes growth predictable. So predictability shows up in our math. When we go beyond land, expand and extend into embed, we see massive upside.

Customers who embed, adopt more use cases and generate more revenue. That lifts unit economics and sets up the next turn. The point, expansion isn't luck, it's a playbook. And we have more than 80% of our customer base with headroom for significant growth because embedding multiplies impact and our unit economics.

Now I'm going to walk you through some examples here because OneZeta has evolved from a sales motion into an operating model. However you enter with us, Platform Out, Media In or OneZeta as a system, the path is the same. Start small, show results fast and then make it part of how you operate.

Platform Out, where we would start with the CDP or some other embedded technology, for a major retailer that was where we started, but the hinge point, where this went from smaller to bigger and bigger to transformational for them was when we were able to take Connected TV and make it an addressable channel for them. We were able to connect an individual to in-store visits and in-store visits to sales so they knew what to scale, that's knowledge they could not have gotten anywhere else, and that is something that's repeatable creating a flywheel for them.

Media-In where we started with a smaller activation program. This is a major airline. We have gone from a spoke in their hub to a hub and some big spokes. And that's because they began to see that we knew more about their customers and their prospective customers than they did. We also were able to prove to them that loyalty did not mean devotion. So we focused on those loyalists that they were able to get more of share of wallet, because it all started with authenticated identity.

Authenticated Identity is the unlocked to AI-powered marketing. And then what we've done more and more of is starting with what I call marketing-intensive middle market companies. The ones we're marketing is the distinction between surviving and thriving. And we've begun to pitch the full system out of the gate. When we do that, they commit to us. Everything connects. Nothing competes. All the tools are built for each other for us and our partner. The ZMP becomes the center of gravity and what that happens for us is it increases deal size materially in this particular case, 4x larger out of the gate, but even better, they are seeing much stronger results from us than without us with this change.

Let me add one more for you, as I talked about authenticated identities, is the unlock to scale. We just met with a Fortune 50 company top 100 advertiser and talked about our AI-powered marketing system. Every program begins the same. We connect their first-party data to our SuperGraph. The CMO was expecting us to match at a rate of 70% or 75%. The gold standard is 80%. The first run came back at 92% and the CMO who we like to think of as a friendly said, "This cannot be, that is impossible". So they ran it again. They made a few adjustments. They worked with our team, wanted to make sure everything was connected properly and it came back with a new number, 94%. That is how you win in this era because these are not in isolation, the data foundation makes this repeatable and it ignites faster ARPU growth.

I will now talk about how once we embed this data foundation, we take our share of wallet from that 1% to 2% range that we are starting at to that 5% goal that we have over time, embedding the data foundation with our SuperGraph at the center of their AI-powered system is the unlock for extended use cases increasing audience scale, expanding our share of marketing budget that we can address.

And then ultimately, when you are delivering results at scale and you are locked in with standards you have pricing power. This is our end state. The cadence is steady. It's about one meaningful step per quarter until we get closer and closer to that 5%, and better unit economics fund that expand, extend and embed. This all comes back to business cases that prove our value, proof unlocks scale.

So I said there were four questions that I was going to address today, but I do have a fifth. And it's the one that decides who leads this new era? How do you move from predictable performance to definitive leadership? And the journey that we've been on at Zeta is to become one of one. And the way we believe we do that is to set the standards to become the standard. And it starts with the embedded data foundation, the dominant data foundation, it's then on top of that, the three enterprise standards that I talked about, a decision standard for how the work runs, a proof standard for how it's funded and an interface standard that's a command center that people actually live in.

With these standards, tools don't compete. They connect, reducing the cost of ownership and locking us in further. Together, these create a compounding growth engine, which makes us one of one. Companies that are one of one lead new cycles. What we've seen today is that the conditions have changed, and we are meeting the moment. I believe you can see why we have such conviction that only Zeta can lead the AI revolution and marketing. I'll now turn it over to my colleague, Matt Mobley. Thank you.

Good morning, everyone. We're starting actually on sort of the application of some of the technology on these pieces. So admittedly, I think the [indiscernible] side of this conversation will come when Chris and Neej come out to talk about the innovation that we actually create. But the -- my argument is to it, as I look at these things is the fact that as much innovation that we can create out there in the AI world, the problem is people are sort of like struggling to sort of get through sort of the notion of how they look at the applying it to the actual business.

We -- we're in a world where there is a place where sort of AI is sort of ramp it across the organization. People are sort of pursuing sort of the options to it, but are people actually getting value out of the things that they're actually doing with it? We can create the sexiest agent in the world that does everything for you in essence that goes to it, but are the -- do people understand the expectation set within the organization that's out there.

So -- as we look at it, we think about it, we're saying, "Hey, listen, Zeta is becoming this fully AI-powered sort of organization." It's not just about the things that we pass on to our customers, but it's also about the things that we create for ourselves in order to do the work and to accomplish the things that we want to do, at a level of being able to lower costs and increase productivity to those things.

But also focused on not only operating leverage, but even as we think about like platform adoption, as they think about what pieces are people sort of using and being able to do within the platform every day, do the agents and does the AI help promote those things and educate our customer base and help them understand how to sort of move on to new use cases in it and ultimately giving them something in which we deliver to, be it the notion of mail or e-mail or SMS or all these things, but ultimately, all powered by the AI side of this thing.

The challenge, as I was talking about, as I look at it, this is arguably, I would say that every company has this problem, which is AI is sort of ramping, its across the organization. They've all created a mandate. They've said, listen, you shall go forth and use AI in the organization because we want to drive cost down to it. But the reality is, is that it's sort of the value of AI is really locked up in those organizations because it's sort of opportunistic, enthusiast, sort of the tech guys that sort of get it -- they go out there. She grabs it, puts it on there and goes, "Hey, this is the agent that we're going to do." But it's in a small silo that can't have enough of an impact on the organization.

So we took a look at the problem and said, "Hey, we have to rethink the model and order the way that the model of which we sort of adapt and sort of use that AI in order to be able to accomplish more with it." We can't just go out there and say the mandate, we have to actually set the expectation to it.

So along with all of the innovation that we had, we created an operating model, that goes out and helps the organization sort of digest how they should think about AI. And in our operating model, we look at it from a standpoint of all the way from David Steinberg down to the the lowest individual within the organization, we're going to set expectations at every role of how much AI they should be using as part of what they do for a living.

Also, we started to set it up. We know we do a -- we have a sort of a dual layer sort of model. One is that we govern it centrally so that we can have compliance and standards and figure out the right tooling, Think about how we're sort of going to approach all of the innovation that goes in, but we create local champions that are within every group within the regions that are out there so that they understand from the central governance gets past the local champions. They understand exactly how their SOPs work.

They understand exactly how their processes work and all of those things, so that they can go apply it to the things that they do every single day. And they have expectations set at that level. They have a metric set at that level. So that there's no doubt on what they have to do with those things.

We've created training AI immersion, we've set policies, and said "Listen, we're going to do everything, AI first." There's no sort of default. The natural default is everyone because of sort of adapting or adopting new technologies. You go back to sort of those human-centric ways of saying, "Well, that is the way we've done it." I can guarantee every time that if I do these 12 steps, we're going to move through and I get this sort of outcome to it. But the reality is we can do the same thing within AI, we just have to force that change in what is that sort of natural behavior that they have to it.

And then we also look at things like cultural integration. How do we make it sort of part of the core of Zeta? How has it become part of everything that anyone thinks about, anyone that joins the company, they're going to think that I'm joining an AI company. I'm going in that the work I do is about orchestrating agents. It's not necessarily about performing it myself every time that's in there. So getting it in there creating cultural integration, we do this through not only just through the training, but also as we look at thinking about leaderboards, we're thinking about their everyday life that they going through.

When I have to write a review about myself, am I using an agent to write my review, my self assessment every year or am I going out there and spending the five hours in order to accomplish those things. So every part of everyone's life, we're trying to integrate sort of the agents as we look at it. We have -- even when I talk about the roles, like here's the expectations that we set out for every role. So you'll have, you'll be an orchestrator sort of an AI-led role that's out there. Every role we'll have a classification.

It will be enhanced, that's in there, so it sort of augmented, you'll be in that sort of range where 30% to 50% of your sort of role should be accomplished by the agent, by the AI, by all of the aspects or you're aware, and these are probably more roles that have a higher level of, I don't know, sort of ethical judgment, things like that, so places in HR, things in legal, that you would have to go out. Not everything can get sort of moved into sort of the world of the agent, but everyone will know what their expectation, even as we've started to roll this out in our pilot programs as we go through.

We've seen -- we were predicting sort of 50% sort of productivity against sort of the things that they accomplish every day. What we're seeing is there's a phenomenal amount of return against those, versus the investment of the tooling and technology against even the labor in order to sort of go implement it, that goes out, we're seeing 10x sort of return on that investment that goes into the AI side. And I actually think that, that's just the start as we look at it. If we look at areas where we think about sort of the use cases where we've applied it, if we think about -- one of the biggest challenges for our customers is -- I have to migrate or our potential customers, I have to migrate from something that does e-mail or data or whatever it is today, over to a new platform. That's the biggest barrier that goes into it.

What we've done now is create the agents in order to help them sort of make that swap over. So every tooling set, we have a sort of a scripting language, everyone like even the Salesforce does. All of these people have those things. But now we have agents that can look at the actual code, the things that they've built within there and recreate them within sort of the Zeta platform. So we removed the friction of people moving over. So we're seeing faster on-boarding as we look at it, even as we think about our sales side of this house, their ability to go out and understand like the individuals that they're getting ready to speak to the customers that they're going to go talk to, they have agents in order to help them prepare for those meetings, that are out there.

And then on the product innovation side, where Chris and Neej will talk about, our ability to produce product faster to code, to make enhancements to the platform have been greatly increased over the fact that we have this sort of a deployable set of agents that go into our larger sort of workforce that's out there. And truthfully, it's not only just about Zeta, as Steve said, sort of Zeta on Zeta is arguably my life in this thing. But the reality is, even as we look at sort of rolling this out to our customers, we're giving them the ability in order to adopt these technologies.

So we provide them sort of foundational agents, which are focused in the areas where all customers use the platform most. We're giving them agents that they can go out there and use those things much quicker and reduce the amount of time that they're spending in sort of the mundane task and thinking more about sort of the strategic aspects of it, then, we sort of graduate them through the more strategic aspects of it when we think about like forecasting all the way out into the ability of our customers to leverage the platform to build agents that are more specific and meaningful to their organization.

It's sort of the -- as we look at it, it's build the trust, understand the technology, understand that the value it brings and the things that it unlocks for you, unlock value and then ultimately start to think about how you sort of transform the organization overall. The other thing I mean, I think this is probably sort of a hot topic within the organization. We're in the process of sort of evolving the pricing strategy. I mean, I think it's always a question and probably an obviously, in your space, you'll think about how our organization is going to monetize sort of the AI aspects of it?

So we're in the process now of saying, listen, it's not only a question about monetizing AI, but it's also a question is, if the AI creates better adoption of the platform, if the AI unlocks more value, how do we remove the friction of the things that are actually happening within that organization as they go to adapt new aspects of it, think about bringing new agents on, get into new parts of the platform.

How do we sort of remove the friction, monetize everything and then ultimately sort of a sign of value for the base cost that we have within there. So probably, I'd argue within -- maybe after the first of the year, we'll be launching sort of a new pricing strategy that goes out and looks at all of those things. How do we create a place where if you could remove all of the friction related just of the procurement side alone, the marketer could go out there and go, "Hey, I've had a new idea on the strategy of what I want to do. Let me just go do it because I know the contracts are already in place and the pricing is already in place for these things. And I can take the next step and actually go do something that's going to have a meaningful outcome to the organization that's in there."

And I think that even as people have looked at sort of pricing strategies, a lot of them have sort of attempted to unlock these things, but the reality is, is they still create the silos that will exist within pricing. People price on entitlements and all the other aspects of it. The other side, even as we think about it within the AI side, within the pricing side, within the unlock for the customers, at the end of the day, for us, this is what we're chasing.

What we know is, is that if you come in and you buy technology from us or you come in and you leverage sort of strategy aspects of it, the further that we can expand you out within the organization, obviously, the greater value of the customer is to it. Obviously, the stickier it becomes, as we look at it, someone is in from more of the strategic marketing aspects of it. We try to get them the platform. Platform we try to get the strategic marketing aspects of it. What we know is, is that with these agents with AI, we can create a faster road map to their adoption of more of the platform.

We can have more clients that are considered sort of OneZeta who think of us more broadly in the application of their organization versus having us sort of contained into, "Hey, that's just an e-mail provider for me."That's just sort of a data provider that's out there.

So we use those agents not only to help them progress but also to help them sort of move through our value chain, our sort of way that we look at sort of the organizations to it. We're even using it in the integration of the new organization. It's interesting to go in and be able to talk to Marigold and be able to say, "Hey, listen, this is how we've applied sort of AI in our world, but oh, by the way, this is how we're going to apply it in order to look at ways to optimize your organization." Everything from the things that we've talked about to what capacity can we create within the base that we're sort of bringing on and the number of employees out there. How do we allow them to innovate or integrate or migrate better to our platforms that are on the side?

How do we start to bring all of these things together. And because we built the tooling that we've used within our own organization, it becomes the application to their side and allows us to unlock sort of the value and the opportunity within their organization much faster than what it would have been if we went through the channels before of just sort of the -- have multiple meetings and go through and go through all of the process that you would have as you think of it actually happens within those organizations.

So it's been -- as we look at it, it's really an opportunity for us. I like to think maybe it's -- maybe it's because I work here, one of those things. But I look at it in a very simple way. Zeta is an AI-native enterprise. Like we're not going out there and sort of allowing sort of the organization that are just creating sexy tech and all of the aspects of it. We're actually thinking about the application of it within every aspect of it, be it within the legal side, the HR side, the technical operations side, the product and innovation side, we're asking ourselves like can we be AI first in every one of those things? Can we actually control -- as we look at the aspects of the organization through this notion that we are as much as an AI organization has anyone else within there.

And so we've spent a lot of time. We think it's a default engine for speed as we call it, in order to achieve all of the things that we want to achieve. And ultimately, what we do know is, because we spent not only the time to build the technology, but the time to apply the technology that's in there, what we know is, for sure, we're the best partner for the organizations that we engage with to not only help them say, "Hey, by the way, here's a great agent you can use, but now we're going to show you how to apply it to your organization so that you can be successful in those things."

So it's a two part. As I look at it, I like to consider myself sort of the stake to Chris and Neej's sizzle that's out there, but we'll bring Neej up now to sort of talk about those aspects of it, and I appreciate it.

Good morning, ladies and gentlemen. My name is Neej Gore. I've met many of you. And with Zeta Live upon us, this is a revolutionary week for Zeta, our customers, our prospects and even our investors, as we talk about our strategy and showcase new products. But there's something bigger happening in the ecosystem. This is a revolutionary era for all marketing technology companies. And if you look back to the 1900s when we had catalog and direct mail, and forward to the era of loyalty and demographics and forward again to data-driven marketing to now to the Answers era, the company that controlled the unique data set around identity was set up to succeed. This has been a consistent theme across all the marketing eras that we've seen.

Now at Zeta, this is some recent benchmark testing we've delivered. Our data is delivering the moat that's helping our customers win and helping us win. In the last three months, we've run testing. We've seen using our data, customers see a 30% to 40% increase in prospects, a 30% to 50% reduction in CPAs, a 10% to 20% increase in conversion rate and a 10% to 20% increase in lifetime value.

So the Zeta data model is the one that moves from category -- from commodity to category leadership. This is very important in the era that we're in today. The data is providing a moat around the entire business. Why is the data providing moat around the entire business. The first thing is that the data provides context when you're engaging with customers. Our data gives our enterprises a view of a customer that exists outside of their four walls. They can be more strategic in the way that they actually communicate with those customers.

Our data also provides confidence around ground truth outcomes, less hallucinations. We've seen it before. We know it to avoid, and our data also creates a compounding flywheel where signals are accelerating engagement that then accelerates signals back into our graph. And so from every experiment in AI, and Steve talked about how many POCs fail, we are turning that into an advantage for all of our customers.

Back in December, I talked about why and how I consider a data asset to be valuable. First and foremost, size, scale and durability. Is the data asset comprehensive? Does it last over time? Second, act to compliance, do you meet the needs of the future laws and the current laws? Are you meeting compliance guidelines? And third and perhaps the most important here, do you have a seamless AI activation model? Are you creating an unfair advantage for your customers? We're going to come back to this.

The Zeta Data Cloud sees about 245 million U.S. adults every single month, on top of which, we stitch in about 1 trillion signals across data at rest and data in motion to create AI-powered intense scores around interest, around intent, around what someone is trying to do next. This is comparable to the Walled Gardens. And with the addition of LiveIntent, it's only made our graph stronger. And that SuperGraph that exists today is really like no other in the ecosystem, around identities, around signals, around identifiers and into intent, we source data, and we cultivate it into a very, very durable format. Returning to what makes a graph durable and predictable and profitable, 245 million identities in the U.S. about 90% of the U.S. adults covered, and that graph has grown over the last four years through all the regulation that we've seen.

Seamless activation model. We have over 2,500 NLP powered and LLM powered audiences built into the platform for our enterprises to take advantage of. And number three, we are ahead of the curve on compliance. But it's not just about being durable and predictable and profitable for Zeta. These are the exact same capabilities that drive the who, the what, the when, the where and the why for our customers. We want to make sure that they are durable and predictable and profitable as well. This is very important. So the combination of our SuperGraph, meeting our AI is really what unlocks the power of acquire, grow and retain and gives us a one-of-one advantage in the market.

Now there's something very important about this slide, that I want you to take note of. The shift that's happening in marketing today is moving from data-driven to Answers driven. Answers is what marketers seek today and with Zeta, the age of Answers has arrived. Zeta Answers touch every part of our platform. The answer questions about strategy, about discovery, about experience delivery, about verticals like Steve talked about this morning to what's next.

They're built into all the applications we run and when interacting with our AI, they create incredibly powerful outcomes. I'm going to take you through some of these that we're going to showcase at Zeta Live and with some videos as well here. So the first one I'm going to talk about is answers that craft strategy. We are releasing the Executive Intelligence Hub. Imagine if you had one single app that looked across all Zeta data to give you your opportunities as a CMO around acquire, grow and retain all in one place, refresh daily and keeping you up to speed.

This takes days and hours out of the work that a CMO and their marketing team need to actually operationalize from strategic to tactical. Answer, is what drive commerce. We are launching our Commerce Cloud. Retail is obviously a very important category for Zeta. Our Commerce Cloud in partnership with Fiserv sees brand affinity, sees brand transactions across 90 million Americans and about 250 million to 300 million transactions every month.

We also see product purchases over 800,000 product purchase categories. With this, we're able to create retail diagnostics. We're able to create real-time analytics. We're able to create 2,500 brand panels to measure longitudinally across whether marketing is working, and you can answer some of the questions like you see here on the right. What's driving my brand's performance? Show me my average sale price versus my competitors, did my target audience spend and how much did they spend? Spend is a very important part of our commerce strategy.

A lot of times in retail, marketers don't even know what the first question to ask, should be. So we have actually used a new agentic capability in retail diagnostics to give marketers a view of their scorecard as it relates to themselves and their competitive set. Retail diagnostics, again, is built directly into the platform. It taps into that partnership that we have with Fiserv and it really promotes our identity graph to give a view of the consumer and a view of the buyer like the marketer has never seen before. With retail diagnostics, you can also interrogate the data, you can ask questions of the data. So you can enter the conversational world and then proceed and ask questions that might not be available in the UI.

Measurement. Measurement is one of Zeta's superpower. Answers that measure everything, everywhere, all at once. The measurement model needs to cross over owned and paid. The world today is not built for the measurement models of last year. Consumers are fluid, they're operating across owned and paid channels. You want to be able to demonstrate that natively in one place, and the big key here is we can also measure across the social black boxes. This has been a thorn in the marketer side forever. So being able to combine social, owned and paid all into one view and give them the ability to see what's working and how to increment is very, very important.

CPG. We've recently expanded our CPG catalog. We have coverage from 100% of major retailers. We're seeing over 800,000 products in the CPG catalog. And really, you can also tap into intelligent summaries now, you can see summarized views of what the intelligence is saying. And you also have the ability to, again, converse with the data. If you're a marketer and you have a question, you can drop into our assistant here and actually take note and ask a question of the data that you're seeing. So you have a consultant that's ready to work with you at any point of the day, 7-days a week.

Answers that shape social influence. Tell me who you hang out with, and I'll tell you who you will become. This is the famous line. The way to target you is not just you, it's your circle. It's your colleagues, your friends, your family. Circles of influence actually answers around who you actually spend time with that create influence in your life. We've made this available to marketers directly in the platform as well. It's an entirely new way to think about targeting strategy. Answers around generative engine optimization. We've gotten so many questions this year about the future of search. What's happening?

About 60% of search traffic never actually clicked out before LLMs, 60% of search traffic doesn't click out after LLMs. So that hasn't really changed, but the dynamic of people that do click out demonstrate much higher intent purchase. How can we help our brands have the best visibility within LLM context and then decide how to improve their visibility using Zeta Data. Zeta Data can inform the questions and the questions inform the GEO strategy that helps brands actually show up more and be more discoverable directly in LLM context.

Answers to provide foresight. Last year, we released leading indicators. This is for a Fortune 100 tech company. Leading indicators essentially is like a time machine. It detects nuanced signals over time that increase in propensity leading to a conversion. So it's like a dynamic audience that gets built by the AI. This brand experienced a 97% increase in audience size 4.3x increase in CBR conversion rate and 4.2x increase in lower CPAs for their campaign. Now this year, we're actually expanding the time machine, and we're introducing Journey Pathing. Wouldn't it be great to know what parts of your marketing are actually driving incrementality, is an exposed population on a specific channel actually helping your marketing performance.

Marketers can now showcase this through Journey Pathing directly in the platform and see exactly what's causing people to come to stores, what's causing people to buy online and what tactics are working the best, again, driven by Zeta AI. Answers that accelerate vertical dominance. In this new world, AI is the new UI. We are actually creating an entirely new interface around opportunity explorer, which many of you have seen in the demo, if you've attended one of our investor demos, and it really consolidates down the information and makes it more bespoke for brands across acquire, grow and retain. Easier to interact with, easier to pull insights out of and leverages AI directly that's built in the platform. Again, it consolidates the view across customers, prospects, competitors and the market now in a much easier interface.

Steve alluded to our collaboration with Snowflake. We are expanding the capabilities of the Zeta Media Engine. This allows our retailers to not just collaborate with us through our platform, but also collaborate with their partners that may not be Zeta customers. They can actually use the ZME to combine the data in a privacy safe way and they can use that combined data to drive analytics. They can use that combined data to drive activation, to drive measurement, and we are powering this for retail categories. You can't be Zeta Global without being global. So we are very excited to launch the GEO Explorer.

This gives a view of the first global ecosystems that we are building our capabilities for, and we have a lot of data across the world. We're starting to synthesize it into strategy. The U.K. is one of the first markets we're going to go after than Western Europe and then Latin America thereafter, and you're going to be able to see what Zeta's assets are in those markets and as we recreate the model that has worked so well in the U.S. in other markets.

Now Answers at the beginning of this marketing revolution that I spoke of. And an example of that is audiences. For the longest time, when you select an audience in a DSP or in a system like LiveRamp, you just basically have to choose the audience segment and you market to it. Wouldn't it be great to know which members of that audience have a positive sentiment versus a negative sentiment. Now with Zeta's capabilities, you can highlight and isolate people for specific kinds of use cases around sentiment. Who likes your brand, who might churn. It's the next generation revolution of the audience capability that exists in the platform. And it's one example how answers are actually pushing this marketing revolution much further. But I'm going to close on one more point.

With this revolution, the goal is not just to provide tools that shape Answers. The goal is to move this into a platform that delivers wisdom. So moving from this concept of answers underpinned by Zeta SuperGraph; Two, the concept of wisdom underpinned by the Zeta marketing platform and underpinned by a topic that's very near and dear to my heart and Chris's heart, which is Athena. So I'm so excited to welcome Chris Monberg, my partner for a long time to the stage, who's going to give us a preview of Athena and tell us more about the road map for Zeta Marketing Platform. Thanks, Chris.

Neej is a smooth operator. And my goodness, this screen is beautiful. Nate, you got to get a picture, so I can show my kids. So I'm going to walk you through a little bit of where we've been today. The effort that we put into our AI foundation wasn't an accident. I've been writing about it and working on it for a long time. After that, we'll talk about where we are today with impossible products, and as Steve mentioned these earlier, the way marketers work with our platform is fundamentally different. It's something we couldn't have imagined 10 years ago. It's something that's very real today. And last, we'll talk about where we are going. I'm going to introduce to something that we call Gen UI which I think is probably the most exciting thing to happen to software since it moved to the cloud.

So every line of code we write, every idea, every integration. It's not just a tool we're building. They are new standards and we really drive ourselves to it and hold ourselves to it. In fact, 8 years ago, when I joined Zeta, we wrote out our ethos, how we want to build software and where we think it's going. And it has underpinned every single feature we have built during that time.

Let's talk about how we built this foundation. So Neej said, wisdom is the destination of every revolution. Revolution start with frustration. They start with limitations. They start with being held back. And enterprise software has been a big part of that. It just -- it makes us conform to it. And you guys all use software in your day-to-day lives and you kind of have to learn the software and wish it worked differently. And that's a great paradox is that marketing clouds are supposed to fix that. They're supposed to make it easier to do things, but they're too slow. Too dumb. I don't know if I can say that, but marketing clouds are kind of dumb. And they don't help you to your job any better.

Zeta uniquely has built this wisdom up, and I want to take you through this path of how we built this wisdom. This wisdom it wasn't born out of obedience. We weren't trying to be like everybody else. It was built and broken and built again in the forge of what Zeta is and what I've been doing in my career since 2013. So as we say, we don't need another tool. We need standards for answers in action. And Neej and I have been at Zeta since 2017. If you fast forward to 2019, we shared, it was the end of 2019. We shared a long-term vision. I'm going to play this for you because I think it will come full circle in a second. This is an exert from our town hall where I fumbled with a demo, I built probably over a couple of bottles of wine over the course of a few weeks. And -- this is just a...

[Presentation]

So you can see me talking to my phone there. We knew something. We knew that marketing was going to be conversational. We knew that Answers, Intelligence and Answers and action was going to come together, had to. We also knew it required a different foundation. Fast forward to a big day for us and for many of you, we IPO-ed in 2021. And we had so much conviction that we hung our literal banner of data plus AI equals intent. This was still a little bit early. It was 18 months later that ChatGPT came out. And all of our competitors, many of my friends in Silicon Valley, they're standing around and saying, "Oh, crap, what do we do?" We've building the old way. Now we have to conform to something new, and we don't know how to do it. Not Zeta.

Our wisdom had brought us to where we were, we had anticipated this and fortune favors the prepared. So in 2025, we're focused on AI impact, and you've heard a lot about this today. Steve talked about the replacement cycle. We need to onboard our customers faster. This is a big deal. People are worried about migrating off these behemoths of old marketing technology. We'll show you examples of that. Transformative operations through AI is what everybody is talking about, how that's culturally apparent is a hard thing to figure out. You actually have to get deep into what Matt was talking about, so that you can get margin expansion, which is a key goal of every CFO that you guys talked to.

Next, you'll hear me and others talk about developer experience. And that's a term that people talk about when they're talking about AI, changing the way engineers work. I'm very proud of the work that [indiscernible] and Patrick and others have done on the team. We've become a bit of the model ground in Silicon Valley. If you want to learn how to use AI to change the way you work, you come talk to us. If you're a vendor that's creating AI tools to help engineers work faster, you partner with us. And last and most importantly, we talk about customer outcomes through AI-powered marketing. These aligned to -- we call them our GTM objectives, but they're not really go to market. These are align of things that happen at Zeta. We've got a align, amplify, ascent and Neej talked about Athena.

Athena is a super intelligent agent. It's an expansion of our Zoe vision, the one that you saw me share from the end of 2019, beginning of 2020. It's going to broader purview on what you can do in marketing. It's personalized and it helps with personal and team productivity. So I want to dive in a little bit into what Athena's foundation is.

Neej spoke about the SuperGraph. And in every revolution, there are visionaries, but there's also architects. And we've been building the SuperGraph and breaking it down and building again in the forge of Zeta for many, many years. It's not simple. We've got the experts. What we have today is truly special. It brings answers, identity and data together. Next, I want to talk about AI infrastructure. Now this is the deterministic foundation, which complements the highly probabilistic world of AI perfectly.

People ask questions. Infact I've had the question from a few of you on calls before, like, "Oh, couldn't somebody just go build this with AI and some vibe-coding"? And the answer is no, because this deterministic foundation, again, was built in our forge. It takes a lot of understanding of how to build technology that comes back to an individual and route that through LLM, MCPs so that the application can work. And third, contextual intelligence. This is the crown jewel in a lot of ways. This is what creates memory. This is what creates personalization, this is what make sure that we don't have generic agents. Instead, we've got an extension of the humans that are using it.

So foundations don't create a revolution. But what you do with a foundation, what you build on top of that foundation can. And I'm very excited, although I'm an engineer, so I never look excited. Very excited to share something with you right now. This will be the first glimpse of Athena that anybody has seen. Tomorrow morning, David Steinberg will unveil it, and the world will know about Athena. We'll have Roman demoing it live if you want to see it. I have got a recording from Roman, it's a little bit quiet because it's baby who sleeps, he's got a brand-new baby. But it takes about 3 minutes. I hope that you enjoy it as much as I do. For me as a technologist anticipating this being in the forge and building towards the future, I believe that we're finally there.

[Presentation]

I was hoping for a clap or something, right? Thank you. And obviously, thanks to -- I've got quite a few more slides. And thanks to the team that worked on this, this adaptive fabric that we've built, the core of our foundation is what makes this possible. And it really is magic for the marketers that see it. We've had a couple of beta customers come in and look at it. Their eyes get big, and they start to understand how they can drive more cross-channel marketing in a more effective and intelligent way. This unlocks OneZeta in a way that we never had before.

So next, I'm going to go through impossible products. These are the products inside of Athena powered by Athena and that foundation. I'll go through them pretty quickly. But the way I've set it up is we went through the data life of the marketer, maybe it's a week or a month in life of the marketer. It starts with data, it goes into planning, forecasting, creative and measurement. And we asked ourselves, how would they work if they weren't conforming to technology? How would they work if the system was more intelligent?

And on the right side, you'll see how we're setting the new standard. We'll talk about moving from the legacy to the new way. So starting with the data foundation, fragmented to foundational. Every marketer you talk to, and you may not talk to that many on a given day, I do. Their data is fragmented. It doesn't all have to be consolidated in one place, but it needs to be accessible for these federated services. I want to walk you through the story or I want to talk you through a retail CTO that needed faster on-boarding. This is a real skip. And they wanted 50% faster on-boarding. We delivered far in excess of that. Some of our agents were 5x faster. Overall, we're closer to 80% faster than what he was expecting for a timeline.

So this is the new data standard, and it starts with connected data. Every company does. We do that for them. We have agents that help do that. We've got connectors that do it. Then it goes to a workflow. This is a line and it has job cards, each job card has an assistant. This assistant takes a screenshot from Salesforce Marketing Cloud. Just a screenshot. It quickly analyzes it. It converts it to Zeta and our taxonomy of thousands and thousands of audiences and attributes, and then it builds it for them. What's important here is that it puts the human in the center. We start with humans, we have AI, automate and then we end with a human, and it enriches with data cloud. Next, I want to move from data to planning. We work with a lot of planners and strategists that want to look bright. Sometimes they want to have a excel sheets, sometimes they want to move directly to activation.

In the old days, they had a hypothesis. It was built with a lot of good intention, but what they needed were data-driven answers. We work at a travel brand. They've got a strategist, and that strategist is majorly overwhelmed. They have to do a lot of media plans on any given week or any given day. Their goal was, they just needed to work faster across our portfolio of products and they couldn't keep doing it in excel anymore. So this is introducing. We're a little bit behind on this. Here we go. The new decision standard. AI Studio has the ability to build your own model, your own workflows, your own agents.

Here is a media workflow that very quickly takes some instructions to put together a budget and a plan, and you'll see this in the demo tomorrow, it creates the steps for you along the way.

It has context of what your goal is, has context of the brand. And for each piece of their journey, this workflow that's automated, they're able to generate a media plan. This is something that would typically take weeks for a strategist to do. If they're trying to cheat it, maybe they've got a template they use, and they do it in days. Now we can do it in moments. This is real ROI.

Moving from planning to forecasting. Once you have a plan, you need confidence it's going to work. And that confidence was rooted in strategy, the big capital S word, a lot of people use, but it didn't have the data it needed. We've built simulator which I'll show you in a minute, that helps people understand what's going to happen before a dollar has been spent. We have an e-mail CMO that was working in one channel, and they said, "Well, I want to use other channels. I just don't know what's going to happen. We don't have any experience with it. We don't have any data.

Zeta was able to help them do that driving channel adoption. This is the new proof standard. So starting with the goal, which are aligned to the business, you can go through and change your methodology, add new data inputs like linear TV, which data doesn't run. This is part of the forecasting model and you get the outcomes. Once you activate that, it can be pushed into the next step or you can look to create campaigns, export or generate a proposal deck again, creating transparency around AI is a big goal of ours. And so you have to have things like the auction funnel and the bidding effectiveness and even understand audience insights and overlaps, if you're going to build that trust with your customers.

Next, moving from forecasting to creative. You need campaign managers. They're going to build these plans out once they have confidence. Every single company we work with is understaffed on their campaign team. Those poor people, oftentimes are 24 years old and -- they are working 16 hours a day, day after day after day, making changes to campaigns. We want to help them with efficiency there. So this is the new creative standard.

We've talked a bit about the workflow tool. Very similar. I want to do a win-back campaign for Black Friday. It will go through and build the steps for you, but it will also go through and help you understand what the campaign should look like. Inside of our campaign builder, you can interact with it. It's hooked up to your digital asset manager, your CMS or even [ Sigma ], which we're hearing more and more about hot tip there, and it brings in brand certified content. This just saves time. It's got an e-mail today. And with a click of a button, you can extend that one creative to other channels. Again, all of this is in an editor and human in the loop is so important. This drives cross-channel adoption.

And for Zeta, that drives revenue. The final step in this is measurement. And we talk about moving from static to adaptive. Measurement is not the destination. It should be a feedback loop, but the whole industry feels like it's the report card they get at the end of the semester. We have a retail CFO that was on the phone with the CMO, reached out and said, we need help hitting our numbers. What can you guys do now to boost revenue in quarter, and we had an answer for it. This is the optimization standard, and it's the way all measurement should work.

This is Performance Adviser, it gives you recommendations that are aligned to your business goals. And this is AI working in the background constantly looking for new recommendations based off the tactics you have. It gives you methodology. It tells you why it's creating the recommendation, and it tells you what it should do in the future. You simply apply it and then you can see the impact of it as soon as it is live. These selected recommendations stack up which becomes a very hard problem to solve that humans can't do on their own. They need sophisticated eye to drive it.

So tomorrow, for those of you that are able to make Zeta Live, we will be introducing more impossible products. And I am incredibly proud of the work the team has done. Please introduce yourselves. There will be a floor full of bright people from my team and Neej's team to be more than happy to take you through questions, answers, how people are using it. Yes. So introduce yourself.

Last chapter is new horizons, Gen UI, as I said, and we like to think about this as software-on-demand. So for over 20 years, we've been conforming to technology. This next era really flips it on its head, and this is the paradox should an individual adapt to software or should software adapt to the individual. And it's not meant to be rhetorical. It's meant to actually reflect where most of us are sitting and working today, the way we write our notes, the way we reclaim knowledge from the notes that we create. So in the old days, make it akin to people had screw drivers and hammers. They had the tools in front of them and they conformed to work in that way.

As we look forward, I think it's more like Tony Stark and his Iron Man lab, and you have AI building AI. You have AI building software. You have AI building products, and it becomes a real extension of you. And well, it's [ grandiose ] and a great picture. I don't think we're far from it. I'm going to take you through a very recent use case. This is a global travel and hospitality brand, although we started with hospitality with them. They gave us an RFP and it almost read. I can still remember the first paragraph. It almost read, we're a global hospitality brand. We want to be able to track our properties across the globe, and we want to be able to market to lagging properties. It sounds pretty simple. And they kind of have a white-labeled software that hotels use around the world.

So great. We can solve that. In fact, [ Old ] Marketing Clouds can solve that, too. Here's the way it would typically go. You build reports manually, you'd monitor them manually, like with eyes on reports. You'd have to go select audiences that you think are in Geneva or wherever the hotel is and you develop creatives manually, you can figure channel tactics and build more reports and monitor those manually. That's the way software has been. But we have this adaptive fabric. You saw evidence of it in the video earlier. We got all this infrastructure and all this context of those goals, it knows how to link it up to technology. When you bring those together, you do get to the world of UI on demand. This is Generative UI. Let's look at an example of it driven by Athena.

So this is the prompt, going and create an app and right out the RFP, you can copy and paste in there, maybe a little color about what you want, like a heat map to go over the map. On the right, you'll see it mapping capabilities to the platform. On the left, it's churning away. An AI Shield down to the bottom is scanning code. It's making sure it's ready for deployment, and you get an app that's built just for you.

This is actually what they wanted. They wanted a heat map that shows how occupancy rates are going. They want to be able to scan these things. And then they want to create a campaign to market those people, select their strategies that were recommended by Athena, select their audiences that recommended by Athena and select their channels that were recommended by Athena. They want to run those campaigns, and they want to see performance go up into the right. They want to see their occupancy rates solved for. This is a new era in all enterprise software. And all us are going to experience this in the next 10 years.

Zeta is a pioneer because of the work that we've done in our forge a building and breaking and building again. But one app is not a revolution. I think an ecosystem of apps, they're all connected, they're all share one brain that know what the other apps are doing this starts to get to that Tony Stark vision, where they can work together to build something much greater.

So I want to introduce Agentic Workspaces. This is the new interface standard. And -- we have a bunch of apps we call them agentic apps that are already in the platform, but people can build their own like you just saw. Say you want a retention app that's really focused on your job, your retention marketer, people we work with all the time. Let's create a unit interface that meets just your needs. Let's talk to it via Athena. If you want a logistics app or a warehousing apps, just talk to Athena and build one. Maybe you also want to look at your data guard rails or do an audit of that data and that retention app, we'll then build it, bring it into a workspace, look at them side by side.

Maybe you have other concerns as a business like, "Oh, we've got a calendar of other campaigns I don't know about, but people will put them in there. Look at them again side by side. This is like the Bloomberg terminal for marketing. Maybe we should call it the David Steinberg terminal for marketing. I'm sure he would like that. This creates intelligence across your entire business, both inside and outside of marketing in one view. So as I've talked about, One AI platform with a solid foundation creates infinite possibilities. In this line, when software adapts to people, imagination becomes a limit is something I deeply believe in, all powered by Athena.

So in closing, a good friend, Neej said that AI revolution is here, and I agree with him. While every revolution does start with frustration, it starts with a paradox. It ends with pretty infinite possibility. Our hard earned wisdom, the time we put into this going back from me to 2013, it hasn't shifted much, it's been built in that forge. It brought us Athena, which is such an exciting moment for all of us. But tomorrow, with our customers, we will imagine the impossible. So next, you get a break. I appreciate everybody's time today. Thank you very much. I think it's a short break. There's coffee in the back and probably the music will go on or the lights will dim when it's time to come back. Thank you.

[Break]

Excellent. Well, welcome back, everyone. Thanks for taking the time with us today, and thank you for your attention on everything that's been going on. It's a hard act to follow that Athena demo and really to spend some time talking about it. I think we're supposed to be having the intra pages up. Okay. Well, I'd like to introduce my panel, Marc Brodherson from McKinsey. Courtney from Publicis Sapient, Sudarshan from Bounteous.

So the topic today is really on how marketing and advertising are converging. One of the things when we look out there, CMOs are really stuck saying, what is it I'm supposed to do with the advances in AI? And we have been talking to the CMOs and saying, what is it you really need? What do you really want? And it comes down to a couple of simple things.

First and foremost, the CMO has to be able to produce profitable customers. That is what the CFO is looking for, that's what their boards are looking for, and that's what the CEO is looking for. With that, the CMO is having to look at a different way of managing their business. Historically, we've had divisions between advertising and marketing, which are really artifacts of how we bought media, how we've worked with agencies and how we are managing the touch point with our customers.

But today, that ability, the need for that is changed and the ability to bring it all together into managing a series of touch points has really made a difference. When we're talking today, one of the things I just want to get out with the group is, what are you seeing from CMOs? What are you seeing as their needs? What are you seeing shifting? And Marc, what are your thoughts on that?

Well, first, thank you for having me. Second, I just smile because we've talked about this for years, right? I always say, start with the consumer. I talk to my kids. They have no idea what the difference is. I say I work in marketing and advertising. Isn't that the same thing, right? And if you look consumer back, of course, they don't understand. The brand is talking to them, right? And at sort of a self-imposed distinction. That's created a lot of problems, both for consumer experience and for companies themselves.

But quickly, look, I think -- there's not a CMO I speak to who disagrees with this. They may not articulate it as simply as the convergence of marketing and advertising, but they're all feeling it. I think the smartest ones that we're talking to are viewing it as the solution of that convergence or the Holy Grail is a decision layer above it. And that's what can blur the difference, right? It's which customer am I speaking to? What am I trying to say to them and what's the economic impact that I think I'm going to have with what I'm saying to them? Right? And therefore, the channel I'm going through really doesn't matter.

Exactly. And I think one of those big things there is about managing across touch points. Courtney, Publicis Sapient, you have a great view across the industry. What are you seeing both from a Holdco perspective and a Sapient perspective?

Yes. I mean I can agree that we've been talking about this for years. I've worked on both the media side, the marketing side and the agency side. So I've seen all perspectives. And for a while, we've been talking to our clients about we need to bring together understanding how a consumer views your brand and not just here's media, here's marketing. Here's an e-mail -- here's maybe a website -- and what we're seeing is that CMOs more and more are talking about this.

And they're thinking about how do we bring these things together because what's happened in the past is everything was stood up in silos, right? Like media companies, they stood up their own little team here, their own little technology, their own little data. And then our e-mail platform at the same. And then our website did the same. So now how do we bring these all together. We have different processes. We have different orgs. We have different ways of working, and we have different platforms.

So CMOs are really looking to us at Publicis Sapient to say, all right, how do we reconfigure all of this that we put the customer at the center. And they're calling it all sorts of different things. Some CMOs are calling it E2E like end-to-end customer life cycle. Some CMOs are talking about it and like, "Oh, the full customer life cycle." And some of them here at Publicis Sapient, we call it [ Pesos ], which sounds terrible, but it means the same thing. So whatever you're hearing in the market, everyone has their own name for it. This convergence is very real.

Courtney, do you mind defining Pesos?

Yes. Yes. So sorry, it's paid, earned, social and owned. So it talks to the different silos of an organization where they do marketing or advertising, and made an acronym of it. So it's not like a Spanish Dish or something like that. Just in case you were wondering.

In marketing, we like to make up different acronyms.

We love acronyms.

Sudarshan, Bounteous has a very unique perspective as a digital transformation firm. What are your thoughts? And what are you seeing?

First of all, thank you, Ed, for inviting me to this panel, looking forward to this conversation. I absolutely echo Marc's and Courtney's comments on that. This convergence is very real. But I think we need to sort of frame it in the context of what's happening now with, with AI enabling multiple touch points across our clients' life cycle, whether you look at it from the perspective of -- from the perspective of third-party data or first-party data and the entire value chain of having our customer life cycle and journey mapping through that.

The marketer today needs to operate like an orchestrator of a growth operating system, where it goes beyond just driving brand value for your clients, but actually impacting profitable customer journeys for the firm. To give you an example with -- for example, one of our clients, Wawa. I think what we're trying to do with them is to move them -- move their end customers from just coming to the store for a morning coffee to actually making it a ritual where they come in for dinner.

And that means looking at it from multiple touch points. And it's not just about -- it's not just about where in the life cycle they are but about having unique insights using all the -- all the data that's available to drive that convergence between marketing, advertising and ensuring value for your clients in a way that is profitable for you. That's the difference, and that's happening now largely because of the availability of tools like AI, and that is something that is going to impact significantly how market does evolve over the next few years.

Sudarshan, you had a great point there, that evolution of marketing. We hear about the AI revolution. Do you think that this will actually increase the maturity of CMOs and being able to deliver profitable customers to their businesses?

I think it's it sort of has to happen. If it doesn't happen, if the CMOs who don't embrace it, are not going to be relevant anymore. In fact, when I talked to a lot of my clients, it's not just the CMO, it's about breaking silos in the organization across technology, across data, product, CFOs, all trying to drive towards the same profitable customers. And it's about moving from marketing viewed as just experience or brand or advertising to actually contributing to revenue growth per customer.

In fact, if I look at three or four years from now, I think the ones that will matter are journeys where you can individually customize and say this customer is somebody that I want to focus on because I can drive profitable growth through this customer. It's personalization at scale and the tools that we have today enable us to do that and marketers who don't embrace that won't be relevant anymore.

I think that's a daring item, an important item. I think you're hitting at the heart of CMO tenure. One of the big things here behind that is the idea of creating, I think what you're saying almost a customer supply chain that the CMO needs to be in charge of a customer supply chain and they have to act as a general manager to produce that customer profit. Marc, Mckinsey has really delved into that with a couple of white papers and other things out of the last few years. Your thoughts on that?

Well, first of all, I was going to jump in when you said Peso, the McKinsey term has become the customer supply chain, which shows we're not marketers, and that's across a lot of industries. But I do think it's very resonant and it's evocative for a lot of CMOs to say, "Oh, okay, and I'll get into the work, but that I should actually start operating more like a P&L owner and thinking myself like that, which gets to -- you can't think about profitable and growth in the same sentence, if you don't have some form of even a synthetic P&L.

But yes, I mean, as you know, we've done for the last three or four years, this research into what was first the CEO-CMO, dynamic and now the triangle, the CEO, the CFO, the CMO. And I would start with I said my kids don't understand the difference between marketing and advertising and say most CEOs and CFOs don't either. And like one of the first findings was just a pure communication gap. But you have a CEO who ultimately wants durable profitable growth.

If you really boil it down and apologies of CFOs out there, the CFO is thinking unit economics, which is really hard for marketing and advertising to translate its language to, and so CMOs are struggling to communicate back to them and also get what they need, which is you need to be able to move your money around fluidly, be able to prove incrementality, and drive closed-loop measurement to show that it actually worked and there's ROI, right?

So the couple of things I would say, the latest round, we did another 100 interviews or so I think it came down to three things for the CMO. The first was actually an org implication, which is what we call single custody of the customer. You look at C-suites for all publicly traded consumer companies. C-suites that have only one role that touches is responsible for the customer and the customer experience. On average, those companies are growing to 2.3x faster, I think, than companies that have sort of diffused responsibility at the C level.

The second is what you said, Ed, right, is thinking like yourself, a CMO as a General Manager. One of the big shifts has been there is what AI is going to enable us to do, I think, is this -- I predict a bold prediction other than like maybe live sports and news. The CPM will be gone in five years, and you'll talk about LTV and CAC everywhere, and that allows to think that way. So those are really like the two big fundamental shifts that we see happening.

I think there's a common theme that I'm hearing here really is the CMO's role is going to change. What they have to deliver is going to be discussed differently. CFOs, yet, they'll look at the advertising, but they really want to see the numbers first. The advertising is nice. When you take a look at this, that's going to change the demand that CMOs have for tools and capabilities. Courtney, your thoughts on that?

Yes. No, absolutely. I think you want to think about it in a couple of ways. Marketing now, there's two words I like to describe it. It's becoming unified and it's becoming precise. And you need the tools and enablement to do so. If you're breaking down those silos, not only do you need to get your data in a common place but you also then need to be able to activate it, and I think Marc talked about a decision layer of some sort, commonly, and you need to be there in the moment when the consumer wants it. It doesn't matter what channel, right? It just doesn't. You just need to reach them. And then you need to measure. You need to prove that growth.

And what we're seeing in today's market, and we did a lot of research on this at Publicis Sapient, is that there's a little bit of white space in that area, right? Like I said there were silos. We stood up a DSP over here. We stood up a CDP over here. We stood up a CRM over here. And there's very little organizations out there that can bridge that gap. Now I know we're at Zeta's Investor Day. So it sounds a little like -- but I do have proven research that Zeta is one of the few companies that operate in this space.

And we've talked to customers, and it's well recognized in the industry that because of the capabilities of Zeta between identity and data, CRM, e-mail, DSP activation and then the measurement, you can actually look at that full marketing pesos view with the platform, which makes it super attractive as CMOs are looking to bring their teams together and work within this space.

So Courtney, on that topic, what you're saying is a real major shift instead of just a dashboard saying, how did I do you're going to have a view that says, how am I doing and what do I do in the marketplace? Does that mean the CMO is going to change your role in buying technology? Are they going to be the actual decision maker as opposed to influencer?

I think so. I've seen it in organizations. It's about 50-50 right now, I want to say, and I see that pendulum swinging a bit. And because -- the reason why I see that pendulum swinging is because they are now responsible for that P&L like we just talked about, they're responsible for that revenue previously the role of the CMO was like [indiscernible] position, drive as many people as you can into the funnel. We don't really know what's working, who knows? But we'll worry about that later. But now with the precision I talked about, we can understand what is causing that revenue, which marketing touch point is which gives the CMO way more influence and what tools they want to buy to activate that.

And Sudarshan, given that you serve across the corporation, what's your thoughts?

I think, Marc referred to as customer supply chain. Yes. We call it growth operating system, and that is the CMO's role today has evolved or should evolve. And like I go back and saying, if it doesn't, they won't exist to becoming an orchestrator of that system across the firm.

Example, we -- one of our clients, what we're talking to them about is not just conversions, but how to triple the EBITDA in half the time. And this is with the CMO because that's really the conversation that they're driving, and I'm talking about a Fortune 100 firm, and all of this revolves around having your content experience, data analytics and underlying technology stack work together. The only way if that doesn't happen and if they can't orchestrate this across all of this and drive profitable growth, then they just won't be relevant anymore.

So from my CMOs that we talk to today, it's all about having -- delivering that business impact and not just about more conversions or driving more towards the digital channel. Yes, that's one of the things that we'll have to do as part of the toolkit. But how do you do it, has fundamentally changed. And again, that's where firms like Zeta come in and firms like Bounteous come in, where you need that underlying platform to be able to generate those activation insights. But then you also need consultants who bring in the strategy, the experience, transformation and an understanding of all the digital technologies that drive this transformation. And that's where Bounteous and Zeta are exploring some opportunities today.

Marc, when you are out there in the marketplace and looking at this marketing operating system, the customer supply chain, what do you see the conversations coming from the CMO -- do they see themselves as generating demand for these tools? Are they turning to their CIOs? Or where do they play in the space?

It's a great question. I would say, again, it depends. 50-50, although I would say the momentum is shifting. We've had probably like 3 or 4 engagements in over the last year, 1.5 years, which are -- CMOs bringing us in specifically to be the objective voice who says, paying for me a proper McKinsey style and was Board level narrative of why this needs to change. What fundamental shifts I need. And by the way, that is budget and that's tools, and I think that is always at the heart.

But a lot of it is word changes, data governance, all of the surrounding pieces that -- the tools are great, but they don't work unless the company is set up to actually take advantage of them and implement them, bringing in the merchandising group, bringing in, there's -- you can't do this, at the scale and the ambition we're talking about without some fundamental changes around technology. And I think that puts the CMO in a much better position actually than a CIO or CDO because they can talk in that holistic way about everything that needs to change and the total outcomes, whether that's measurement, profitability, that when you have just a CIO leading that, you talk a different terms.

You are talking to CIO? And I think as we get our CEOs and CFOs more knowledgeable about what we're talking about here in terms of not just top line, but actual enterprise value creation, that holistic perspective is really starting to take more and more of a front seat.

Excellent. So behind all of this, what I'm really hearing here is the CMO has -- CMO must change your role. Some are already on that journey. Others are recognizing it. It sounds like they also want a marketing platform and marketing operating system built by and for marketers to really be able to manage the production of a profitable client, a profitable customer. Do you think that demand is going to be durable? Courtney?

Yes. I mean, I do. It's almost like asking me like, do I think the Internet is durable in 1998? Like I absolutely think it's going to be durable. The most incredible thing that's happening right now is we are witnessing and watching a change in the industry, and it's happening before our eyes, and it's not going back. It's not going back to the way it was. AI agents, they're going to continue to evolve. The role of the CMO is going to continue to evolve. It's becoming more and more important that the CMO not only has the seat at the table, but has a very large voice at the table. And I'm going to tell you why.

The reason is as things become more agentic, people are going to crave more human connection. And the person that can give that both things to them is the CMO. It's not the CIO. It's not the CEO, it's the CMO. So I do think it's durable, and we're going to see the CMO taking a much larger seat at the table.

And so working off with that for a second, and I'll open this to the full group. What I'm hearing here is all revenue in this ecosystem, will be originating with the CMO flowing to their agency, their partners and everything else. So it really is a key role as we look at the financial dynamics here. Thoughts on that?

Just adding to what -- I mean, Courtney said -- this is relevant what you're saying. The reason it's durable is the economics. And it's not -- it's -- every time there's a shift, there's some going to the high [ territory ], some going to durable. The ones that go to durable territory are the ones that have positive economics. And AI is driving positive economics for the CMOs in driving profitable customers. And that's why it's durable.

I agree with that. I was going to say in my first year, McKinsey right, you do the sort of industry analysis, which is driven by customer shifts, technology shifts, regulatory shifts. I think you have all of those coming together right now, which as we really are at something that I think is going to be the new normal pretty quickly, right? Like we've talked about the CFO.

I mean the financial implications of this and the benefits are already becoming clear. AI models are just getting cheaper and more productive, which means you're going to start to see even a larger percent of decisions being made, model based decision. It's a metric I would -- I think you guys are starting to track, I think, I would keep an eye out on the street for that versus rules-based decisions, outcomes-based pricing, like this is enabling a lot of things on the finance side.

Obviously, you have the platforms and the privacy like the cookie thing is one thing. But just in general, we're moving more and more to Walled Gardens, other forms of privacy deprecation. And then lastly, I think we're talking today about how AI is transforming the current marketing system. Chris was up here talking about GEO. I mean there's also AI transforming the entire consumer journey itself and where they're going to encounter brands, how they're going to make purchases, et cetera, and that just opens up a whole new marketing challenge.

How the hell do I get my brand into a black box that is internally more complicated than the Google search algorithm ever was? And I think companies that have that durable identity and the closed-loop measurement capability and the multichannel distribution all in one, are the only ones we're going to be able to help solve that.

Excellent. I couldn't ask for better close. I want to thank my panel for joining us today and thank you.

I'm very excited today to have Adam Potashnick, the CEO of Brainlabs North America. And before I jump in and ask Adam, a little more about Brainlabs, I was going to ask a little more about Adam, I want to start broadly by saying that Brain Labs is an independent advertising agency. And independent agencies and large agencies are a very fast-growing segment of Zeta's.

Now as a guy who's been in advertising for 26 years. This makes perfect sense to me. Zeta offers a state-of-the-art data powered enterprise platform for marketers and agencies are enterprises, they to acquire, retain and grow customers, for their chief customer, a CMO. Advertising is a subset of marketing and [ ad visions] are part of a CMO's organization. So it makes perfect sense. And that brings me to dive a little deeper here with Adam on this topic. So Adam, you're the CEO of Brainlabs, North America. But prior to Brianlabs, why don't you tell everyone what you were doing?

Well, thank you so much for having me, Jed. It's a pleasure to be here. For 20-plus years, I worked within WPP, one of the world's largest holding companies in the advertising ecosystem. Inside of WPP, I worked inside of the media arm called Group M within one of their Opcos, which was Mediacom. I was their Chief Operating Officer. Prior to that, their Chief Revenue Officer. Chief Growth Officer, and I ran many of their largest global clients for close to 20-plus years.

And you did that all before you are 17 as well. Now why don't you tell everyone a little bit of Brainlabs. Please.

Sure. So as Jed mentioned, Brainlabs is a global independent media agency, the independent or in the space of media agency has grown quite significantly over the last 10 to 15 years. Brainlabs was born out of the being a digital-first media agency. We are -- we take a very scientific method to how we manage media dollars and campaigns. We have our own technology that we've built with our 80 plus engineers and our proprietary technology helps us do campaigns, smarter, faster with more agility, and we're seeing tremendous growth, not only around the world but here in the U.S.

And so is that your superpower the combination of your science and technology with your service offering?

Look our superpower is certainly our ability to test and learn and then scale, campaigns that are working most effectively as quickly as possible, but our superpower is not building massive enterprise-level AI platforms or technology. That's where we look to partner with the likes of Zeta, to be able to bring that to our clients and be able to deliver exceptional performance and results.

Segue into Zeta. So we've been partners now for about a year. And before partnering with Zeta, where there are other technology, data fuel platforms and companies that you thought of diving in deeper with besides data?

When I first arrived at Brainlab's about 2.5 years ago, there were certainly conversations that have started, but nothing came to fruition in regard to let's start a partnership. A formal partnership with an outside technology partner prior to our formal partnership we now have with Zeta.

And how does Zeta, I mean you've mentioned that you're a technology-driven company, you're a science-driven company. How does Zeta complement this?

So Zeta is built on its identity graph, it's technology, data and AI-powered tools and applications within the Zeta platform. We do not have that. So without Zeta, we cannot serve some of our clients or pitch new clients without this partnership. The partnership with Zeta makes us just as competitive, if not more competitive with many of the holding companies as well as many of the independent agencies out there in the marketplace.

So diving more into that, do you utilize data more for a differentiation with the Indies? Or can you now compete with some of these huge holdcos who have invested hundreds of millions, if not billions inside some data graph or something they try to put together. Is it more an Indie difference maker or allows you to play bigger?

The answer is both. There is no one in the marketplace we cannot compete with even after they've spent billions of dollars in acquiring large-scale data companies, there is no one we cannot compete with because we have Zeta in our corner and Zeta as a partner, we can compete with anyone in the marketplace.

And who are some of your bigger clients?

So some of our bigger clients are Capital One is our largest client here in the U.S., which is one of, if not the most data-driven marketers on the planet. We also serve as Walmart in Canada. Bells, which is a large-scale retailer. We also service certain parts of the Microsoft business, AT&T, LEGO, Pepsi and many others.

Yes, that is quite a list. And as you got to know Zeta and began the partnership about -- as we talked about, about 1 year ago, Zeta helped you with a new business pitch. That was one of your first intros into the power of the platform. Who was that with? And can you talk a little bit about that?

Sure. So in the initial conversations with Zeta, I wanted a superpower. I wanted a data technology in my corner that can help us compete with both the holding companies as well as the other independents. And so working seamlessly with the Zeta team allowed us to do that. They provided us with complete access. There was nothing that was sacred, and we couldn't access because of our partnership, they gave us access to all applications and all data sets within their platform.

It allowed for us to be fully transparent with all the brands that we were pitching to say we have a partnership with Zeta. And by having that partnership, we can bring you this audience intelligence as well as this activation of your media that could drive you better results, in each and every case of having those pitch meetings and conversations in which we were up against both large and small agencies we performed exceptionally well, and we went deeper and deeper into the Zeta platform and the CMOs and the marketers that we met with all were very pleased with what Zeta had to offer.

Got it. So that's a great example of the acquired part of how we help enterprises and an agency as an enterprise with how you plugged into Zeta. Integrated with Zeta's platform, so you could utilize the intelligence of our platform to help you play bigger and bring on new customers. Now from that, what about the retain and grow aspect of the drive of an enterprise? How are you utilizing Zeta right now to retain your existing customers and drive their business ahead?

So because at Brainlabs and like many other independent agencies, we are not going to invest our capital in the data sets that data has already built into their platform, and that they allow for us to access on a daily basis. We have our own logins, we log in, we provide to all of our clients, audience intelligence and deep insights that are required for us to be able to support them strategically, but also help identify new audiences to help them grow.

With certain clients that we have such -- in the retail space, it's very important for us to understand location-based data. The location-based data that we found within the Zeta platform is second to none. It's allowing for us to drive new footfall, new customers, new store traffic to many of our clients that have physical retail brick-and-mortar locations, and we're seeing massive success with your place, data your GEO-based data inside of your platform?

Yes, for the companies that still have many, many brick-and-mortar locations, that can be a real struggle when they just have no idea who walks into that location whether they've made a purchase or not, if they're not a loyalty customer, if they're not logging into your website. So that's something that Zeta has been able to help your retail customers with understanding. Did they see advertising? Do they walk into a certain locations. Did they take action and that then can feed the CRM and feed that marketing funnel as with Adam's referring to.

Now tell me now we've had the success with helping Brainlabs to win and be the best Brainlabs can be in pitches. And then we've had some success as well with driving the growth and the intelligence for our existing customers, what do you think is next for Zeta at Brainlabs. How do you see the partnership in the future?

Yes. So alongside Zeta, we have one of the deepest partnerships with Google as well as with Meta in the industry. Now well, Google and Meta bring to us and the partnership that we have, we find that data is the perfect complement to what we're already doing with both Google and Meta. So the differentiation that I find and that the team finds within the partnership with Zeta is just that it's such an open, flexible, easy to work with platform. And the way that we work with the Zeta team really is customized around our agency, around our clients and around our business. It's not a one-size-fits-all for everything that we have to service and to do for our clients.

I mean, we've started with one very large retailer here in the U.S., which is Bells. They have both Bells and Bells, Florida. The store traffic and the ROI are doing exceptional and month-over-month, the revenue or the insertion orders that we're sending over the data continues to go.

And this has been for over a year. Following that success in those case studies, we've also been able to add another client, which is United Parks. With United Parks, who owned SeaWorld and many other amusement destinations. We're driving inbound tourism from the U.K. to Orlando to drive visitation and to drive people to the parks to buy tickets. We're seeing massive success in the early stages of that campaign as well. We're in other client conversations, active conversations both new and organic to see how we can leverage the platform and maximize the ROI for our clients.

Excellent. Look, I think Adam really pointed out how he looks at his business just as any enterprise would. He's looking to acquire customers. He's looking to retain those and grow those customers. And the idea of Zeta sitting alongside Google and meta to make the whole agency smarter and work better in order to accomplish this is a big part and a big foundation to this partnership that is again, been about a year, and we look forward to the future. And this is just an example of how Zeta partners with independent agencies and in reality in holdcos alike. So I want to thank you very much, Adam, for joining us on stage. I hope that was helpful for all of you. Thank you.

Well, thank you, Jed, and Adam. A lot of great content covered so far today. Let's see if I can keep the ball rolling. I'm going to step you through a series of metrics that we believe prove the durability, predictability and profitability of our growth, starting with how durable our growth has been. I began the day discussing our track record as a public company of growing greater than 20% every year in which we've been public.

The actual compound growth rate of our business over that period of time has been 28%. That's even after you adjust for the help of the biennial political candidate revenue contribution. And as you can see in recent years, the growth trajectory is pointing upwards.

Underpinning that growth has been expansions in total scaled customer count and superscale customers. In fact, we've compounded growth since going public at 13% in total scaled customers and 22% in super scaled customers. But that only tells part of the story. That's because when we work with global enterprises and agencies like you just heard from Adam, we'll count those as one scaled customer.

On the brand dimension, as depicted on the iceberg, that's a different growth vector. In fact, just since our Investor Day 2 years ago, we've grown total brand count by 45%, to upwards of 850 unique brands. And each one of these brands meet the definition of a skilled customer. So for context, 850-plus brands equates to 567 scaled customers, which, as you can see, has been growing 33% itself over the last 2 years. But not all of the growth has simply come from agencies. In fact, over that same 2-year period, enterprises on a compound growth rate basis, have added 18% more brands and agencies, 40% more brands.

But keep in mind, just the consolidation of our 5 agency holdco partners, they support over 15,000 brands. So we're barely 1% penetrated into that opportunity. And the addition of brands by enterprises and agencies has a positive effect on ARPU growth, obviously. But you can also see here how durable ARPU itself has been, and we have three ways in which we can expand ARPU growth. First through channel expansion. We think of that as an up sell motion. Examples of channels on Zeta platform include email, mobile, social, display, video, Connected TV, audio, the list goes on.

We can sell incremental use cases. Examples of Zeta's use cases include customer retention, customer growth and customer acquisition. We think of that as a cross-sell motion. And as you're going to increasingly hear from us, we can drive AI adoption, which drives more usage. And we'll go into each of these now in more detail.

First, starting with channel expansion. In late 2021, we made a complete shift in our go-to-market model. We went to a hunter-farmer sales model. And when we did that, we then made it available to all sellers on the platform to sell all channels. Prior to that, we were siloed. And as you've seen in our product demos, Zeta knows which channels, individuals in our data cloud prefer and are most responsive to, which then allows our customers to build hyper personalized omnichannel journeys, which are sellers have become very adept at selling and their progress is hard to miss.

The fastest-growing customer cohort are now those customers using four or more channels who constitute greater than 50% of revenue on our platform. And the more channels customers use the higher their net revenue retention rate. And we continue to add channels on the platform with room to expand.

Here, you're seeing the total channel breakdown for all of our skilled customers. Email, continues to serve as that strong activate foundation. But yet there's very strong diversification across programmatic channels as well. The addition of Marigold will only add to high margin e-mail footprint. Adding incremental use cases is also a powerful tool for ARPU expansion. In fact, it is the biggest opportunity as you've heard from Steve Gerber, in our existing customer space. We call that our OneZeta sales motion.

Back in 2024, when we initially created the OneZeta sales motion, we did so to a very narrow subset of customers. And it was only this year that we began to gradually widen that net. And you're starting to see a really exciting inflection point. But what I would argue is the most important element is how much runway is in front of us, greater than 80% -- of our total scaled customers today, all 567 still just use one of our customer retention, growth and acquisition use cases.

But when we do see that jump from the first to the second, ARPU triples. It goes from an average of 1.5 million per scale customer to 4.5 million per scale customer. And then the third leg of the ARPU expansion tool is driving AI adoption, which creates incremental usage. The inflection point here was in 2024, late time, early '25. We actually took our internal learning and development teams that were focused on training our sellers.

And we turned them into a customer facing organization. So we're rather than only relying on Zeta Live once a year to bring all of our existing customers and prospects together to learn about our products, train on our products, we began to take ourselves on the road. And what we're seeing is rapid adoption.

Here are three of our top-tier users of our generative AI. We're not talking about Machine Learning or Natural Language Processing. Those capabilities have been embedded and induced by our customers since prior to going public in 2021. This is about how they're creating pulling intelligence out of the platform, building agents, linking multiple agents together to create automated workflows. And what we're observing when that happens is that it spins our flywheel faster. A time to a faster audience spins the flywheel. A higher ROI audience spins the flywheel. More agents linked together performing autonomous work, spins the flywheel, which drives ARPU higher exactly as you're seeing with these customers over the last several quarters.

So we looked at durable growth trends in customer count and brand count, for channel expansion, for use case expansion, even adoption of AI dreading usage. But now let's transition to how predictable Zeta's growth has been.

As an investor, you can underwrite predictability when there's a track record of execution. When we first went public, we immediately published our first long-term model, Zeta 2025. And on each one of those elements, we exceeded our goals. So now I want to look into what creates the ability for us to set these goals like Zeta 2028 in this case and then continually over-deliver.

We believe at Zeta, balance and diversification are key ingredients to predictability as opposed to how concentration can create lumpiness. It's why we strive to keep a balance of our sales team between hunters and farmers. Hunters are focused on closing pilots, proof of concepts and RFPs. They're charged with driving new customer revenue, whereas our farmers are charged with driving existing customer growth through ARPU expansion, which comes on the back of great customer outcomes.

And it's led to very organic balanced growth. Since 2021 through 2024, we've averaged 12 points of our growth from existing customers, 15 points of growth from new customer revenue and 2 from M&A. So now let's drill into each, focusing first on that existing customer growth vector. One of the big takeaways I hope you get from today is the longer Zeta's customers are with us, the bigger they become.

Historically, we've shown you 3 cohorts. Those customers that have been on the platform less than a year, most oftentimes closed through pilots, 1 to 3 years and greater than 3 years. Here, we've added another cohort, customers that have been on the platform now for 5 or more years. And they follow the same pattern as their predecessors. Each year, they're spending more. But more importantly, they serve as the foundation of spend on the platform.

Almost 60% of Zeta's revenue now comes from customers with us 5 or more years. So now combine that cohort with a cohort of 3 to 5 years, and you have greater than 3/4 of Zeta's revenue with a track record of generating high net revenue retention. In fact, that cohort generates greater than 115% net revenue retention over the last several years, and that's just an average. Last year was higher.

So zooming out, 76% of Zeta's revenue, our longest tenured customers who keep spending more, who we can predictably rely on generating at least 115% net retention in the beginning of each year. Our new customer sales engine is not just highly predictable, it's very productive. What we're seeing from our hunter sales team is each year on average of expanding their sales by at least $300,000, to at the end of last year, an average of $1.4 million per hunter. Now keep in mind, most of the deals these individuals are closing are between $50,000 and $150,000, pilots and proof of concepts. So the average number of deals closed per year is more than 1 per month.

Now to put this even in more perspective, for 2023 and 2024, as you're seeing here, new customer revenue contribution was 16 points of our growth. We've also talked about our improving revenue visibility. Obviously, the planned acquisition of Marigold's Enterprise Software Business is only going to help. And we're looking at the organic part of Zeta. And I'm removing the seasonal nature of political candidate revenue and advocacy revenue, which is more consumption-based.

As you can see, not only is the trend working its way up, but the amount that our recurring revenue base grew in 2024 was 35% year-over-year. I think there's a perception that most of Zeta's growth has come on the shoulders of our consumption part of the business. Now against that same benchmark, consumption has grown at a healthy 23% rate. But you can see, the recurring part of our business has been a very strong contributor.

So we discussed predictability from a few different vantage points. The contribution from our existing customer base has been strong. It's predictable, and we wake up with a net revenue retention rate for about 3/4 of our business of 115% each year. A very productive and predictable new customer contribution and more and more visibility, not just because of a growing recurring revenue base, but the addition of Marigold to come.

So now let's focus on profitability. Every year since we've been public, we've expanded adjusted EBITDA margins and free cash flow margins year-over-year. In fact, we've grown free cash flow dollars the fastest relative to revenue and adjusted EBITDA.

So now let's look at the building blocks that has enabled us to do that. From a cost of revenue perspective, our biggest lever is positive mix shift, and we're excited to see what's unfolding with the agency customers in particular. Since we really started to rapidly scale with them at the beginning of 2024, late 2023, not only have we added a substantial amount of revenue from expanding brand relationships there, but you can see that's been on the shoulders of those agencies wanting to use Zeta's direct channels. Direct channel mix for our agency holdco customers has gone from 45% to now north of 60%.

Not only do we see positive mix shift continuing, but the addition of Marigold's Enterprise Software Business, which is high-margin e-mail, should only be a further tailwind. In fact, if you look historically at their cost of revenue profile, it's been sub-30%, whereas Zeta for the last couple of years has hovered between 38% and 40%.

Now shifting gears from COGS to operating expenses. We've maintained discipline. You heard this throughout Matt's presentation and even Neej and Chris' in terms of the addition of headcount relative to the addition of revenue. From 2022 to 2024, we've added 15% more heads. By the way, the vast majority of those came in this form of our centers in India, which grew 17%. But against those benchmarks, revenue grew 30%.

And what you heard from Matt is we're not just focused on bending that curve, but breaking that curve so that we can grow without needing to add people. We're also focused on the sales and marketing front on building a high-performance culture and high productivity culture. We're not afraid to continually adapt and evolve our go-to-market.

You heard me talk about our shift to a hunter-farmer model several years ago. A year after that, in 2022, we fully verticalized our sales team, creating specialty sellers. We changed our hiring habits. We started to hire much more experienced, longer tenured sales reps. We even changed our internal management systems, going to a process now where every single day, we understand what are the habits and what are the activities of our sellers so that we can win faster and fail faster.

And clearly, it's having a positive outcome. Pipeline per seller, the value of the total value of their pipeline is up over 50% year-over-year. The total contract value of the deals they're winning is up over 50% year-to-year. And their average deal sizes are up 50% year-to-year.

So what is the really big point? The levers that we have visibility to right now in COGS and in operating expense, we now believe we can get to a structural adjusted EBITDA margin of at least 30% by 2030. And we see ourselves arriving there through between 1 point and 5 points of positive mix shift affecting cost of revenue, getting another 3 to 5 points of productivity from our sales and marketing part of our portfolio.

Now by the way, in the last 2 years, we've averaged around 340 basis points. And then in G&A, where we do the most amount of scrutiny of where we need to add or where we can subtract, we're targeting 4 to 6 points or getting effectively, our G&A structure between 8% and 10% of revenue. And more and more of our adjusted EBITDA will drop to free cash flow. As compared to our Zeta 2028 model of at least 65% conversion, we now see a clear pathway to at least 70% conversion.

We've created a whole new growth, or I should say, shrinking trajectory in CapEx and intangibles that should stick. The eventuality of working through our working capital headwinds that as we've seen this rapid growth with agencies as part of their normal payment cycles creates a working capital deficit for us, we see that normalizing. An interesting data point, year-to-date 2025, our cash conversion has averaged 58% from adjusted EBITDA. If we just had a neutral working capital position, that conversion would be 80%. So we're even being conservative in this session. We're still assuming a headwind.

So as we bring all of this together, throughout the day, you've heard about the durability of our data, of our competitiveness and what I've covered, our growth rates. You've heard about the predictability of the types of outcomes that we can drive for our customers as well as Zeta's revenues and our margin expansion. And you've heard about our focus on profitable growth. So if you carry forward our revenue growth model of at least 20% organic revenue growth every year through 2030, you carry forward the adjusted EBITDA margin goal of at least 30%, you've got a Rule of 50 business there. But if you extrapolate the 70% free cash flow conversion rate, that's north of Rule of 40, as my friend, DJ would always remind me on a free cash flow margin basis.

So with that, let me wrap, hand the stage over to David to bring all of what you've heard together, and I look forward to connecting with you during the Q&A session after that. David?

I've been told you have to push the button very hard. So I started yesterday. Well, maybe I went too far. Okay. So we got here -- I got here Sunday evening, Monday morning, I did Bloomberg at 7:00 a.m., which was early L.A. time. Then we ended up closing the New York Stock Exchange, Monday, rang the bell. Tuesday, we did our global town hall yesterday. I have not seen that much excitement in our business since its founding. Then I had to fly to Dallas to give a speech yesterday, have dinner, got back at 1 in the morning. And then at 8:00 a.m., I was at the breakfast for our Customer Advisory Board.

So simultaneously to this meeting, we have our CAB meeting, which I was just so blown away. We have some of the biggest brands in the world are in the room helping to make our business better. We have 138 current projects that have come out of our Customer Advisory Board meetings that we're already building products for consumers. I will say Chris is very difficult to follow when he's talking about Rule of 50, Rule of 50, Rule of 50, but I've been relegated today to brand and M&A and long-term strategy. So what Chris tells me to do, I deliver on.

What I would say is the move from Zeta who to why Zeta has happened. When we walk into a room, I no longer have to spend the first 50 minutes of the hour explaining who we are. I now get to spend the full hour explaining why they should be choosing us over our competitors. The next evolution, which we're really hoping to get to, I believe, over the next year, I don't think this is a 5- or 10-year journey, is Zeta now. Our pipeline going into Zeta Live is already at a record high. And last year, Zeta Live was the single biggest pipeline creator and business creator in the history of our company. My goal is to dwarf that this year. And as we grow into next year, the question is, how do we get people saying, I must have Zeta now.

Now must-have Zeta is a little more aspirational. That's more like a must have Microsoft or must have other brands of its type, but it is what we aspire to. If you look at Zeta Live this year, it is really changing the game for us as a business if you look at our website use, you look at our demo requests, you look at how we're rated. We put out on news, I think, 2 days ago, we were rated #1 in AI integration from a marketing perspective by 3 separate rating sources all at one time, including Forrester. 240% attendance this year. To be totally transparent, just to be clear, we've got fire marshal approval for 1,200 people. We have over 2,000 non-Zeta employees registered. I don't know how the hell we didn't shut it down earlier. But we then have the seventh floor, which you guys will have access to at some point, where we're going to be able to park people.

So now what we're doing is we're going to livestream it to our offices in New York City, and we'll rotate employees in and out and try to make that work. Our RFP volume is through the roof, and the positive sentiment of our company is at an all-time high. When you think about the evolution of our business, we always think about M&A, right? We've been in business for 17 years. As I always like to joke, we've bought 17 companies in 17 years. It's highly probable there will be an 18.

Our strategy, though, continues to be incredibly disciplined and very, very focused. We will continue to look at the 5 main criteria and then look at how Marigold fits into that. So one, can we fully integrate Marigold into our platform in the first year? The answer is absolutely yes. I actually believe we can do most of it within 6 months. Two, will it be accretive from day 1? We have already told you we've paid approximately 10x forward EBITDA to purchase it, well under 2x revenue. That is the definition of our current valuation of accretive.

Process clear synergies. We believe that we can cross-sell the heck out of this group. You've got over 100 global enterprises, including more than 40 Fortune 500 companies and 20 of the 100 largest advertisers in North America, all on one use case. How do we get Ed See in there, as you saw Ed speak, and make these One Zeta customers. Just a little side note, most of the One Zeta customers we've created thus far started on the use case of retain. We find it's easier to go from retain to activate and monetize at least at this stage of One Zeta than it is to go from activate the other way.

We're going to crack the code on all of it. But the thing I like about Marigold is 100% of their customers today are on retain, which also is nice because it's almost all subscription revenue at very low cost of goods sold. So that will help us with our long-term visibility into our business and give us even greater views into that. Although we get a lot about visibility into the business, I don't know at what point we will start to get credit for understanding our business. We have been public for 16 quarters. We have beat our guidance 16 quarters and raised our guidance 16 quarters in a row. Maybe we'll have to get to 20 or 30 before people say, oh, these guys actually know what they're talking about, but we'll get there eventually.

We think we can grow this business at or above our organic growth rate. That's really important. The business itself is right out of our playbook, where we're going to take sell-through, we're going to combine it with LiveIntent and discuss into building the premier publishing cloud in the world. Let's be clear, in a post-OpenAI, post-Gemini world, publishers need traffic and they need monetization help.

And our Publisher Cloud is going to deliver both. We pick up Selligent in Europe and EMEA, where for the first time, we will have a meaningful presence there. Our data cloud already exists there as native to the European environment, and we'll be able to merge the data cloud in with Selligent very, very rapidly. And then, of course, you've got Cheetah Digital, which is one of the premier marketing automation platforms out there. Merging that into the Zeta Marketing Platform is going to allow it to scale very, very quickly.

For the fourth quarter, we're going to do nothing to just satisfy the customers. We got to make sure everybody comes out of this very, very happy. And then access to world-class people, we're picking up some of the world's best talent in sales, engineering and management, and we're very, very excited about that. To remind you, about a year ago, we told you we would do all of this with LiveIntent, and we have. So from a credibility perspective, I think we integrated all of LiveIntent within 90 days. I'm not sure we'll be able to do that quite for this. But I think we'll have everything done, integrated within 6 months, although Gerber might kill me for that. This is the future of our company.

I will tell you that this, to me, is the single biggest thing we've ever done. I got the full demonstration about a month ago, and I literally got chills at how good it was. I will tell you that when I saw this product, I -- and not to belittle Zeta -- I thought this would be a Meta product. This would be a Google product. But we are the ones who cracked the code. This is truly conversational artificial intelligence in a platform that can then control the full ZMP on an integrated basis today.

Tomorrow, this can be our clients' full ERP and operating system. We believe this can integrate into anything that they're doing, not just from a marketing and a business intelligence perspective, but from a product development perspective for them, from how do they make their businesses better and how does this truly become the operating system of our clients' lives and businesses.

Now to be clear, that is not today. But tomorrow, we're going to be doing a full rollout. I have been bullied into doing this at the open of the conference. So I'm going to do a live demo of it, which I've never done before. So I'll try to channel my best Steve Jobs tomorrow when we open, but I'm going to open, and I'm going to begin a very deep conversation with Athena, who's going to tell me some really interesting stuff. And then at 11:00 tomorrow, Chris, Neej and [ Nate ] are going to do a deep dive. It is unbelievable. I really encourage you all to see that.

When you think about it, why are we uniquely positioned to do this? Because if you take our data, it cannot be replicated. So the data informs Athena in ways that no other algorithm can be informed. I will go out on a limb here. Those of you who know me know I enjoy doing that. And I will tell you within 5 to 7 years, I believe most artificial intelligence will be ubiquitous. I like to remind people that then think I'm crazy that 100 years ago, there were 3,000 companies in America that sold cars. And no, I was not old enough to have been there. But today, there are 4 or 5 companies in this country that sell cars. We're going to have a very similar situation, I think, in large language models and algorithms. The difference is going to be the proprietary data you feed into it.

So when our clients access Athena, they're accessing the consumer data platform that houses their first-party data, merge with our first-party data, merge with the vast majority of data from the open web. Zero data exhaust, all of the intelligence will live inside of the platform, and Athena will effectively, day 1, become your data scientist and your ability to activate seamlessly in a fully conversational way. It's really exciting to me, and I'm excited for everybody to see it tomorrow.

We are pacing well ahead of our 2028 goal. You can certainly do the math on it. And from a mathematical perspective, I won't pretend to give anybody in this room math advice. My assumption is you all can do it better than me. But the faster we grow earlier in the plan, the more you would have to decelerate to only get to the $2.2 billion in 2028.

So as Chris already started talking about, we're thinking about 2030. We're thinking about how do we get to a 30% operating margin, not just a 25% operating margin. We're thinking about how do we take our free cash flow conversion rate from where it is to greater than 70%. These are all things that we're very focused on as it relates to operating the business and something we're very, very proud of.

So the replacement cycle is accelerating. We are seeing more RFPs than we have ever seen, ever. A lot of that is going from Zeta who to why Zeta. Hopefully, we'll get to Zeta now. But a lot of it is also just you're looking at the technology that's out there. Think about this. Salesforce bought ExactTarget 10, 12 years ago. At the time, it was their primary secondary hustle. Then they bought Slack. And now all of a sudden, ExactTarget is the side hustle to the side hustle. You're not seeing investment dollars into infrastructure flow into the large marketing clouds, and that's Salesforce, that's Adobe, that's Oracle.

When you look at our business, everything we do is purpose-built to be the world's greatest marketing platform. So we're really seeing in this replacement cycle, a lot of the enterprises that have been on those competitors for 5, 7, 10 years are like, they're moving, and we're seeing that happen faster. We are the leading AI-powered marketing cloud. And when you plug Marigold -- say that 3 times fast -- Marigold Enterprise in, it's going to accelerate it. We really feel that the ability to take their customers, make them One Zeta, migrate them onto our platform and grow them on all use cases is going to be a meaningful driver to growth. Our innovation is better, creating better outcomes and sharper differentiation.

To be clear, the other thing we really get out of Marigold, which we've talked about a lot on the last call, I'm talking about a little less today, but is the loyalty program. When you think about the loyalty program, I was -- as I said, just at the CAB meeting, 3 CMOs of 3 Fortune 500 customers literally came up to me and said, we love the loyalty idea because we do it internally, and we're just not doing it well. To me, that's great, but the more valuable thing is training the algorithms. Today, for every dollar a client spends on the Zeta Marketing Platform, we return between $5 and $7 in revenue. I have not been shy about my aspiration to get that to $10. We're already 100% better than our competitors. I want to be 300% better than our competitors.

I think the loyalty data, the ability to get SKU-level data into the models will make us that much better. Our growth is durable, it's profitable. And guys, for the love of God, it is predictable. 16 quarters in a row of beating guidance and raising guidance. At some point, you have to give us credibility for being predictable, although Marigold certainly will help, hopefully, with that, as we meaningfully increase our percentage of subscription versus utilization, and we are pacing well ahead of our 2028 targets.

With that, I believe we're moving to a Q&A session, Chris? Excellent. I have to leave.

All right. Well, first, thank you. I know this is a huge, huge time commitment of yours, and it's our privilege to be able to do this with you. So we've left 30 minutes. There's a countdown clock back there. If I'll kind of give us 10 minutes and 5 minutes, just you can get a sense of getting questions in. Matt Pfau is going to be running around with a microphone. So let's go ahead and get started or Matt's got to choose favorites.

Great. I guess I didn't know I was getting the first question. Scott Berg, Needham. Thanks for the time today. And of course, tomorrow, this is a great event. Lots of questions to choose from. Steve, I wanted to pick up one of your slides on there. You talked about a 4x ARPU kind of growth opportunity. Your customers, after they stay with you for 3, 4, 5 years, are already spending 2, 3x what they initially spend with you.

How does the AI functionality that you're talking about today, whether it's with Athena or other applications kind of bend that opportunity? Does 4 go to 5? Does it go to 6? How do we start thinking about that? Because my guess is that 4x opportunity does not properly embed what you're starting to see from the new innovation you're bringing to the market.

So it's a great question, and it was obviously a big part of what we were talking about of the predictable growth trajectory. And so there is some AI that's already baked into that, that again goes back to the notion that provable results unlock scale.

But there's 2 dimensions really to your question. So one is time and the other is value. So I believe that as we establish the interface standard, that's going to compress time. Once we also have the interface standard combined with the decision standard, that's what expands the addressable market for us. We also, on top of that, have One Zeta moving from motion to model. And Ed, who is right behind me, is turning that into more of a repeatable playbook. And we're already seeing greater than 4x movement for certainly the opportunities that I showed in the case studies. Ed, anything to add?

I think as you think about that and moving into the model perspective, it is going to become an accelerant and bend that curve even more. So the discussion with customers will make a significant difference to them on what they're going to be able to do and how much of their budget will be able to impact.

Next question.

Thank you, Arjun Bhatia with William Blair. I appreciate all the insights today. I think it was very encouraging to hear some of the pipeline trends. I think even you mentioned 15 points of growth on average coming from new customers, all great data points. I think one of the things that I remember is a critical point in your kind of customer journey is when customers are in pilot and can you get them successful to come out of that pilot phase because then you can get into the 3-, 4-, 5-year tenure phase, where they exponentially kind of increase their spend.

I'm curious if AI or some of the new product developments that you've talked about today will help change that success rate of those pilots and if there's any data that you track that you can share with us that maybe talks to the success of customers moving out of the pilot phase into production.

Neej and Jed, maybe you want to take that, and then anybody else can jump in.

Sure. So I think that the value of Zeta data is a well-known quantity now amongst our customers and prospects. So the operationalizing that data through AI is becoming easier and easier for us, as you've noticed in Chris' presentation and my presentation. So certainly, the performance, we expect to continue to improve. The moat around the data as a differentiating asset continues to build. And we're seeing that with the pilots that are coming from Jed's team and Pam's team as well. So it's kind of like a self-fulfilling thing at this point where the data is empowering the AI, which is actually creating more data for us along the way. Jed?

Yes. So we're seeing it in 2 ways. The easiest on-ramp is utilizing Zeta data for a customer. We're just utilizing Zeta data. And then we create the opportunity to bring in the clients' data and enrich that data, and then we become even stickier. So that's really how we're seeing that on-ramp to the opportunity is beginning with our data, less friction, easier, faster for the client to test the underlying intelligence of our platform and realize ROI, and then incomes their data, and we double down and supersize that.

Arjun, to be very specific, yes, I believe that the AI will help us increase the percentage of pilots we convert to full-time customers, and we are seeing that trend happening now. So with the pilot, one of the hardest parts is the onboarding, getting it started. By way of example, statistically, we can now onboard a client using our automated AI platform 5x faster than it used to take us to onboard a client.

Those types of solution sets and speed to market impress the client, really help with the return on investment day 1, whereas it used to take a lot more discovery. As a pilot would run, the algorithms would get smarter over time. Today, because the algorithms are so much better, we're able to deliver superior return on investment to a pilot as a percentage of return on investment than we would have even a year or 2 ago, and we're seeing that help us convert more pilots to full-time customers.

Awesome. Matt, next question.

Awesome. Elizabeth Porter from Morgan Stanley. I wanted to ask again on Athena. Clearly, your enthusiasm for the product shows through. So first, just vision for how it gets monetized. Is this embedded in the platform and drives more usage? Or is it a broader replatforming that has some sort of amplification on the platform fee?

And then the second part is, just as we make it a lot easier to get more of this technology into the hands of users, what does it mean in terms of broadening the addressable customer base? And second, the shift from agencies to in-house as you can just do more as an in-house, making this technology a lot easier.

I'll take the first part. And Chris, Steve will take the second part. So the answer is day 1, it's about getting it into everybody's hands, Elizabeth. How do we get all of our clients using Athena? And when you see the demo, you're going to see it's going to actually -- today, it's in beta with internal use. We'll have clients using it this quarter. I'm hoping it's production ready to go out to everybody by Q1. It's just going to be added to the platform. So it's going to drive meaningful increment in usage initially as they want to add modules to it. So as it moves from marketing to business intelligence, to more ERP functionality, we will charge for those modules.

So day 1, remove friction, create additional productivity for the client because they'll be able to replace the vast majority of their internal data scientists. And the vast majority of the people that are hands on keyboard activating will all be replaceable by Athena. Down the road, I believe it will be a meaningful ability for us to sell those modules as they move into new business cases. Steve?

Part of ubiquity and ubiquity is core to all of the standards that we've talked about establishing. Core to that is the partner ecosystem. So we view, as you saw today, agencies and SIs as partners. We don't view them as competitors. One of the benefits of Athena is that it can move laterally as well. So not just at the enterprise where that becomes the center of gravity, but also into their partner ecosystem so that everyone is using the same standard. And that's how the different tools connect instead of compete. So we see it as an amplifier, not a replacement.

Next question?

Great to have the leadership team on stage. My question is on data. And specifically, you talked about Snowflake a couple of times. When you look at your large enterprise customers, talk to us about what they're doing with their data estates. What are the use cases that naturally belong within Zeta? What are the use cases that do not belong within Zeta and belong as part of a broader data strategy with Snowflake and Databricks? And where do the 2 converge?

Maybe Neej and Pam, do you want to take that from some of our retained customers' perspective?

Sure. Sure. So Snowflake is interesting because in the last 10 years and Databricks as well, enterprises have tried to really containerize their data in one place to make it economical. What's happened because of that is that now their CIOs and marketing teams are looking for ways to monetize. So enterprises are different in their configurations. Some people consider the golden record to live inside of Snowflake. Some enterprises consider the golden record to live outside of Snowflake. We can support both models, and we do.

And when we layer on top of Snowflake, what we're doing is we're essentially adding the application layer to make that data valuable in production. So you can acquire, you can grow, you can retain. Snowflake as a container doesn't do anything for the enterprise natively, but it gives you an environment where now you can apply the AI, you can do something more interesting and you can achieve better ROI.

One product that I called out today is the Zeta Media Engine. That is a co-developed effort with Snowflake, and it allows customers that are on Snowflake to collaborate with their partners, collaborate with Zeta in a tax-free manner and move data into an activation workflow in a cleanroom so you don't have to actually exchange any PII with us. So that is a very powerful product, and it's a very powerful and on-ramp into Zeta across media use cases, and we're seeing more and more adoption across that product with the most sophisticated enterprises. The largest hotel chains in the world want to operationalize with us in that way, the largest airlines. So it's becoming more of a standard for us to deploy as well.

Yes. And there are certainly many use cases outside of the media engine. So customers are storing their transactional data, any of their website visit data, even store visit data, loyalty data, all of those things really to try to get customers to be more engaged in any channel, but also to do repeat purchases or repeat transactions. Whether that's travel and hospitality, retail, telco, we work with all industries. So many of our customers are storing a vast amount of data in Snowflake. And again, it can range everything from customer data to transactional data. And then combined with our data assets, as Neej mentioned, makes it more powerful and the decisioning easier and faster so that we can be more accurate in who to target when and what channel.

Awesome. Thank you, Pam. Matt. Next question.

Thank you, guys. I appreciate all the color today. DJ Hynes from Canaccord. I'm going to ask questions of the 2 Chrises. Chris, I'll start with the finance question. You made the case that the replacement cycle is accelerating, then you gave us some very Zeta-specific data points, right, 50% increase in deals per rep, 50% increase in -- I think it was deal size. Is the takeaway that you want us to have from the finance part that the business is accelerating as well? Maybe I'll start there, and I can ask Chris.

The broader trend would say yes, right? I don't want to get into where third quarter is. We've got early November to do that. But the underlying metrics, if you look at it as backwards as '21, '22, '23, '24, whether it's our scaled customer count, our brand expansion, our use case adoption, all of those metrics, which eventually make their way to revenue. Those are improving.

Okay. And then, Chris, on the tech side, you made a comment, and I'm paraphrasing, something along the lines of like you can't [ bytecode ], this stuff, right? Intuitively, it makes sense to me, but it's like the unknowable bear thesis that's afflicting the category today. So maybe to go like a layer deeper, like what can you [ bytecode, ] what can't you? And what gives you confidence in kind of the durability of the platform?

Sure. So this is a tricky question because you have to go like 4 layers deep in order to really get to the marrow of what's preventing people from building enterprise software at scale using [ bytecoding ]. I'm going to start with the tools that we use at Zeta and our engineering team. AI-driven tooling for engineers is here, and it works incredibly well. Automated QA testing, digging into an issue. We're seeing massive performance gains. Quite literally, something is solved in 2 minutes. It might have taken a team of engineers hours and hours to figure out before. So AI tooling is here.

When it comes to building enterprise-level platforms, where the broader industry is nowhere close. You can't use one of these coding environments to build something that has trust and security and deployment and scaling all in it. So we will see organizations come out with really jaw-dropping applications that they built in a night, but they're vaporware. They're this thick. For them to go through and productize that, if they're lucky, they've got a robust adaptive fabric, like I talked about earlier, that data foundation that serves all of it, and that data foundation really needs to culminate from years of wisdom.

An identity graph. I've been in this for a long time, built a lot of identity graphs. Getting it right is not something you do in a single shot. And AI today is still very single shot oriented. You can evolve it slowly, but it's not going to scale at an enterprise level business. SMBs, if you're a 4-person start-up, eat your heart out, but we all know that 4-person start-up is going to get something that gets product market fit into market, and then they're going to go after build it afterwards.

Let's also be clear, DJ, to get through a large enterprises, data security audit, their procurement team, getting to the level of enterprise-grade solutions that are necessary to these large companies, no large language model is even in the ballpark. So I do think -- there's been a lot of talk about it over the last week. I think it's massively overstated as it relates to just enterprise software, not just Zeta.

The other thing I would say that is a meaningful differentiator to Zeta is our data cloud. None of the large language models have any deterministic data. Now, they might have some small data sets on the people who are logging in and paying them to use their product, but that's not going to help them in the enterprise ecosystem. That's not to say that OpenAI, Claude and the others aren't building incredible businesses, they are.

They're just not even remotely in the ballpark to be building enterprise-grade software that could get into a large enterprise. I mean, could you imagine the largest banks turning that over to a large language model, the largest airlines, the largest hotels, the largest automotive manufacturers. They have built their businesses and are not going to trust it to a non-enterprise-grade product.

Awesome. Next question, Matt.

Terry Tillman, Truist Securities. It's a 2-part question, sorry in advance. Pricing strategy, you've alluded to this several times. And I know with some agentic capabilities, that's going to naturally be a kind of a pricing dynamic that's different. But you talked about into next year, there is some pricing strategy kind of evolution going on. I'd be curious if part of that is to further accelerate One Zeta or maybe it's to capture more of this point in time replacement cycle that seems like it's a big deal right now?

And then the second part of this question is, what do you think of all the things that's going on Athena? And you have a bunch of new things you're going to be talking about Commerce Cloud, [indiscernible]. What do you think is the biggest single unlock for that second use case? Because that's the real revenue uplift when you start getting into that as you talked about earlier, Chris.

Maybe Matt and then I want to give Nate a chance to give a perspective, but then feel free to close it out maybe.

Very good. So on the pricing strategy, I mean, as I said, we're still in the process of sort of refining. But what we do know as we look at sort of our customer base and we think about the adoption path that are going on and even as you talk about sort of capturing more of the One Zeta sort of aspects to it, is ultimately, we're trying to create a strategy that removes all of the friction related to the adoption.

How do they have the ability at any point in time as their strategy changes to be able to go into the next feature of the tool, the next capability, the next channel without having to go back through procurement prices, go back through negotiation, go back through all of the aspects that really prevent them from sort of moving forward. So we're looking at mechanisms that creates fungibility of what they spend with us in order to give them opportunity to really explore and use every aspect of it, from the AI to a new channel to a new set of features to help define sort of the strategies that they're going to sort of leverage in those things.

So we're in that process now. We're actually working very closely with our customers and sort of talking to them about what it would look like within their world because as much as we can go in and launch those strategies out there, it's a little bit about how they also buy. So we're working with them in order to understand those aspects of it to make sure that we're going to end up in a place that doesn't necessarily create more friction when we're trying to remove all of the friction from that process. That's out.

David, do you want to...

Let me jump in. I'll let Nate talk about Athena because he's really, really good at that. When you see the demo of Athena tomorrow, Terry...

They got us a little bit of a sneak peek, but not the full.

I heard that. I was surprised, but that's okay. When you see the deep dive tomorrow, which was supposed to be tomorrow, that's fine, you're going to see Athena seamlessly move through multiple use cases in a conversational manner. So when you think about the ability to move from 1 use case to 2 and 3, I have never seen us or, quite frankly, the market develop a product that removes the friction, to use Matt's vernacular as well as Athena does. So effectively, you could be a single-use case activation client using multiple channels. And Athena could literally ask you, hey, have you thought about the fact these customers are likely to churn, we can help you save them literally in real time. Nate, did you want to add to that?

Yes. Just to compound on what David has articulated and Chris, as we -- tomorrow, we'll really start to see the journey around the application of Athena, where apps have been built on our SuperGraph and data platform. Now when we think through moving forward, what that looks like, we want to really evangelize the developer community that's really the unique data set that we have and start to build applications, more applications at the top of it for the marketing jobs to be done and as well as adjacent industries. And so we have OpenAI tomorrow, who will be speaking as well on our panel and comparing those to my friends at that business, that's where we truly believe is going to be the step change as we move forward as well.

Thanks, Nate. Thanks, everybody. So we're about 9 minutes, probably 2 to 4 questions, if we keep them to single part questions.

Jackson Ader at KeyBanc Capital Markets. The One Zeta strategy kind of began with -- had some restrictions on it, right, on who could sell it, who you were actually targeting. It seems like the 50% slide, right, like 50% pipeline up, 50 -- up above 50%. Are there any limitations still on the One Zeta? Or is it like everybody can sell it now to everybody? Or is there still some sort of like strategic rollout that we should be waiting on?

Steve?

So One Zeta has gone from a motion to a model. And when it was a motion, we wanted to ensure that we could perfect it. Testing, learning, scaling is core to anything that's data-driven. And as we're moving from data driven to answer driven, we're able to expand the aperture.

The other thing that we did was structural. And when I talked earlier about the notion of growth being not just predictable but structural, it's not just how the platform is operating, it's how we are operating. So the notion of an operating model is purposeful. And a big part of perfecting it with a smaller population was so that we had the beginning of a model that recruiting Ed See out of McKinsey would be an amplifier to take it to another level. So I'm going to tee it back to my partner, Ed, to talk about how we are taking this to the next level and how each and every case study that I walked through today is a now example, not a yesterday example. And those are not in isolation. Those are all repeatable. Ed?

Absolutely. I think one of the big things, as Steve was mentioning, was moving from motion to model. What we're doing with One Zeta is really opening up the CMO TAMs. Beforehand, we've been working deeper down the organization with semi-fungible budgets from CRM, CDP to performance media. Now we're beginning to say, how do we address the CMO's need, as you heard on the panel before.

And that's really saying, how do we help CMOs be able to recognize pockets of opportunity, reach those pockets of opportunity, deliver relevance to those pockets of opportunity and make sure that they can actually see and track the results. This idea of being able to tie all those pieces together to manage a customer journey and to manage a customer from end to end is what we're now able to do, and we're taking that to the CMOs.

So we've broadened the TAM. We've broadened the folks that we're talking to and we'll continue to make sure that we're going to help marketers be able to take advantage of our precision scale across all touch points.

And to be clear, all of our sales reps can now sell this.

Yes.

Just to be crystal.

Matt, next question?

Madeline Brooks from Bank of America. A quick pointed question for you, Chris. You mentioned NRR of about 115% for 75% of the business. Can you just give us a refresher on the other 25% and trends that you're seeing there?

Yes. The -- so just to kind of create context, the customers that are greater than 3 years on our platform, that's the 76% that has a multiyear average of greater than 115%, where we see the lowest net revenue retention is our less than 1-year customer. A lot of that is driven by the pilots and proof of concept. So when we are between, call it, $50,000 in spend and, call it, $300,000, somewhere in that range, that's where there's the most call it a flame out of a pilot. It could happen for a multitude of reasons.

It could be customers didn't really set aside the budget that we expected to go much broader post the 3- to 5-month pilot phase. But that's where we get the most turnover. So as you would expect, as you look at that slide, you can almost draw a line up into the right in terms of where net revenue retention was. That -- call it that less than a year category. I don't want to be like decimal point precise, but probably somewhere between like 95% and 100% NRR. Sorry, I was doing Matt's job for him. Bad habit.

Matt Swanson from RBC. I guess when we talk about this process of moving from Zeta who to Zeta why to Zeta now, could you talk about the advantage of partnerships like a Snowflake and for companies to be able to say, maybe even also with the increasing business units to say, hey, I can standardize with these guys because there's some kind of shared...

Yes. So let me start by saying that when nobody knew who we were, it was really, really valuable to be able to say we're fully partnered with Snowflake and AWS and others. What's now happened is they've started selling our products as well. So as we've moved from why Zeta -- I'm sorry, from Zeta who to why Zeta -- I'm getting confused with all the different things we say here. We're seeing more sales inflow from Snowflake and AWS in particular. And I think a lot of that was the evolution of the brand. I also think it's one of the reasons we're seeing our pipeline at sort of record numbers. So I do think that, that's helped with that.

I think it's also helping in the agency business, interestingly enough. So a number of our agency clients -- we go one brand at a time. They bring us in to solve a problem, and then we're able to expand there. Some just turn it on. It just depends on the agency. And the ones where you're sort of going brand to brand, we're seeing meaningful uptick as people are even in many cases, saying to the agency, we want to work with Zeta, can you make that happen. So I do think that the brand evolution is meaningfully driving the business.

I think it's also having, by the way, just because I -- as I look at our candidate funnel, and I'm like the constant like, gosh, do we need this many people, but it's actually helping a lot in recruiting. And maybe talk a little bit about our recent accolades that we've had with Forbes and others.

Yes. I always position it that when our clients are choosing us, they're also choosing the culture that we have, our collaborative innovative culture, being recognized by Great Places to Work as well as being on the Fortune top list for technology overall. It just is an accolade to -- and a testament to the environment they're creating for allowing our employees to do their best work, which at the end of the day, brings the client outcomes and successes.

So the other side of that coin, yes, great products, great services, but it's all the team who gets it done and the culture that we provide in order to make that happen.

And to Chris' exact point, as the brand evolves, the level of people that we're able to get join our company as evidenced by Pam, and Ed and Nate -- see who else behind me. Well, you guys have been here a while. But as you look at the new people who are joining us, I won't speak for them, but 3 or 4 years ago, I don't think they would have made that decision. Thank you, Pam. She turned -- I wouldn't know. But the truth of the matter is we're seeing that in Chris' group in a meaningful way. We are bringing in engineering talent that I don't think we ever would have had access to. Chris, do you want to touch on that for just a second?

Yes. I mean we've always recruited the best from around the world, and you have to go out and get your tendrils into those communities. Now they're coming to us. They're showing up at our doorstep. They've heard about us, either they've worked with us as a partner in the past or they say, I want to get into AI, and they see Zeta as the battleground for their career to prove out that they can be pioneers. It's been absolutely exceptional, and a smaller group, I could talk about the last 2 weeks, people that have joined from the top companies in the world because we don't just tell, we show. And that's a big differentiator for Zeta. It's about rolling up your sleeves and doing the hard work.

All right. Let's do one more question and then we'll wrap it up, if there is one. Jason in the third row.

Jason, this has to be a good one. It's the last question.

That's a lot of pressure. Jason Kreyer from Craig-Hallum. I just want to ask about international. I mean you're acquiring Marigold, that's got more EMEA presence. You launched the GEO Explorer. So just how you think about international, that opportunity changing from just a few quarters ago?

Steve?

I'll let David take this one.

I was told not to talk too much today. So I was trying to be good. You're yielding the time.

Yielding the floor.

So listen, our platform operates globally. As you all know, the vast majority of our revenue currently is in the United States. One of the things we were very excited about with the Marigold acquisition was the acquisition of Selligent. They have a meaningful platform, sales team, operations and revenue in Europe today. So our plan is to merge our Data Cloud, which is already GDPR-compliant, already operates in Europe into what Selligent is doing and accelerate our growth, specifically into Europe over the next few years.

So I think that we had always said, Jason, that we thought of international would come with some type of M&A. Quite frankly, it was sort of like when we first started looking at Marigold, they wanted us to buy the entire thing, which didn't work for us because we didn't want to be in the small to midsize business ecosystem, at least not for the very foreseeable -- the long future.

But we were really excited about the enterprise businesses because you got Selligent, which perfectly plugged into Publisher Cloud. You've got the loyalty business, which we think game changing from an algorithm, data and deeper relationships with our clients. You've got Cheetah Digital, which is one of the premier platforms in marketing automation, one of the other very few firms in the Forrester report, which will merge into us. And then we were very excited about Selligent.

Now I know Gerber was particularly excited because now he gets to go visit Europe more often than he was doing, and he's already planned out visiting all the offices, specifically in Southern Italy. But no, I'm teasing.

Just to build on it, though, I think it's an interesting point in time, particularly in Europe. 5 years ago, there was a divergence of forces. There was a divergence of buyer behavior in Europe specifically. We're now seeing a convergence of that. So we believe that the platform that we have, the assets that we have are hitting the market at scale at the right time.

It's also, I think, about to go through a very similar replacement cycle that were -- we saw start in the U.S. a year or 2 ago. The dominant platform in Europe, I mean, they say they have a cloud solution, but I haven't seen it yet. So it does appear as if a lot of what's going on in Europe continues to be on-premise behind the firewall which is very difficult to scale. So we think our cloud solution in partnership with Selligent is going to be a meaningful capability as we focus on growing in Europe.

Two final thoughts from me. First, lunch after this in the cafe. And then second is a thank you. Thank you to our team, to our customers and our partners who were so gracious to speak today, and then really to you all. It's an enormous investment of your time. You've got 1,000 things going on at once. So thank you, and we look forward to mingling with you over lunch. And see you tomorrow at Zeta Live. Bye-bye, everyone.

Greetings, and welcome to the Data Acquisition of Marigold’ Enterprise Software Business Conference Call. [Operator Instructions] As a reminder, this conference is being recorded.

It is now my pleasure to introduce Matt Pfau, Senior Vice President of Investor Relations. Please go ahead.

Thank you, operator. Hello, everyone, and thank you for joining us on today's conference call for the announcement of Zeta's entering into an agreement for the acquisition of Marigold's Enterprise Software Business. Today's presentation and news release are available on Zeta's Investor Relations website at investors.zetaglobal.com, where you will also find links to our SEC filings, along with other information about Zeta.

Joining me on the call today are David Steinberg, Zeta's Co-Founder, Chairman and Chief Executive Officer; Steve Gerber, Zeta's President; and Chris Greiner, Zeta's Chief Financial Officer. Before we begin, I'd like to remind everyone that statements made on this call as well as in the presentation and press release contain forward-looking statements regarding our financial outlook, business plans and objectives and other future events and developments, including statements about the growth opportunities and accretive metrics related to the Marigold enterprise software business acquisition as well as near- and long-term synergies related to the same.

These statements are subject to risks and uncertainties that may cause actual results to differ materially from those projected. These risks and uncertainties include those described in the company's announcement release and other filings with the SEC and speak only as of today's date. In addition, our discussion today will include references to certain forward-looking non-GAAP financial measures, which should be considered in addition to and not as a substitute for GAAP measures. We use these non-GAAP measures in managing our business and believe they provide useful information for our investors. As forward-looking non-GAAP measures, we do not provide a reconciliation to the closest comparable GAAP measure because of inherent uncertainty and unavailability of information without unreasonable efforts.

With that, I will now turn the call over to David.

Thank you, Matt. Good afternoon, everyone, and thank you for joining us today and on such short notice. Today, we announced an agreement to acquire Marigold's Enterprise Software Business. The acquisition advances 3 levers of our strategy. First, scale with enterprises by adding over 100 global enterprise brands, including 20 of the top 100 advertisers and more than 40 Fortune 500 companies. These brands spend billions of dollars on marketing, presenting a significant opportunity for us to cross-sell our other products.

Second, use case expansion through the addition of a scaled loyalty business, a true on-ramp where AI and lifetime value meet and global reach by increasing our presence in EMEA. The business is greater than 90% subscription, carries a cost of revenue below 30% and is expected to be accretive to adjusted EBITDA and free cash flow in year 1. Let me briefly dive into an overview of Marigold's enterprise software businesses, followed by discussing its alignment with our M&A criteria. Then our President, Steve Gerber, will provide more details on the strategic rationale and our CFO, Chris Greiner, will wrap up prepared remarks with financial details before we open the call to questions.

Marigold's enterprise software platform includes Cheetah Digital, Selligent, Sailthru, Liveclicker and Grow. Cheetah Digital delivers enterprise-grade marketing software with global scale and includes a scaled and proven loyalty offering. Selligent provides a flexible enterprise marketing platform to execute, analyze and optimize customer engagement across multiple channels and has a strong presence in Europe. Sailthru is a publisher-first marketing automation and personalization platform. By tightly integrating it with LiveIntent, Sailthru will elevate the Publisher Cloud into a unified stack for identity, messaging and measurement. This is mission-critical in a post- OpenAI and Gemini world and will work in unison with our generative engine optimization product.

And Liveclicker delivers interactive engagement and conversation through real-time dynamic personalization. Against our publicly stated M&A criteria, the transaction meets or exceeds each threshold. First, we have a disciplined plan to fully integrate the acquisition within 12 months with customer continuity the top priority. For Marigold's long-standing customers, the integration will be nondisruptive now and additive over time. We will also fully integrate the Data Cloud into their existing platform as a benefit. Second, the acquisition will be accretive to year 1 adjusted EBITDA and free cash flow and will lower our overall cost of revenue percentage. Further, the acquired businesses revenue has high visibility and will increase our subscription revenue base.

Further, the transaction price represents a less than 2x multiple on the acquired businesses revenue and less than 10x adjusted EBITDA. Third, Marigold's enterprise software business adds over 100 global enterprise relationships that will benefit from our one Zeta model, providing significant cross-sell opportunities. We will also have the opportunity to sell Marigold's loyalty offering into Zeta's 567 scaled customers. Fourth, the acquisition expands our EMEA footprint with entry into APAC and adds experienced customer and product teams in underpenetrated markets.

Further, we are incredibly excited about the people we are adding to our Zeta team through this acquisition. And lastly, we expect cross-sell and upsell synergies to be accretive to Zeta's growth over the next several years and incremental to our Zeta 2028 targets. This acquisition is a true win-win-win. Enterprise loyalty and messaging amplified by Zeta's data and AI, delivering high conversion, stronger retention and predictable profitable growth for brands while strengthening Zeta's subscription core.

Now let me turn it over to Steve Gerber, Zeta's President, to provide additional details on the business. Steve?

Thank you, David. Our strategy is to be the indispensable platform for enterprises applying AI, turning identity, intelligence and activation into predictable, profitable growth. This acquisition accelerates that strategy, adding 3 enterprise messaging franchises, a scaled loyalty business and deeper enterprise reach in EMEA and APAC. Our job now is execution, nondisruptive today, additive over time.

How we win comes down to 3 things: product, customers and integration. First, product. We will unite Zeta's data foundation, our proprietary data cloud, robust data model and real-time connectors with Marigold's loyalty and messaging products to sharpen personalization, expand cross-channel capability and lower total cost of ownership. Marigold's applications have operated without a native CDP. Zeta supplies the enterprise data foundation, persistent ID and real-time signals they plug into to expand scale and increase precision. Enhancements will be modular, methodical and seamless to the user with benefits visible quickly in consumer experiences.

Next, customers. Marigold's blue-chip base relies predominantly on retained use cases. These enterprises are ideal for our One Zeta playbook, introduce AI-powered acquire and grow use cases natively to deliver more value to the customer and higher ARPU for Zeta. Historically, when enterprises adopt a second and third use case, revenue per customer increases 2 to 4x over time. We'll use loyalty, amplified by AI as an on-ramp to expand and extend within existing enterprise customers, lifting LTV and creating durable paths into additional One Zeta motions.

Finally, integration. Our first principle, do no harm, then add incremental value by focusing on the points of least friction and greatest opportunity while retaining top talent and top customers, setting us up for transformational value creation for customers and for Zeta. The replacement cycle that began in 2023 has accelerated. AI-powered, not AI adjacent platforms are taking share by delivering better experiences for consumers and better outcomes for brands. AI is the spark, results are the fuel. That's how we turn 1 plus 1 equals 4 into greater opportunity for our teams and greater value for our customers. I'll now hand it off to Chris to share more on Marigold's scale and the deal terms of the transaction. Chris?

Thank you, Steve. Total consideration for the Marigold acquisition is $325 million, subject to adjustments. $200 million will be paid at close, of which $100 million will be in cash and $100 million in stock. Three months post close, an additional $125 million will be paid, of which $50 million will be in cash and $75 million in stock, subject to adjustments for working capital, indemnity holdback and other items.

As David mentioned earlier, the acquisition either meets or exceeds our disciplined M&A criteria. While the strategic and synergy merits discussed by David and Steve earlier make for a very compelling acquisition, I'm personally encouraged by many of the next level financial KPIs that further strengthen our business model, namely Marigold's revenue model and cost of revenue profile. Notably, over 90% of the acquired businesses revenue is subscription and highly visible, bringing Zeta's total recurring revenue base from approximately 50% to now almost 60%. From a cost of revenue standpoint, in fiscal 2025, Marigold's cost of revenue was less than 30% compared to 40% for Zeta in calendar 2024 and 38% year-to-date June 2025. With these 2 metrics in mind, our established playbook for use case expansion through One Zeta and channel expansion, along with our history of achieving integration savings makes owning this asset at the price we paid a highly favorable outcome.

We anticipate the transaction will close late fourth quarter 2025. And at that time, we will provide details on the expected revenue contribution for the fourth quarter of 2025 and full year of 2026. But to give some perspective of the business' scale, we expect the acquired business to contribute approximately $190 million to 2026 revenue with a mid- to high teens adjusted EBITDA margin profile. We also expect the transaction to be accretive to 2026 free cash flow. With integration synergies over time, we would expect Marigold's pace of adjusted EBITDA margin expansion to mirror that of Zeta, which based on our Zeta 2028 plan is approximately 150 basis points per year at a free cash flow conversion rate equal to or greater than ours.

And longer term, we expect the acquired business to have a margin profile in line or above Zeta. Given there could be variability in the close date, we're guiding analysts to not yet include Marigold in their 2025 or 2026 estimates until the transaction closes. We want to make sure that consensus estimates do not become a mixed bag of organic and acquisition-related revenue. So upon announcement of closing in late 4Q 2025, we will provide explicit guidance on the contribution for the fourth quarter of 2025 and full year 2026. As we have done with prior acquisitions, we plan to clearly break out organic versus acquired revenue for the first year post transaction, just as we have with LiveIntent.

Lastly, we're reaffirming our third quarter and full year 2025 guidance. In addition, the Marigold transaction is incremental to our previously issued Zeta 2028 plan, and we will update these targets as well.

With that, let me turn the call over to the operator for Q&A. Operator?

[Operator Instructions] Our first question is from Arjun Bhatia with William Blair.

Yes. Perfect. Congrats on getting the deal done here. I want to maybe touch on the product side a little bit. It sounds like, Steve, you mentioned, I think they don't have -- Marigold doesn't have a native CDP. So obviously, that integration will help. But in terms of what kind of other functionality that Zeta brings to the table that can enhance their offerings, can you talk about like do they have orchestration capabilities? Are they kind of omnichannel? Is that something that you'll also add into the equation? And then I'd be curious to hear just in terms of the maybe difficulty or how long it might take to integrate Zeta Data Cloud into the Marigold business.

Thank you, Arjun. Let me start, and then I'll kick it over to Steve Gerber. To be clear, their clients are almost exclusively one use case, which is retention. So in order to move them to acquisition and monetization, we would be fully integrating them into the Zeta marketing platform. As you know, Arjun, we see the CDP as the connective tissue. I think you're going to see a very quick, I would say, 90- to 180-day full integration with our CDP capabilities and our Data Cloud being fully integrated into the existing platform.

I think as we grow within, I would say, that same 6 months, we can get orchestration capabilities and omnichannel activation completely integrated. So I think it will take us a total of about 12 months to fully integrate at the MTA level and sort of the architecture level. But I think we can have our CDP Data Cloud and marketing activation capabilities fully integrated within 3 to 6 months. And because all of them are on one use case, I think it's just an incredible opportunity for One Zeta. The numbers that Chris has put out don't include any synergies at this point. It's what we believe the core asset is going to do. So we think there's upside from there, obviously. But I think it's going to take us some time to get in there and get a lot of this done.

Gerber, did you want to add to that?

No, I think you hit the key points. And these are big enterprises, Arjun. So this is one where we focus on continuity in the short term and opportunity in the longer term. And the way, as David said, the glide path is through our CDP and our data cloud that we are able to deliver results and use cases that they cannot today in a more seamless way. And it's through that proof that we'll be able to move more budget and more investment to us over time.

Arjun, just to finish, we really feel like the special sauce here in addition to the customers and the scale and the recurring revenue and the low cost of sales is the loyalty business. We're now going to be the loyalty provider to some of the largest North American and global enterprises in the world. And that data will train the algorithms that we have as proprietary to help those customers substantially better deploy their activation and monetization capabilities. So adding our AI, which, as you know, sits core to the platform and sits core to the CDP, we think is going to be a meaningful game changer. The other opportunity is adding that as a new product or a new channel, depending on how you want to look at it, to the 567 global enterprise clients we currently have today that are scaled. So it's -- we really see this as 1 plus 1 equals 4.

Yes. Perfect. That's very helpful. And David, you kind of touched on it there, but I was going to ask, it sounds like their business is very focused on EMEA, as you pointed out. But in your perspective, there's no reason that their product and their offering once integrated, can't be sold to your kind of North America heavy customer base. Is that fair or...

Well, 60% of their revenue is North American. So I think that it's fair to say, but it's probably not exactly accurate. I'm trying to make a joke. But this platform operates meaningfully in the United States, Mexico and Canada today, about 35% of their revenue is EMEA, which, by the way, is more than we currently have. So -- and we think that, that's an area that we can really scale and grow because it's a new opportunity to us to really have a presence there. But this business is tried trued platformed and operationally scaled in the United States today. So I think that makes it even easier for us to expand their clients to additional use cases and expand our clients to their new products.

Our next question is from Scott Berg with Needham & Company.

Hope you can hear me interesting acquisition. I guess 2 questions for me is, one, is there any customer overlap today? And then two, how do you think about the cross-sell opportunity? Is this more about taking your data products and some of the top of the funnel opportunities and cross-selling it into Marigold? Is that the bigger opportunity? Or do you think taking their loyalty products and selling that into the existing Zeta customer base is maybe the bigger opportunity?

Well, Scott, it's -- I would joke and say yes. We think it's an opportunity both ways. What I would say is the larger shorter-term opportunity is working with their brands, which include greater than 40 Fortune 500 customers and greater than 20 of the top 100 advertisers in North America today and extending their use cases from just retention to also adding monetization and activation. As you know, those are very big and very meaningful opportunities.

The beauty of adding loyalty to our clients is, yes, it's additional revenue and additional profit at very low cost of sales, but it also will immediately make the algorithms smarter for those clients by feeding all of their own loyalty data into our proprietary artificial intelligence model. So it will really accelerate the flywheel on helping them to do a better job creating, maintaining and monetizing customers. So I'd say in the short run, the bigger opportunity is adding use cases and then by definition, channels to their clients.

In the longer run, it's adding loyalty to our clients, if that makes sense, Scott.

Very helpful, David. I appreciate that. And then Chris, from a financial perspective, the only metric you really didn't talk about was maybe how fast the business is growing. How do we think about the growth rate of Marigold’' Solutions relative to Zeta's kind of organic growth rate this year without LiveIntent and without the political revenues? Just trying to understand if that will also be accretive to your growth rate or not as we think about '26 and '27.

Sure, Scott. Their business was flat to, call it, low single-digit growth, which was part of the reason why the multiple we paid was what it is. It's what we've been talking about in the last 2 questions that we've received around our ability to have the asset grow at our organic growth rate or faster, so call it mid-20s over the last 6 months, what we've been growing through the upselling of more channels and the cross-selling of the grow and acquire use cases.

So to be clear, Scott, one of their clients moving to a true One Zeta doubles this business. It's really -- I'm not saying we're going to get there overnight, and that would be over a number of years because they wouldn't move all of that budget at once. But this is a very meaningful opportunity. The fact that it was flat makes sense to me in that they had sort of rolled together 10 or 12 different companies. They hadn't really integrated them, and they were operating a small to midsized business division. They were operating an enterprise division. They were operating another division.

I think they did a really good job sort of holding everything together. But our strategy, of course, is fully integrate the asset, fully cross-sell, add all of the activation and monetization capabilities with, as you know, 14 to 15 channels that they can go across. I think you're going to see us really supercharge their growth. And I want to be clear, we see this deal as fully accretive to our current 2028 plan. So we see no slowdown in the Zeta business. I don't want anybody to even infer that. Our business continues to grow. You saw we reaffirmed Q3. We reaffirmed this year. We are very much on track for our 2028 plan. This will simply be on top of that.

Our next question is from Matt Swanson with RBC Capital Markets.

Maybe just a couple on the Sailthru, which you mentioned as part of your opening remarks being a really interesting product they have. And then also maybe just kind of the thoughts around the Publisher Cloud, which I know is also something we built out a little bit more after LiveIntent.

Yes. We're very excited about Sailthru. To be honest, we've known the Cheetah and Sailthru assets quite well for many, many years and have always admired both those assets and the amazing people, which, by the way, we've gotten to know Selligent better and the other assets better and, of course, are big admirers of theirs now and very excited about the people who are there and what we're going to do together.

When you think about the Publisher Cloud, it's sort of really starting to emerge at a very difficult time for publishers, right? You're looking in a world today where post Gemini and post OpenAI, the vast majority of questions that consumers are asking are now being answered on those platforms, whereas they used to be referred to publishers to answer those questions. So one of the biggest challenges publishers are having today is traffic and monetization. So now let's look at the chess pieces we put in place. Eight years ago, we bought Disqus, which is the world's largest commenting and sharing platform.

Over the last year, we fully merged that with LiveIntent, which is the #1 monetization engine for electronic newsletters and publishers. You're now going to add to that the #1 messaging platform for publishers in North America. So you're really looking at a publisher cloud that can meaningfully accelerate a publisher's traffic, can meaningfully grow their monetization and can do so at very high -- very low cost of sales to Zeta. So I'm very, very excited about the full integration of Selligent into the Publisher Cloud. I'm sorry, I meant to say Sailthru, I apologize. A lot of assets.

Our next question is from Zach Cummins with B. Riley Securities.

David, I just wanted to ask about the integration front. Zeta has been very successful in recent acquisition and integrations. But just with having 6 different products that you're trying to integrate here, can you talk about maybe some of the incremental challenges that could come with this in terms of integrating this into the overall Zeta platform?

As usual, Zach, great question. What I would say is we are exceptional at this. This is probably amongst the things we do best, which is buy small, really good technology companies with great people and great tech, but don't really have the type of sales engine and integration engine that we're able to add. So when you look at the integration, the integration, which will start with the CDP integration and the data cloud integration, which will move the AI as core to what they're doing will be quite -- I don't want to say simple because I'm sure my tech people would kill me for that, but it's something that we see as one of the faster moves.

The ability to then sort of connect the ZMP to the platforms in themselves will probably start with a proprietary API integration in and out, which will allow for activation quickly, but won't fully integrate probably for a number of months. If you look at it, we're going to do -- what I think we've also done in the past, this is not the first time we have bought businesses that had multiple divisions. One, loyalty will live with the Data Cloud, which will integrate there. Two, Cheetah will integrate with the ZMP, which ultimately will come together there. Three, Selligent will integrate into the Publisher Cloud. So that will happen there.

So you'll have the 3 largest assets from that perspective, we will integrate in. As it relates to Selligent, because we don't have a big platform in Europe, we're going to probably lean more heavily on them and use their technology and their people and then our relationships, which are global that we've not been able to take advantage of internationally because we didn't have the assets to really take advantage of our existing global customers in EMEA. That will be, I think, a very unique opportunity to bring our existing customers to them to scale them very quickly as well. So we're sort of looking at it in 4 or 5 different parts. And when you break it into those parts and you build the multiple work streams, it's easier to integrate them when you think of it that way.

Steve Gerber, would you like to add to that?

No, I think the main point is the playbook that we have is something that is repeatable here, making sure that we do this in phases in a way that is nondisruptive for the customers while we're bringing in the components of Zeta that add incremental value. When we start with the notion of the data foundation, which is our proprietary data, combined with the customer data wrapped around our AI, it's a glide path to a faster implementation and we're able to show impact more quickly. The 3 tracks that David laid out, we have expert teams ready on day 1 to start with this. We've already got the playbooks laid out, and we're working very closely with the teams from Marigold to make this happen as well.

Our next question is from Elizabeth Porter with Morgan Stanley.

I wanted to follow up on your comments about just leveraging the EMEA customer base. As you're looking to break into this market more aggressively, is there anything that is required from a data center, data sovereignty perspective or investment in order to capitalize the opportunity? I'm sure there are some assets that you're inheriting, but would love to just hear more about what it might take to kind of get further into this EMEA opportunity.

Thank you, Liz. And I thought you would be particularly happy about the 90% subscription revenue here on multiple year contracts as we've heard your desire for us to get more into that. The -- I would start by saying no. We have all of the assets we currently need in Europe. I would say, quite frankly, that the existing business has maybe even overbuilt for what they're currently doing from a capacity perspective. So I think we have a long runway as it relates to the assets that we are getting that have been built out from an infrastructure perspective there. And remember, we are still in Western Europe already. We already have hosting assets in Western Europe.

We already host our algorithms in Western Europe. And we're already fully in compliance with the EU and CDPR -- I'm sorry, CDPR -- with GDPR in Europe as a data platform. So we host all of our clients' data for Europe in Europe, it does not come back to the United States as we're supposed to do. The ability to integrate our existing hosting assets with the data cloud and the artificial intelligence that we run natively in Europe into their platform might take a bit. As you know, that's not something we'll probably be able to turn on overnight. But I think that's something that we will be able to get to early next year, as I think Steve has pointed out a few times. These are very large global enterprise customers. Our single biggest goal is to not disrupt them during the peak period of year for their businesses. So we plan on adding the Data Cloud and adding CDP capabilities quickly, but really not doing anything that would move anything around until early next year, if that makes sense.

Got it. And then just on the large, very global enterprise customers. Usually, those large enterprise customers have more of a direct sales motion. So anything that you're inheriting from a go-to-market kind of seller side that we should keep in mind with the acquisition?

Yes, we're picking up a great sales force and picking up incredible people. My understanding is almost all, if not all of this revenue is direct to enterprise.

Yes, that's exactly right, David. I think when we think, Elizabeth, about some of the kind of next level financial metrics that come with the deal, many of which we'll learn a lot more on our pathway here to closing in late 4Q. But we don't have to learn a new go-to-market sales motion. The sales team at Marigold, just as Zeta's sales team every single day, as you noted, is selling into these enterprises with proven budgets, very, very large scale. So our sales motion is consistent. The visibility that we have into our revenues increases, as David mentioned, call it, roughly 50% of the revenue today being recurring, now approaching 60% with the addition of Marigold.

From a COGS perspective, they're at sub 30%, whereas, call it, Zeta is at right around 40% today. So really nicely accretive there. Obviously, all of what we'll be selling through their products will be direct as well, should only further help our overall mix. And then this is right in our integration sweet spot. Our genesis was in e-mail and our ability to take platforms that have not yet been integrated and get them into the ZMP quickly with teams deeply embedded is what we do really, really well.

Yes. We're -- as you can tell, Elizabeth, we're very excited about this.

Our next question is from DJ Hynes with Canaccord Genuity.

Congrats on the deal. So David, the grow and acquire cross-sell story is very clear. Where I have a little less visibility is on the loyalty side and what your 567 scaled customers are already doing there today? Like is this still a white space opportunity? Is there incumbent tech in there that needs to be replaced? How many of those customers need to run loyalty programs? Any color along those lines would be helpful and interesting.

That's a great question. It's certainly not white space, to be honest. I think taking them from 1 use case to 2 or 3 use cases is white space and can be a meaningful scaler to our business quickly. I think as it relates to loyalty, by definition, our scaled customers are scaled. They're big businesses. They're either going to be doing this internally, which I think is an easier sale or they might be working with one of the other loyalty platforms out there. I think the way we will bring this to bear is we will, once again, take a page out of everything we've done. We will be able to provide that service of loyalty solutions to our enterprise clients at a substantially lower cost than they are currently paying to existing stand-alone vendors.

Second, it will make the algorithms that are figuring out the intent-based score for their current use cases, whether it's acquisition, retention or monetization, substantially smarter. And you know this better than anybody, DJ. Today, for every dollar that is invested into our software and data, we return between $5 and $7 in revenue. My shorter-term goal, I shouldn't say short, my goal is to, on a sooner versus longer perspective, get that to $10 for every dollar they invest. Clients who move their loyalty over to Zeta for those use cases are going to see those types of returns because that's how much smarter the algorithms will get when they start to get the SKU level data, not just the credit card basket data, which is what we get from most of our partners today, if that makes sense.

No, it does. It makes perfect sense. And then, David, you hit on this a little bit, but I just want to kind of hammer the point home. Investors can be at times a pessimistic bunch. One of the questions we often get asked when M&A like this hits is whether, in this case, Zeta is doing something like this to mask any deterioration in the core business. You guys...

Yes. I would say that's why 3x, and I will now say it a 4. That is not the case. This was an opportunistic deal for us to pick up some of the greatest companies in the marketing technology space at a very reasonable cost. To point out, we are paying on the existing business, less than 10x EBITDA and below 2x revenue. So I think this was a unique opportunity to pick up incredible tech, incredible customers, incredible people at a reasonable cost, but I want to be clear. We are reaffirming Q3. We are reaffirming the year. We are reaffirming our 2028 plan, and this will be accretive to that. And as you know, DJ, our 2028 plan requires a 20% organic compounded growth rate between now and 2028. This deal will be on top of that.

And DJ, just like we did with LiveIntent, we'll continue to break out once we have the final details post the closing. We will provide to you and our investors not only the fourth quarter stub revenue, whatever ends up being depending on the close date or if it goes beyond that, we don't expect it to, but it could as well as the quarterly breakdown of 2026 revenues, and we'll break that out as a separate line item in our guidance as well. So just, again, full transparency, the organic business continuing to be at the rates that David said.

Looking forward to see you guys at Zeta Live in New York next week.

We are very excited. Obviously, this has been a busy few weeks for us leading up to this and Zeta Live next week, which is shaping up to be the best event I think we'll have ever hosted.

Our next question is from Richard Baldry with ROTH Capital Partners.

I'm curious to what degree any of the component pieces you're buying could be leveraged by the global agencies that you've had a lot of success with in the last couple of years?

Well, I always love when you're curious, Rich, so I appreciate that. Absolutely, yes. So I think the loyalty offering, in particular, will be very interesting to a number of the large holdcos. 1 or 2 of them have their own offering, and they're going to continue to focus on theirs, which makes total sense to me. But I think that there's a meaningful opportunity to do that because when you look at how much smarter the algorithms get when they're ingesting that loyalty data, it is really, really exciting.

I think that will be sort of the biggest one in the U.S. Now I think in Europe, it's going to be very interesting because, as you know, all of our large holdco clients are also in Europe. This is going to give us a really supercharged team over there. And Selligent does have omnichannel capabilities today, which we'll be enhancing. They just have not been selling them to any of the agencies. So I think this will be a meaningful opportunity to grow our agency relationships, which have flourished in the United States and Canada. I think it will give us a meaningful opportunity to really supercharge them in EMEA.

And last one for me would be why the 2-step payout period, the 3-month delay, sort of curious what the driver behind that is? You clearly have enough cash on the balance sheet to do this in one step.

Yes. It's not about the cash. I think the real answer here, and Chris said it subtly in his prepared remarks, there's going to be a number of adjustments that could drive that number down based on working capital, based on the strategic plan around transition. I've always felt it's easier to pay somebody less if they don't deliver what they say versus clawing it back. And this was really my insistence on making sure that you have the ability to do that.

I am not questioning the Marigold team in any way, shape or form. It's just we haven't closed the deal yet. And until we get the deal closed and then you've got 2 or 3 months to look at collections, working capital, free cash flow, which, as you know, is very important to us. There'll be adjustments either up or down in that. That was really the main function. Traditionally, we've structured our deals. I can't remember a deal we've done without some level of structure. Normally, they would include some type of either an earn-out, which we would be able to claw back from or some type of a note payable. In this case, in order to get the deal done at the multiples we paid for it, they needed the money to come a bit faster. And this was the happy medium we came up with, if that makes sense.

Got it. And maybe one more. Because there is a stub business being left behind and I think in the SMB space, are a lot of the sort of senior exec people who are not necessarily sort of VP or presidents running the divisions you're buying, are they being left with that entity so you kind of don't have the drag of some of those salaries coming across the take?

So what I would say is they were run as separate businesses already, although we're not taking any of their sort of corporate SG&A to your point, which we were happy about. The top 20 employees of this asset that we're buying, Marigold Enterprise, we are wrapping our arms around. We're super excited about them, but we didn't end up taking a lot of what you would have considered corporate overhead because of that, and we were pleased by that.

Now we're also big fans of Michael and his team, who we think are going to do an exceptional job in the SME space, and we are, of course, rooting for them. They've kept the people they need to run that business and most of the corporate overhead.

Congrats.