# Building GTM AI Agents: Lessons from Deploying to 6,000 Users — Sait Izmit, Snowflake AI Engineer · 2026-08-26 Sait Izmit of Snowflake says winning over 6,000 go-to-market users comes down to quality over coverage: he wrote 150 sales questions before testing, accepted 50% first accuracy, and chose 50 questions at 95% over 100 at 70%. The Snowflake Cowork agent, live since September, has answered over a million questions (~40,000 weekly); 60% of data arrived post-launch, and it now spans 15 semantic views, 85 tables, 3,000 columns, MCPs, and 20 skills. After pilot and a 600-user 10% beta with 70% retention, GA showed only 20% of the org tried it, so Izmit spends 60-70% of his time on demos and sales meetings. He warns the wow factor collapses quickly, so teams must move from data chat to workflow automation, build fast with today's stack, accept rearchitecture, and mine logs for feedback loops. ## Questions this episode answers ### What did Sait Izmit mean by quality over coverage when building Snowflake's GTM assistant? Sait Izmit wrote 150 questions from the sales process before trying the agent; the first run scored 50% accuracy. The team chose quality over coverage: answer 50 questions at 95% rather than 100 questions at 70%, because a chat box is judged on its first five questions and trust is lost overnight. [4:42](https://aiengineer.podhood.com/4edba0f2-fd48-4d5f-b4eb-ca0179c62941?t=282000) ### How did Snowflake phase the launch of its GTM assistant? Sait Izmit used a phased launch: a pilot to prove accuracy with AI-native users, then a 10% beta of 600 people to prove the MVP and retention, exiting with more than 70% retention rate, then GA. He adds that only 20% of the organization may try the product, so he spends 60, 70 percent of his time on demos and sales meetings. [5:36](https://aiengineer.podhood.com/4edba0f2-fd48-4d5f-b4eb-ca0179c62941?t=336000) ### What is the 'collapsing wow factor' in AI assistant adoption? Sait Izmit explains that after four to six months, users get used to talking to their data and start complaining about missing features; the wow factor collapses. You must keep raising the bar by moving from talk-to-data to workflow automation and team-built skills, otherwise users will switch to a better product overnight. [9:19](https://aiengineer.podhood.com/4edba0f2-fd48-4d5f-b4eb-ca0179c62941?t=559000) ### Is it worth waiting to find the perfect architecture before launching an AI agent? Sait Izmit advises against chasing the perfect architecture. He launched to 6,000 people using a nine-page agent instruction and a Google Doc, then added skills, MCPs, and more; 80% of the original architecture changed. He recommends building fast with today's stack and being comfortable with constant rearchitecting. [11:45](https://aiengineer.podhood.com/4edba0f2-fd48-4d5f-b4eb-ca0179c62941?t=705000) ## Key moments - **[0:00] Intro** - [0:33] Snowflake's internal GTM assistant has answered 1M+ questions and 40,000 a week since September, says Sait Izmit - [1:26] At Snowflake, half of ~10,000 employees are in sales, where reps juggle 15 tools and 1,000 accounts each, says Sait Izmit - **[1:31] The why** - [3:17] Sait Izmit: 'User trust is earned extremely hard and is lost overnight' — first five chat answers decide if a rep returns; winning back costs 10x - **[3:24] Trust** - [4:05] Before trying the agent, Sait Izmit wrote 150 sales-process questions; first tests hit 50% accuracy, so the rule became: 50 answers at 95%, not 100 at 70% - **[4:16] Quality first** - [5:06] Snowflake's GTM agent now has 15 semantic views, 85 tables, 3,000 columns and ~20 skills; 60% of data was added after launch, says Sait Izmit - [5:36] Snowflake rolled out its GTM assistant in a pilot, then a 600-person 10% beta that had to exceed 70% weekly retention before GA, says Sait Izmit - **[5:46] Phased launch** - [7:11] Two weeks after GA only 20% of Snowflake had tried the GTM agent — Sait Izmit says AI projects fail at activation, not technology, and spends 60-70% of time on demos - **[7:14] Change management** - [8:53] Sait Izmit: the 'collapsing wow factor' hits 4-6 months after launch — talking to your data becomes baseline, so agents must keep raising the bar - **[8:56] Wow factor** - **[9:44] Automation** - [9:44] Go-to-market AI evolves from talk-to-data to automation to team-built skills; Sait Izmit warns staying at stage one gets you disrupted in a month or two - **[11:49] Rearchitecting** - [12:26] Snowflake launched its 6,000-user GTM agent with a 9-page agent instruction in a Google Doc; 80% of today's architecture differs from the original PRD, says Sait Izmit - **[14:09] Feedback loops** - [14:09] Sait Izmit: LLM-classified logs on 1.2M questions reveal feature gaps in real time and auto-generate battle cards to feed back into the agent - **[16:35] Takeaways** - [17:21] Sait Izmit: 'Every time people are happy, you should be paranoid' — always plan what to show users in a month or two to keep the wow factor - **[18:36] Q&A** - [18:48] Q: Is Snowflake Intelligence the layer the GTM agent is built on? A: It's Snowflake Cowork, Snowflake's no-code agent platform, says Sait Izmit ## Speakers - **Sait Izmit** (guest) ## Topics Agent Commerce, Enterprise AI Solutions, Developer Tool GTM ## Mentioned Salesforce (company), Snowflake (company), Confluence (product), Cortex Analyst (product), Cortex Search (product), Cortex Sense (product), Gmail (product), Jira (product), Slack (product), Snowflake Cowork (product) ## Transcript ### Intro **Sait Izmit** [0:13] Hi everyone. So, I think I'm one of the last speakers that is standing between you and the long weekend, so I hope I can get your energy levels up. Um, so I'm responsible for our internal AI tools for our sales team, and the reason I'm here today is indeed, like, we launched our internal go-to-market assistant, uh, in September last year. It answered more than 1 million questions so far. We have roughly answered 40,000 questions a week. Um, and we are the customer zero for a lot of Snowflake products, so this is built on Snowflake cowork. Um, and I meet a lot of customers every week, okay? So I meet a lot of enterprises, Fortune 500 companies, and then they're all trying to build similar things, and they all struggle,right? So, and then I end up, like, having this discussion with them all the time. Like, they ask, like, "How did you guys do it?" And then we share our best practices. So I will try to share some of those things with you. Uh, I'm told that I need to have some code in my presentation. I don't, but I will try to show you at least some architectural diagrams, just to make it more interesting for the engineering audience. Uh, but let's jump into it. Um, I think before we start, like, I think I already I was watching the other presentations. Like, I think everyone tries to give their interpretation of, like, you know, why are we even building things for go-to-market. Okay? So this is how I explain it to family and friends. So let's take Snowflake. Okay? So we are a company of, like, you know, close to 10,000 people. So if you look at our organization, almost half of our basically workforce is sales,right? ### The why **Sait Izmit** [1:39] And what are they responsible for? They are responsible for revenue generation. What do they struggle with? And I introdu you know, I talked to a lot of customers. It's very common, you know, everyone's data is siloed. We work with a lot of first-party data, a lot of third-party data. It's all locked down in these, like, SaaS tools and things like that. And literally, we have, for example, like, reps who are using 15 different tools, not because they love the UI of those tools, because every tool has a different data point, and then they end up stitching all of that together in spreadsheets and running it there,right? And the data is endless. Like, we have reps who have 1,000 accounts assigned to them, 1,000 customers. They have to stay on top of their recent news, what's happening with their consumption, did they get in support tickets recently, what was their latest earning result, everything. There's no it's not a single human on this planet can stay on top of that much data. And then they need to do that 30 times, 40 times a day,right? So what does AI offer for them? It offers data democratization. No more, like, thousand dashboards,right? No more access to analysts. Like, you know, um, it offers automation possibilities for them,right? It frees up their inbox. It offers tool consolidation. No longer 15 different tools that I need to work for. And that brings productivity savings. It frees up your time,right? You can use that time on other things. It helps you become a better seller. You are more effective with your customers. And that translates to business results. You can cover more of your book. You know, you can have better win rates. Uh, you can have shorter deal cycles. And ultimately, what everyone cares about, you can get incremental revenue. Okay? So that's the reason why I'm I'm working for, you know, making the go-to-market organizations more effective. But there's a catch. These are non-deterministic systems,right? And I run into this problem every time with users. I see many, many, many AI projects fail, and then it fails on this principle. User trust is earned extremely hard and is lost overnight,right? ### Trust **Sait Izmit** [3:38] So at the end, what you are doing is you are putting a free-form chat box there,right? And people will come in and they will ask any question they can think of. If they like what they see in the first five questions, they come back. If they don't like what they see, it's 10 times more effort for you to win them back, if you can ever win them back,right? So we have a saying in our team. We say quality is P minus one,right? And that's basically we take that very, very seriously. So one of the things that we really cared about is when I first joined the team, you know, the team had all these, like, data sources connected from our top dashboards. ### Quality first **Sait Izmit** [4:17] We they had a knowledge assistant built into it and so on. We had three lines of agent instructions. And then before I even tried the agent, I opened the spreadsheet, I took the sales process, I wrote down 150 questions. And then the sales our engineering team was like, "What are you doing? We don't have that data in the agent." And I was like, "It doesn't matter. These are the questions your sellers are going to ask,"right? And then we run our tests, 50% accuracy, you know, like, everyone's depressed and so on. So we said, "Okay, let's make sure that we don't go for coverage, but we go for quality,"right? We don't want to try to answer 100 questions and get them 70%right. We want to answer 50 questions but get them 95%right,right? Because with that, you get a first impression, good first impression, you build the trust with them. And then rather than being in that boat of, "Oh, this thing doesn't work," people are like, "Oh, this thing is awesome. Can I get more of that?"right? So we started small, and 60% of the data we actually added after the launch, after the six, seven months post-launch. Today, if you look into our agent, I mean, it's not a small agent. We have 15 semantic views, 85 tables, 3,000 columns of data. We have, like, five to six different MCP connections on it, you know, close to 20 skills connected to that, and so on and so on,right? So it's a huge system that we are managing in here. And then you cannot just launch these things to everyone,right? So we said that, "Look, we need to do this in a controlled way because we want to make sure that we earn that first five questions. We don't want to burn our bridges in that first five questions,"right? So that's why with every product we do, we do a phased launch. ### Phased launch **Sait Izmit** [5:49] The first one is a pilot. The goal of the pilot is to prove the accuracy, prove the quality,right? You get your top, you know, AI native folks in the organization who are eager to work with you, give you feedback, improve the product, make sure that you got the rough edges through them,right? And then after a couple of weeks, you come to a point where it looks like, "Okay, those rough edges are more smoother now," okay? Then you go into your beta launch. We do a 10% beta,right, with 600 people. There, you are looking at, "Do I truly have a basically a minimum viable product? Is the MVP really there,"right? And what will happen is that you will start getting tons of requests. Can you connect this data? Can you connect that data? And everything. And then you are looking at, like, where are the actually the concentrations happening? Because that means that if you don't get those things in, you don't truly have an MVP,right? Then it's not going to work for their daily workflows. And then at that stage, you're also trying to prove, "Are they coming back,"right? So the things that we really track there is basically like, "Okay, how many questions they're asking and everything, but what is the retention rate?" So we exited, for example, that at, like, more than 70% retention rate that the weekly active users were coming back. Okay, now we're in a good place,right? We have confidence on the accuracy. We have under confidence of the basically the coverage of the product we have, and people are coming back. Okay, now let's go to GA, and then you launch the GA. But then you have your next problem. So I know that this is a technical conference, but this is also where a lot of these products fail. It's basically how do you derive change management? So you launch your product, you are two weeks into the launch, and then you are here, and all your management is, like, disappointed or frustrated. ### Change management **Sait Izmit** [7:30] "Why aren't people using this? Why are numbers are very low,"right? And I show them this graph. I say that only 20% of your basically organization actually tried the product. I cannot do anything. It's not the product's fault if people are not even taking five minutes to try try the product,right? If they try it and if they don't come back, okay, that's my problem,right? But if they don't try it, then we have another problem. So the first and I've been, you know, I've seen this with many, many sales organizations in my past life as well and so on. Usually, this is a couple of month process. And then you significantly invest in basically change management, in activation. I will spend 60, 70 percent of my time in sales meetings, giving demos, building dashboards, which teams adapted, you know, shaming the, like, the managers whose team is actually doing good, getting sponsorship from sales leaders to basically, like, make sure that they pro you know, they push their people to try these things and so on. And then ultimately, that gets your blue line up, and then your questions are start coming up, and then your focus can shift into, "Okay, how do I drive more depth,"right? And I want to really, really emphasize this because if we hadn't done this, we would probably be doing, you know, half of where we are today. So it's a very, very important part. And then as engineers, if you spend all your effort, you want to have a good product, make sure that the activation and the change management is, like, lined up, like, post-launch of the product as well. Now we run into another issue. Okay, we are, let's say that four to six months down the run,right? What happens is you successfully launch the product. You are first, like, rock stars in the company,right? People literally show you on the corridor, like, "Hey, your product is awesome. ### Wow factor **Sait Izmit** [9:08] We can talk to our data now. We don't need to wait on the queue to, like, you know, get access to, like, analysts to answer our questions in every two weeks and so on,"right? And after a couple of months, they start coming back to you with frustrations. "Hey, I cannot do this in the product anymore,"right? "I, I would like to " I mean, I saw this other AI product that does this and so on. This is what I call the collapsing of the wow factor, okay? So initially, you are cool, but then and that becomes a habit,right? You basically change their habit and it becomes standard for them. Now you need to raise the bar again. So the journey that we usually see with the sales teams is, like, you start with talk to your data. How do we get you out of those, like, you know, hundreds of dashboards situation, dependency to the analyst? And then first, we basically, like, democratize the data for you so that you can basically talk to your data. Then the next wave comes with all the MCP connections,right? ### Automation **Sait Izmit** [9:58] All the integrations that you are building. Now it becomes, like, automate my workflows. We literally have now sellers who are going to use our agent basically to monitor their inbox, then monitor their Slack channels, you know, keep track of all the customer questions coming about, like, product questions, how use the agent to draft responses that save that in Gmail, review them afterwards, like, send those things out,right? Or they automate their, like, outreach workflows and so on. Okay, that's great. Now I became an orchestrator,right? I'm basically automating my work workflows. Then the next thing you see start happening is teams, they get these, like, you know, tool democratization, this empowerment coming to them,right? Because historically, a lot of these go-to-market teams, they have been always in the backlog of someone, backlog of, of an IT team or, like, trying to get a SaaS budget to then get a vendor on board to actually, like, enable something. And now, all of a sudden, they're able to build team skills. They're able to build, like, you know, custom dashboards that are basically, like, fully, you know, optimized for what their team needs, are able to, like, deploy applications, automations, alerts, and things like that,right? And then there comes a phase of hyper-personalization,right? Everyone is able to now, like, get everything personalized for them, not only for themselves, but also for their customers with living context of customers, contacts, and things like that. I think the main message I want to give here is if you just do the first stage and if you just wait there, you will get disrupted in a month or two,right? Because now you already raised their expectation that already became a baseline, and then they will find another product that does better than you. Andright now, the switch is very easy. They're going to just switch overnight, okay? So you need to keep iterating. You need to keep that wow factor. And then you cannot just rely on the fact that, you know, what I built so far is going to stay cool forever. And the next thing is how do you deal with basically the changing technology? So I talked to a lot of customers, and then, you know, sometimes you run into these customers, big enterprises, very big brands, and then they are still trying to chase that perfect architecture. ### Rearchitecting **Sait Izmit** [12:00] They are trying to, like, test different frameworks. They are trying to see how the, you know, the technology is maturing and everything and so on. But the thing that they don't do is they don't build, and then they don't launch, and they don't learn,right? All these blue boxes that you see here, those are all the things we added after the launch,right? When we literally first launched the agent, it was a nine-page-long agent instructions. It was a couple of Cortex analyst tools, semantic views. It was a Cortex search service for our unstructured data. And we were managing the agent instruction versions out of a Google Doc. That's how we launched it to 6,000 people,right? Now we realized, "Okay, it's not going to work out. Let's figure out CI/CD. It's not going to work out. Let's figure out our basically eval infrastructure with all the, like, the unit tests, routing tests, and everything,"right? Then we start basically, like, coming to a point where, for example, we were creating all these, like, business processes and workflows. We couldn't fit them into the agent instructions anymore. And then the skills came, and we were like, "Oh, perfect. Let's build a skill library," you know? Then the MCPs came. Perfect. But now, like, we had to put a bunch of other instructions to basically orchestrate that. We hit the limits on the agent instructions. What do we do? Okay, let's do the progressive disclosures,right? And then user memory comes, task scheduling comes. We want to go beyond the chat screen and then, you know, chat interface and start doing the Slack interface and things like that. If I look at the PRD and the architectural diagram we wrote in the beginning of the project, if I compare to this architecture we have now, 80% of it doesn't match, okay? So, like, if you look at our sprints, like, maybe 60, 70 percent of the work we are doing is adding new features, improving quality, and all kinds of things. But 30, 40 percent of the work is that we are constantly rearchitecting with the new technology. So this is the time where, like, you need to get your hands dirty. You need to run with the new technology. And then you shouldn't be, like, you know, too much tied to your architecture. You should be okay to, like, pivot very easily so that you can basically double down on these, like, new capabilities and things like that. And then the longer you wait, the more, you know, you lose towards your competition because if your competition is doing these kinds of things, like, three, four months ahead of you,right, that means that they're also getting more customers. Um, last thing is I would really, really recommend investing in your logs, okay? Because they create the basically the feedback loop. So first of all, technically, it's very fun, okay? So you basically use LLMs to, like, classify your logs and things like that. ### Feedback loops **Sait Izmit** [14:24] As I said, like, we have 1.2 million questions. We get 40,000 questions every week. It's technically very fun. You know, how you do that at scale without breaking the bank and so on. You know, our data scientists love working on those things, and then they really experiment with new things. But as a result of that, what we get is we get a very extremely detailed breakdown of topics and, you know, things that we are having. I'm just showing you the top category categorization level there, but then basically, we are able to track, like, you know, what kind of questions they are asking. We are able to break down each of those categories to subcategories. You know, we are able to get, like, detailed example questions, this and that, and so on. All good, but how do we use that? Then we start creating the basically the feedback loops,right? I know I mean, I still interview, of course, users, but now I see in real time what my feature gaps are. I'm clearly seeing what people are asking, and we are not able to answer or where we have, like, a quality issue where they're swearing at the agent or, like, repeating their question so that we see where to improve. For sales enablement, it's a gold mine. Let's say that we launch a new product. Usually, you know, they would need to interview maybe 100 sellers a week to be able to understand, like, how basically the, you know, the topics are changing, where there's gaps in terms of, like, knowledge documents, battle cards. I see that in real time in a minute or two by just asking an LLM question. And then we can then, you know, connect to Confluence. We can connect to Jira. We can connect to Slack channels. We can ingest the PRDs, and in a couple of minutes, we can actually, like, you know, generate battle cards, sales enablement document, and then feed it back into the agent,right? I mean, you cannot do that kind of a, like, a feedback loop with humans,right? So then you can basically automate these kinds of things. Um, within the sales organization, there will be different teams that are trying to connect each other. They are trying to maybe target similar accounts from different angles. They don't know about each other. We do. We are now able to ping them, and then we are able to basically do matchmaking,right? I'm just giving you a couple of examples, but this is also one of those areas where, like, you start building your AI platform, you start building your architecture. The first features are difficult to get out. The next ones are easy. And then once you start tapping into your logs, this, this, like, hockey stick exponential thing actually starts happening, and it's magical. So if you were to take a couple of things from this talk, like, quality over coverage. I'm very, very, like, religious about this. If you go for the coverage, you are going to shoot yourself in the foot, okay? ### Takeaways **Sait Izmit** [16:50] Change management. A lot of engineers don't think about this,right? A lot of these AI initiatives, they don't fail because there's an issue with the technology. There's an issue with that, as assuming you did the first one,right? Right? So they fail actually in activation. So make sure that you have a plan for that, especially in larger organizations where we are dealing with, like, 6,000 go-to-market users,right? Um, again, don't forget this concept of collapsing wow factor. You cannot stay where you are. You cannot just say that, "Hey, I did an innovation. I'm going to serve that for a year." You know, every time people are happy, you should be paranoid. You should be like, "Okay, what am I going to show them in a month or two now? How do I basically keep that excitement going on,"right? Build fast with today's stack. Like, don't try to invest in these, like, you know, super like, you know, architectures and have these, like, six, nine months of long projects and things like that. How do you turn around these things in weeks, days, and so on? And just be comfortable with the fact that you are constantly going to be rearchitecting. That's fine,right? Just don't over-invest in the current architecture. Just make sure that you keep your, like, flexibility out there. Um, and then the feedback loops. I think that's what kind of, like, gives you really that, like, you know, the incremental part of, like, that hockey stick exponential part of the thing. Um, we constantly publish, like, blog posts, I mean, where we kind of, like, try to have our, you know, learnings shared with, uh, our customers and so on. Like, we have blog posts on, like, how we do agent instructions, how we do our structured data with semantic views, you know, how we basically build our rack-based, like, knowledge assistance, the non-technical side of the story, like, how do you drive change management and so on. So feel free to check those. Um, and yeah, I think that's the end of my talk. ### Q&A **Host** [18:36] We have time for one question. Okay, there you go. **Guest** [18:48] Thanks for the talk. Um, I don't know if you already said this, but I saw in the, the titles of the article, Snowflake Intelligence. Is that an underlying context or layer that the tool or system you built was on top of, or was that the tool itself or something else? **Sait Izmit** [19:05] Yep, Snowflake Intelligence. We renamed that to Snowflake Cowork a couple of weeks ago in our summit. That's basically our no-code agent platform that we basically have available for our business users. Um, I mean, the advantage of that is that a lot of these tools around, like, you know, uh, you know, Cortex, uh, Analyst or Cortex Search or Cortex Sense, a lot of those things are basically come out of the box. Uh, we made a strategic choice for our internal thing where we said that, look, it is important that we bring all our data together, and we do that in Snowflake. We bring all the first-party, the third-party data, all the Salesforce data, everything, the call transcripts, and so on, all together. And then these agents then can basically, uh, basically inherit a lot of the, uh, role-based access controls and so on. And then literally, you can deploy these agents without writing a single line of code,right? Um, and then, you know, you don't need to worry about the UI. The chat UI comes out of the box and so on. And then we have been the customer zero of that, like, internally to build this ourselves. And then, you know, our customers are able to go and then build similar things, uh, basically on Snowflake Cowork platform as well. And it comes with the guardrails and things where you don't really need to worry about them going very, you know, crazy on, you know, what data sources to do things and so on. So we are able to do a lot of curation. We are able to do a lot of security guardrails in there as well. **Host** [20:21] Thank you. **Sait Izmit** [20:22] Thank you. --- This library is powered by PodHood (https://podhood.com), the podcast website platform.