How this CEO turned 25,000 hours of sales calls into a self-learning go-to-market engine | Matt Britton (Suzy)

[00:00] With my company, my sales team was consistently telling me that they just didn't know how to find anything. They didn't know how to find what customers were interested in. You had a bunch of salespeople. They said, I need more information to serve our customers better. You realize you had 25,000 hours or something of recorded customer calls, which are the perfect source of truth for how customers want to be interacted with. You're going to show us a zap now that takes a single recording and does a bunch of stuff. [00:30] can I create a feed for Zapier so he knew the call ID of each new call as occurred. So the first step is essentially a trigger where a new call comes in. It'll basically scrape the information from Gong and one of the things Gong will give you is that call ID. So that appended to the URL essentially is all I needed to give browse to be able to go to that URL and say but essentially [01:00] of hack it together. I love a CEO that knows how to build it. I love a CEO who knows that no problem is not solvable. Welcome back to How I AI. I'm Clara Vau, product leader and AI obsessive here on a mission to help you build better with these new tools. Today we have Matt Britton, CEO of Suzy. Now, normally we show two or three workflows, but today Matt's going to show off the one [01:25] mega workflow that rules it all at his company. He's going to show you how to take a single asset and turn it into tons of go-to-market goodness.

[01:35] from emails to customers, enriched data sources, and even marketing assets that can be used to source more prospects [01:41] that are going to be successful with your product. [01:44] Let's get to it. [01:45] This episode is brought to you by Brex. If you're listening to the show, you already know AI is changing how we work in real practical ways. Brex is bringing that same power to finance. [01:58] Brex is the intelligent finance platform built for founders. With autonomous agents running in the background, your finance stack basically runs itself. Cards are issues, expenses are filed, and fraud is stopped in real time without you having to think about it. [02:28] already runs on Brex. You can too at brex.com slash how I AI. [02:36] matt thanks for coming on how i ai i'm excited because [02:41] As I was saying before we started the show, we get [02:44] vibe coders left and right. And I know we're going to talk about some custom software that you built, but we just do not get enough on the go-to-market and marketing side of AI automation. So I'm really excited to show what you have to share. So really appreciate you joining today. It's time to be here. So you and I both really love AI. [03:04] Zapier. And I have to ask, even before the age of AI, was this a tool that you relied on? Why has this specific software become kind of the backbone of so many of your AI-based automations? So I've always been fairly technical, but I've never been a coder. I've

[03:21] I sold the first ads ever on Facebook directly to Mark Zuckerberg and Edward Severin in 2005. I bought some of the first Google keywords ever to exist right when I started my business in 2002, my first ad agency. So I've always loved sort of ad tech and getting like, oh, I didn't understand how these tools work. But at the same time, I've never been an engineer. And as I wanted to get more sophisticated in the tools and solutions I've built for various companies that I've run, I've needed to not just use one tool, [03:50] like AdWords, but multiple tools to stitch things together to be more efficient. And I was turned on to Zapier, like most other people, just do a Google search. And I think I wanted to connect, you know, leads that were coming in through my website to some type of flow, where it automatically emailed the person who signed up. And then I just kind of start to dive into it. But to your point, Claire, it wasn't until Zapier integrated AI. [04:14] when kind of my mind just became blown in terms of what's possible. Okay, so you're going to show us how you take... [04:20] a single asset and I won't spoil what it is and turn it into basically a full suite of activities across your marketing, sales, internal company work. So why don't you pull that up and show us what you built? [04:32] Before I pull it up, I guess I should say that [04:34] I think it's all about figuring out what problem that you want to solve. And I think with AI in general, people get so overwhelmed with just the amount of tools and the rate of change that they just find themselves kind of playing around with all these tools, trying to get. [04:48] to the point where they feel like they're comfortable in understanding them, but at the same time, they're not really moving their business forward. And I think the reason that's the case is...

[04:57] people don't ever take a step back and think, what is the core problem I need to solve for my business? What's holding me back? [05:04] from growing faster than I want to, what's getting in my way, or what's an opportunity I know is there [05:09] But, you know, I'm not able to [05:12] take advantage of it. And with my company, what I was hearing over and over again was my sales team was consistently telling me that they just didn't know how to find anything. They didn't know how to find what customers were interested in. They didn't know how to find, how to speak to people of a certain industry or a certain title in terms of identifying use cases. So just so many unknowns. And [05:37] So once I understood or put my finger on that problem, I just became very sort of tunnel visioned. And I was determined to figure out how I can build solutions that can aid my sales and customer success team to be more in the know. So once you've actually identified the problem, the next step is figuring out, [05:55] What data can help you seize that opportunity? And in the case of understanding our customers and getting that information, it just so happens that since the pandemic, when our company went remote, we've been using this tool called Gong that's essentially attached to Zoom calls that records every single call that we have. So it says this call is being recorded for quality assurance purposes.

[06:25] were amazing and that we actually had 25,000 hours of call transcripts that had been a mess over the last five years. And if you think about understanding information about your customers and your business, there's no better source of truth. So we have since built an entire operating system around this information, not just the historical information, but a variety of different workflows that happen with each new call that occurs, because it's not just about understanding what's happened in the past, but it's also being able to be highly responsive to [06:54] to what's going on in the present. So the first thing I'm going to show today is an automation that we have created based upon calls our teams have, either our sales team or our customer success team. And essentially what happens is as soon as that call [07:11] is over, a series of events happen with that individual transcript. We also do things sort of at large with the aggregate. [07:19] transcripts, if that makes sense. But right now I'm going to show you what happens kind of like real time once a call is completed. [07:26] Great. So while you pull that up, just to recap for our listeners, you had a bunch of salespeople. They said, I don't know how to find the information that I need. I don't know how to generate the information I need. I need more information to serve our customers better. [07:38] You realize you had, and correct me if I'm wrong, 25,000 hours or something of reported customer calls, which are the perfect source of truth for… [07:49] how customers want to be interacted with. And you decided that was going to be the core context for a lot of these actions inside your company. And then you're going to show us a zap now that takes a single recording,

[08:03] and does a bunch of stuff. I got a preview of this and it does a lot of things. [08:06] I tried to give AI to my engineering team that figure stuff like this out. And it just became overwhelming to them, even integrating the product. And what's been helpful for me was first. [08:18] building things on my own. And I'm not technical enough to be able to build on top of our software product. So the tools like the one I'm going to show you today was a great way for me to be able to dive into the power of AI because it was on the edges of the it wasn't the product was sort of on the edges of how we operate it. And through that, though, I became far more adept [08:39] at AI. And now I'm very much involved in our product itself. So often people struggle to find a way in and there's lots of different ways. And one way is actually building something for yourself personally or building something for the marketing organization or somewhere else. And then through that process, you really start to get it. And then you can start to be more, you know, proficient in AI in much more substantive ways within the business. Yeah. And I want all the other CEOs and executives watching this podcast to listen [09:09] efficient to instruct your engineers. [09:11] to build AI. You'll go nowhere. [09:13] Yeah, no, you'll go nowhere. And I've said this a lot. This is a moment for actual hard skill building in leaders, which is you actually have accessible skills to build in. [09:23] using AI, building AI tools, using these sort of like no code versions, [09:28] of tools to really upskill yourself on the capability. And that's going to make you a much more relevant.

[09:34] leader, much more. Yeah, you're opening up the hood. It's like you think about if you bring your car in and you don't know anything about fixing a car and they tell you four thousand dollars to fix a transmission, you're going to say, OK, because you need your transmission fixed. Right. But if you actually just open up the hood, you understand how transmission transition works, even if you're not a mechanic. [09:52] Maybe you can say, well, it really shouldn't cost $4,000 of fixes. It really costs close to $2,000. And I think that's sort of the same analogy when it comes to AI. [10:02] The first step is building what I call a trigger automation. And this trigger automation essentially comes from a tool that we've created called, that we use called Browse AI. So this is Browse AI. And essentially what Browse AI does is it runs like a script where essentially scrapes information from GAN calls. So what you see here is a URL string. You need a URL string in order to identify a call transcript. [10:30] as it comes in. [10:31] And Dom didn't have an easy way to do this. So I basically started to bring up a bunch of call transcripts. And what I started to see is they all kind of start the same way. [10:41] And they just end it with this call ID. So the only thing different from call to call. [10:46] was this call ID. [10:47] So basically, I needed to figure out [10:50] Still can I [10:52] Create a feed. [10:54] For Zapier, [10:55] So knew the call ID. [10:58] of each new call as it kind of occurred. So the first step [11:03] is essentially a trigger where a new call comes in

[11:08] And then what happens is when the new call comes in, [11:11] What it will do is it'll basically scrape the information from Gong. And one of the things Gong will give you is that call ID. [11:20] So I'm able to actually see the call ID. So if I click here and I scroll over, you'll actually see that there's a call ID that I can identify here, which is right here. [11:31] And so that appended to the URL was, [11:35] essentially is all I needed to give browse to be able to go to that URL [11:41] and essentially scrape the call transcript. [11:43] So, [11:44] It wasn't connected. I had to kind of hack it together. So if you'll see here, it basically knows what to run just based upon what's brought in. [11:53] And then it will go to this page, which I will show you here, which actually is where the transcript is. [11:59] And it's able to essentially scrape the entire transcript. So this is the raw transcript that's coming from the GAN calls by Browse AI, going to that GAN page and just getting this information. [12:10] But I had that initiated. So that first step essentially initiates the scrape. And then when the scrape is completed, [12:17] It starts my next automation. [12:19] Yeah, and so just to call this out for folks that are trying to build their own thing, it's okay if your tool itself does not expose... [12:26] the data you want. In this age now, you can usually use another tool or an alternative. There's always a way. Or an LLM to really pull the data you need out of any system. Yeah. And I could have given up, Clara, like at that point, that probably one step

[12:43] took me the longest. [12:44] And if I never would have gotten past that step, [12:47] And I think a lot of people would probably have given up at that step. But after I got over that hurdle, [12:52] then everything else became so much easier. And it's really like an analogy for life, like building something like this. And there are other stumbles I've had along the way in building things, but you just have to know that there's a way. [13:03] and using, just 'cause a tool doesn't do it, doesn't mean it can't be done. And this like in the rear view mirror seems obvious. And now if I had a similar challenge, I'd be able to do it right away. 'Cause what will happen is every time you solve a problem such as that, the next time you need to build something, you'll have all these sort of ideas and like hacks [13:21] in your tool chest, so to speak. And then now I'm at a point where there's like nothing you can tell me to build that I wouldn't know how to build because I just know how all these little things can be solved for. [13:32] And you learn coding along the way, right? Along the way, you learn what JSON means and all these things by having your hands on it. [13:39] and creating the automations. [13:41] 100%. What I was going to say is this is a CEO that I love. I love a CEO that knows how to build it. [13:47] I love a CEO who knows that no problem is not solvable. And I think just even getting hands on with some of these no code tools and these AI tools just gives you [13:57] a little bit more context to be bolder about what you build. Okay, so you have that's right. So the task is done, right? That's the call is done. And so this next trigger is true when [14:08] browse AI successfully scrapes a call transcript. And the first thing it will do is obviously, it'll trigger it. And you'll see here, it'll give me the entire transcript.

[14:17] of the call. And that's basically now it's like, okay, now I'm in business right now. I have everything I need. And there's a bunch of other stuff in that gun call transcript that I use to do database lookups throughout that we'll kind of get into. I'll have a delay of about two minutes before pulling in data like this, just because I want to make sure that all the data is brought in, the scrape is done. And I'm just, you're prone to errors, especially if you're running a lot of [14:47] just to let the system catch up so it doesn't break. So that's kind of self-explanatory. The next thing I do is I run a format where I'm basically removing all the HTML from the transcript. So when you scrape sometimes, it'll pull in the HTML. And I don't want that. I just actually want the actual text. So I run a formatter step where I'm removing all that. I'm pulling out anything I need to that might confuse the analysis. So I'm just essentially getting the raw text. [15:15] Then what I do is I start to [15:17] enrich the data with other information [15:20] Besides just the Gong transcript, because I had the Gong transcript. But one of the things I knew I wanted to build was after the call was done, I wanted to be able to tell the salesperson that was on that call. [15:30] what transpired. [15:32] I want to make it easy for them to write a follow up email. I want to be able to identify who their supervisor was. Right. But that wasn't directly pulled in through the. [15:41] However, we have other data sources that essentially can connect that information. So, you know, we have a lot of data sources that are in the chat.

[15:48] We have a Google Sheet here. [15:50] For example, if you look up this ID, it connects the ID to the brand and the brand to the user, which is a whole separate workflow that we created. So it can kind of connect the dots. Because when you're running an automation, you're not always going to get the data from the trigger. Sometimes you have to round it out. And the way you round it out is using things like lookups on Google Sheets. So you're pulling everything in. It's almost like you're going down a path, you're on a hiking trail, and you want to be able to pull the supplies you need along the way before you get to the destination. [16:20] I had a backpack, but the backpack didn't have water in it. And now I have water, right? Because I grabbed it from here. And you're kind of going along a journey. And I personally, one reason why I love Zapier versus other tools is the way my mind thinks is in a very sequential framework where there's other platforms like NA and, you know, or Bot Press where it's basically like, looks like almost like an octopus, how it's branching out. I just have a hard time thinking that way. [16:44] Now, over time, I've had to because I'm basically describing the difference between automation and agents because agents are not deterministic. Agents have different ways. And my brain has struggled with understanding agents, and I'm finally getting there. But basically, the progression I see people having to take in AI is you start with using AI as a tool. You know, ChatGPT, give me a recipe for lasagna. Then it's, okay, automation, which we're talking about now. And then you get into the world of agents where it's not just always going from step one to two to three. [17:14] day based on what you're trying to accomplish. Well, one tip for you or one tip for the listeners here I found is we'll go through this whole thing.

[17:21] And a good exercise I found is taking a sequential step based automation [17:28] And trying to use, for example, Zapier agents and just describe that automation in natural language and steps and see how close you can get. Even that replication across modalities can be a good way to test your exercise. Yeah, just test it out 100%. Yeah. And it's looking up the information so it's able to basically grab the information. And then after I feel like I've got all the information, the next thing I'm going to do is this where I'm starting to pull in the LLMs. And an important part here is, first and foremost, knowing what LLMs to use. [17:58] I've had a hard time with is actually just, we have so many automations now. I think we can do a better job, the organizational design behind it. Cause what happens, I built so many things and I don't always do proper handoffs. So for example, here. [18:12] It should always say use the latest stable version, but it didn't. [18:16] Right. So, so I'm going to change it now. You're live on the spot because I want to be using the latest version. [18:22] You also want to make sure you're using the best model. I still think GBT4 Turbo is probably a good model for this, but you could see in the platform Zapier, there are multiple different versions that you can choose from based upon, and obviously they all lead up different amounts of coins, but it's pretty incredible in terms of all the models. Now with GBT5, [18:42] It's supposed to be able to choose for you, but it's unclear to me how that works in the context of an API. And for some reason, still in Zapier, you're still able to choose. And, you know, I spend a lot of time testing. I'll go in the chat GPT and test the sample input in a variety of different models to make sure it's like whatever's the best output, the quickest is what I'll tend to use. So you're still losing using classic GPT-4 Turbo, a good old classic, classic favorite. Right. AI is supposed to make work easier, but I've been there.

[19:12] weeks of setup, endless back and forth with engineering, and yet another tool the team never really adopts. That's why I use Zapier's AI orchestration platform. It connects with nearly 8,000 apps, so I can finally put AI to work without the drama, without the delays, and without pulling engineering in every time I want to automate something. With Zapier, you can roll out AI-powered workflows that do real work across your whole company in days, not weeks. I use Zapier every [19:42] It checks my calendar weekly and offers smarter ways to manage my time, and it even drafts emails for every new request. [19:48] that lands in my inbox. [19:50] All of that running quietly in the background so I can focus on the work that matters. And Zapier's built for scale. With enterprise-grade security, compliance, and governance, it's trusted by teams at Dropbox, Airbnb, Opendoor, and thousands more. Go to try.zapier.com/howiai to learn more about how Zapier can bring the power of AI orchestration to your entire org. [20:14] Let's talk a little bit about this prompt. So tell me what first kind of summarization exercises you want to do here. [20:22] Yeah, so basically here, and the reason I can use a model like a GPT-4 is... [20:28] And, you know, part of it again is just keeping up with continuing to update the models, but I don't fix things if they're not broken. So this particular zap works perfectly for us and it gives us everything we need. And we don't need more rigor in analysis here because it's just some core things that we want to identify. So I'd rather not spend the extra money and even go through it. But at a certain point, if it didn't work, I would look at models. So we're going fast enough. What's interesting is that older models tend to work.

[20:54] faster and faster and faster over time and they actually error out less and and sometimes the older models get updated as a new models update as well so it's not like you're you're driving in an 84 chevy so to speak so here [21:07] This is a key step. This is called core summary generator. And what this is asked to do is analyze the customer success call transcript between Susie and our client to gauge the health of customer relationships. [21:18] and identify improvement areas. Start summaries with the customer's company name, key participants, and then kind of going through it, ask for the key stakeholders. And then it gives a call overview. We should describe the call's purpose, the main topics discussed, and the outcome. Exclude small talk. And then I have a variety of different instructions. Assess the overall customer sentiment, noting any frustrations or concern. Provide a sentiment score from one to 10, where 10 reflects high satisfaction, and one indicates potential discontinuation of our services. This is the key thing, [21:48] modify customer sentiment over time. And we actually benchmark this against actual churn. And it's been highly predictive in terms of the, if you take the average sentiment score of customer calls over the past year, it's a huge predictor of if the customer is not just going to churn or are they going to upsell if they're really happy. Also, one great thing the customer successfully did on the call, kind of identify that. And what are some things that they actually could have done

[22:18] where it'll take a transcript and identify all this information for me. [22:24] And then that content, I can do a variety of different things with, but it's a huge part of the overall app. [22:29] So one of the things I want to call out here as I was reading your prompt is [22:33] in an ideal world, [22:35] All your best CSMs are doing this after every call in a perfect way with great objective self-evaluation, all this kind of stuff. And the reality is we're all so busy that your customer success folks, your sales folks are probably going meeting to meeting and meeting. And at the end of the day, trying to figure out their notes and put little things in. [23:05] at their job [23:06] by automating some of the work that they would do. And so... [23:10] I think it's a really good hygiene step for anybody to think, you know, after I'm coming out of a meeting, if I were to do my best job possible, what are the five things I would do coming out of each meeting? And then just automate that for yourself. And then you know that every time you're going to be doing that. [23:25] So the bunch of other steps I have, and I'm not going to go through all of them because there's a ton of them, but basically it looks up the user on Slack. So I understand the user meaning our employee on Slack. It identifies the people who aren't from our companies who can kind of exclude them. It's able to find the user here. So I use Slack as a lookup sometimes because our company's entire directories on Slack. So if I'm trying to get someone's email address in an automated fashion and I have their name, I can actually use Slack as a lookup tool.

[23:55] In zap. [23:56] without even actually posting anything to Slack. So, Thumbpong sees tools actually can be used for other purposes. That's not their core purpose. And then basically, one of the main things I do from this is I send a channel message. So basically, after the call is done, you could see new customer success call alert. [24:13] as the account. [24:15] the opportunity [24:16] the leader of the call from our company, the date of the call, and it basically has that summary that gets sent out. So we have a we have a channel. [24:25] that are that's a constant feed that i obviously the ceo i'm very attuned to and i'll share it right now where basically every time a customer call is done [24:35] it just pops up on Slack. And I'm able to really, you know, we have 300 employees at our company and I'm really able to get a sense of the kind of pulse of the company, what customers care about, [24:46] just based upon looking at something like this. And it's, you know, that alone, if that was the only invention that came out of AI, it would be pretty incredible if you think about it. And this is just like one of many things that we do. So I'm going to pull up and slap right now. And you can see here. [25:02] This is the sample call and it shows who the key stakeholders were, what the call attempted to establish. [25:10] What was the 10 and score gotten an eight right opportunities for upselling? [25:15] feedback, and next steps. And it has basically a transcript here [25:19] And it's great for us to do if a customer is not happy. [25:23] Right. If they, you know, for some reason, score below a seven, we have a turn notification channel.

[25:33] Um, where basically it's called churn early warning system where it'll tell us [25:37] if a customer is not happy for whatever reason. And we've had to modulate it because sometimes a client will say they're not... [25:45] It'll say the client's not happy. [25:47] But maybe they're just not happy with how their business is going. So it's not always like a science. And then in the channel, sometimes the rep will say, oh, no, they're fine. It's just this. But we have in many instances, and to your point earlier, like sometimes the rep might not want to tell anybody, right? Maybe it's a Friday afternoon. They just don't want to deal with it. And then what happens is we end up forgetting about it. And then the customer churns three months later. And we're like, why didn't you just tell us? We don't have to do that anymore. We don't have to ask somebody how that call went with Procter & Gamble. [26:17] later. [26:17] Yep. Okay, great. So [26:19] You take the transcript, you post all of them. So everybody in the company has access to customer calls and summaries, which is just great for general sentiment analysis, knowledge sharing, transparency. You take any ones where the sentiment analysis is low and you put them in sort of like a warning area, churn alert channel, where I'm sure you're paying a little extra attention so you can get ahead of potential churn risks, which as a B2B girl, I really, really love.

[26:49] side of things, but then I know you take off a bunch of [26:52] Yeah, there's a bunch of other things. Yeah. So this next one, again, is all part of the same automation. [26:58] is another LLM call where we're basically describing what Susie does and we're saying analyze [27:04] The key areas of interest stated in the transcript. [27:07] and output a bunch of keywords that we should be buying in Google. [27:11] So if customers are using words that are describing what they're interested in or what we sell, and we're not running Google keywords for them, we want to. So basically these keywords will be mentioned. We extract them, and then we run an automation to add those keywords to our Google campaigns automatically. [27:30] So not only are you taking sort of this is [27:33] I love this one, so I want people to pay attention. So not only are you taking the account level specific context, but you're saying, [27:40] Our customers will tell us in their words what they're looking for, what problems they're trying to solve. These customer calls are a rich source of market insight. And so you're going to use these customer calls to actually extract out information. [27:55] market surface areas, keywords, places where you can put marketing dollars against and then reach customers similar to the customers that you're successful with, which is a really nice. [28:04] closed loop solution. And again, that's right. [28:08] We were talking about how this note summary is the way, in an ideal world, a customer success manager would provide notes. [28:16] In an ideal organization, [28:19] Your, you know, paid search manager would be monitoring all these calls and doing all this for you. But we don't live in ideal worlds and people are busy. And so again, this is not only designing from the point of view of like, what would a person do, but also what would a team do?

[28:34] That's right. The other thing we do is we've done a coach into this. So the next step essentially is called individual call feedback. And what this does is it actually creates a feedback note to the person on the call. So this just goes to the sales rep on the sales or customers just rep saying, [28:52] Here's what you did. Here's what you did right. Here's what you did wrong. [28:55] and actually sends it to them right afterwards. So they understand how they get better. [28:59] which is something that we would have to hire somebody to be on their back and tell them, which they know are on their own. What's interesting is like the people that really want to get better, [29:08] AI is an incredible tool because they're going to want this feedback. And the people who never really want to hear from anyone to begin with, they're not going to want to hear this. [29:17] They wouldn't have been good in either way. So that kind of goes to the point that like, it's going to make the good people that much better. Right. And we add this to a data set. [29:26] So we have a feedback call data set. So we can actually... [29:29] See, are there trends like is AI detecting that this person always cuts calls short or they always interrupt the customer or they don't talk about. And then when it comes time to reviewing them, it's all data driven. It's not just myopic. If managers change over, we have all this information and the good ones want this information. [29:47] Yeah, what I was actually going to reflect on is you're talking about this from the point of view of the individual contributor, the CSM, the AE. [29:55] But what I was thinking is so much of AE and CSM performance is really gated on, do they have a good sales manager coach? Do they have a good... [30:02] SVP sales that can actually provide them targeted coaching on all of their deals right when it's relevant. And this sort of like...

[30:10] evens the playing field. Your manager could be great. Your manager could be terrible. In every call, you're going to get kind of objective feedback on your performance. And so, again, it helps up-level the performance across the organization. And it's democratized. You're right. 100%. The other thing we realized, going back to problem solving, is we heard from our sales team and our customer team, you know, it takes so much time for us to write a good follow-up email after the call. So now we add a follow-up email writer, where essentially you write an email and you're [30:39] that they would want to send as a follow up to the call. [30:43] and actually just and designed very well and it's sent to them for them to basically copy and paste it and send it and it's just a way for them so right after their call they'll get the feedback in their inbox and they'll get this [30:54] email and they can copy and paste and send their edit. And, you know, we could have made this automated, but you know, that's where the human in the loop matters, right? We don't, what if there's the context is wrong? What if they don't want to send the feedback right away? What if they want to copy somebody new? So that's why we have to have a human in the loop here. [31:10] So the churn-only warning detector basically sends through two different paths, and these paths essentially kind of dictate who we should notify and who we shouldn't. So we've also now started to do much more marketing-driven things from this data, one of which is we start to create a database. This is called Customer Profile Database. And what Customer Profile Database does is it essentially structures data after each call with things like, what's the role of the customer? [31:40] product areas of Suzy are they most interested in? What business trends are they most interested in? And we have a structured database across all the calls, which gets fed into a GPT. So if a salesperson is going into a call with a brand manager of an automotive company, they could say, what are the things that brand managers or automotive companies are most interested in, in terms of trends of interest or our product? And it'll tell them right away, because the data and aggregate is stored with a different tool that we deploy. So again, not only do we have

[32:10] that are happening, but we have this aggregate database that we unlock the value of on an ongoing basis. [32:16] OK, I have to ask you a question again as a B2B enterprise girl. [32:20] are you using a CRM? Like, is this data going into Salesforce? Are you like, look, it can all go in Google Sheets. We don't care. I'm just curious. Well, I mean, it's, you know, [32:30] Today it goes in the sales force, but I think the reason Mark Benioff is leaning at the agent forces for that reason, right? It's like, what's the point? Right? So like, what's the point? Right? [32:39] Theoretically, everything I'm building right now is a better version of Salesforce. And guess what? The salesperson doesn't have to enter a record. It's entered. And the manager is getting information. And they can chat with the data. And they can pull reports and aggregate records. [32:54] That's basically what Salesforce was built for. And, you know, from a meta standpoint, our company is facing the same thing with market research. We're like, we built this. So we're all trying to figure out. [33:04] how to disrupt ourselves based upon what's happening. But you're right. I mean, and that's sort of the fundamental issue that exists today. [33:10] What I was reflecting on, though, is one of the challenges with Salesforce, well, you know, one of the reasons Salesforce did so well is because of the flexibility of implementing your own data schema and kind of- [33:22] Gosh, you have to go through your Salesforce admin to like set up anything and get it. Right. You know, and then. And the charts and graphs weren't great. And no one knew really how to. I mean, you just sometimes want to know what's the status of the P&G account. It's what you want to know. And it's just good luck. [33:38] getting that done. Well, right now you could just literally just speak it or type it and you get it. And that's kind of where we're all heading to.

[33:44] Yeah, and then what you're showing is you can create these one-off [33:47] loosely structured Google Sheets, for example, for different various lookups. They don't have to be perfect. They don't have to be hardened in your CRM, but they're useful to your team. And I think that's structured. It's a structured database, which, you know, I think, you know, for RAG, structured databases work much better. And this is a structured database and that's really all you need. I think the point here, it goes back to what I mentioned earlier, is you just have to find it's not about the tool. It's about the data. [34:15] People are so focused on the application layer. It means nothing without the data. And to me, it's like, this is the ultimate source of data. And this is the treasure trove. And this is people in the wild saying what they want. So I want to build everything on top of this data. So that's why when we were... [34:30] prepping for today's interview. You're like, we'll show a bunch of different things. And the way I look at it is differently. I'm going to show you one thing that has many different tentacles, [34:38] based on the most important thing, which is what our customers are saying. [34:41] And that's a different way of looking at it. [34:43] Yeah. And I want you to show one more sort of marketing use case off this master workflow. But while you're not up. [34:51] What I might encourage people to think about is... [34:55] Think of yourself as a single workflow. Think of your team as a single workflow. Maybe even think of your company as a single workflow and figure out how that whole thing should work and then work your way into some of these automations is really interesting as opposed to these little things. [35:09] micro task kind of style things you can really ladder it up to [35:13] What's the step-by-step process this team should follow given a certain task? And so I think it's really interesting that you have this mega automation as opposed to these little one-off things. So that's the last one I'll show you, which is this one was controversial at first and

[35:30] It required massive testing to push it live, which is. [35:34] So we speak to somebody, say a financial service brand, and they talk, Suzy, the market research company, right? So we compete with companies like Qualtrics and SurveyMonkey, et cetera. So we're going to have a, we had a call. Okay. [35:45] with a financial services company and they want to name [35:50] a new product. [35:51] Say it's a new credit card or something. That's a use case that other financial services companies might want to use us for. Now, [35:58] Obviously, we can't share that X-Paint. [36:02] is thinking about renaming something. [36:04] So we but we want to share that Suzy can do this new use case. So what we did is we've done automation where it basically extracts any identifying information from the call. [36:15] So basically that includes the brand, the brand name, any specific strategy that the company had, anything that's identifying to them at all. [36:24] we were decked. And we had to test it over and over and over again to make sure that nothing could get through. That could be it. We'll lose customers and we breach companies. We can't do any of that. But at the same time, [36:35] If a salesperson just talked to a beverage company about, you know, testing packaging, they're very welcome. The next call is, yeah, I just spoke to another company about this. And that's kind of what we wanted to... [36:47] have a programmatic approach to. So what this does is it'll take those transcripts and it'll write a blog post [36:54] that fully redacts all that specified information, but focuses just on the idea of what we talked about. [37:00] It'll create a graphic

[37:02] a headline, it'll even create a custom CTA at the bottom. [37:06] And it will optimize for SEO and it publishes it on our blog. [37:11] And it publishes it 21 days later. [37:14] which is just something that we want to do to even make sure to the nth degree that [37:18] any privacy or anything. So we, we, but now we have 10,000 blog posts that are created. [37:25] on the calls that we're making without any human intervention. It just goes. It goes and goes and goes on every single use case that you can think of. And now we're running [37:34] Apples against yeast. [37:36] through Google dynamic search ads. So, you know, we're starting to get now. It takes a while to gain SEO traction. [37:42] with stuff like this. But even before that, now if someone searches for anything that Suzy has possibly talked to somebody about, we have a blog post up there and we run ads against it. [37:51] This is amazing. I love this. It gives me so many ideas. And what I like about this is it's... [37:59] taking, again, your richest source of insight about not just what a customer wants, but what the market wants, and creating assets that then you can use to go reach similar customers with similar problems. So again, your most successful customers are going to look like your most successful customers. And so you want to go find more of those folks. So again, to recap for everybody, a single gong call generates a summary, a Slack post, a churn risk alert, a [38:29] follow-up email, a coaching email to the CSM. It enriches a bunch of data. It sends out automations. It identifies keywords for you to bid on, and it generates content for you to both

[38:43] bid on and send pay traffic to, but also generate to get organic traffic going off. [38:50] one call. So the other thing I want to call out for people is in this age of AI and automation, you can take a very simple asset, [38:57] and extract the nth degree of value [39:02] out of that asset, which I think is such a useful and helpful tool [39:07] workflow for people. So Matt, we had this is a How I AI First. You have created such a big workflow that we have only shown one. [39:16] And I think that's enough. And we'll have people reach out to you. I know you have a couple other really interesting workflows, but we're going to get you back to building Zaps and running this amazing team. Before I let you go, let me ask... [39:29] Two lightning round questions and then we'll get you out of here. One is, you know, as I've been reflecting, this is a good reflection of how great individual contributors work or how great teams work. How has this changed how you think about building the shape of your team and your startup right now? Yeah, I think it's far more individual contributors, far more people who want to put their hands on keyboard, people who are willing to learn, people who are motivated and ambitious. [39:54] that are proactive at finding solutions. I think those are the people who are going to drive the next great businesses, not order takers, not people who walk into work every day and wait to be told what to do. [40:07] Because you could just solve what I'm able to do if I tell AI what to do. [40:11] So [40:12] I don't need more people to tell what to do.

[40:15] I need people who are going to come up with new ideas and solutions to be proactive. [40:19] Yeah, what I say is this is the age of the super IC. Like if you can be a super IC, you're going to go so far. You know, second question, who do you think should own this inside your team? I know you're building a lot of it, but is this a role? Is this everybody's job? Who do you think needs to be thinking about building these kinds of automation? Well, I think that you need like a couple of go-to-market orchestrators that are almost like general contractors that are looking at the blueprint. [40:46] of all different automations. But then I think you need people who are owning the output of those automations. And so the marketing team should only output the blogs and that's not working. They should go to the, you know, the automation, the automation team and say, well, this is breaking. How do we make it better, et cetera. I think that's the best design. [41:03] But it does require definitely new roles in the organization. Yeah, for sure. And then of course, the last question, which is, [41:11] prompting techniques when AI is not giving you what you want. [41:14] What do you do? Maybe in chat, GPT, like... [41:17] Do you bribe? [41:19] Are you an all caps person? What do you do? [41:21] I have a framework where I first set what I'm trying to accomplish. And then I kind of set the framework for the prompts, almost like guardrails, like [41:30] Here's what not to do. [41:31] And then I think for me, telling it what not to do is a great way of kind of eliminating the issues I see until I get close. And when I get close to it, outpending something I actually want, then I refine what I want it to actually do. And I think that's generally how I go about it. Okay, so you're doing guardrail prompting. Do not do, in addition to this, is what we want you to accomplish. Well, Matt, this has been amazing. I love this. I'm actually going to go steal a bunch of your ideas for my own. Please do. Enterprise pipeline.

[42:01] you and how can we be helpful? [42:03] You can find, learn more about me at mattbritton.com. I just rolled out a new book in May called Generation AI. So definitely check that out. It's about Generation Alpha and the AI generation. And then you can learn more about my company, Susie, at susie.com, S-U-Z-Y.com. [42:20] Well, Matt, I really appreciate it. Thanks for the time. [42:22] Thanks so much, Claire. [42:25] Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube or even better, leave us a comment with your thoughts. [42:32] You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.