The Exchanges

Q So you don't have to have it make it up on its own. It's using your database for reference. Okay. Um, is there anything that you're anything else you're going to show or is that it?

A Um, that's the primary loop. Um, but the thing I want to point out that's very important here is that, um, probably everybody listening to this show is thinking about building an agent, right? You know, building an agent, either an agent is your product or an agent is inside your product, right? So for Untangle, we have Grace. She's our AI divorce agent. She's inside of Untangle. Now, she has specific tools, right? They're very specific to our vertical, right? You know, divorce statute search, case law search, child support guideline search, right? These are very specific to divorce in Connecticut, right? But Grace, Writes all of our AEO content, right? Because she has the right tooling to write legally accurate content. Right. And so everybody needs to take that mentality and say, oh, like I'm creating a highly specialized vertical agent for whatever field you're in. Say it's a floor tiling or, you know, snow removal. Um, you're going to have an agent that has specific skills. That should be the agent that writes your content. That should be the agent that writes your emails. Like this is all the same entity.

AI assessment note: “that's the primary loop. Um, but the thing I want to point out”

Q don't see much is like what you just showed me earlier, which is here's how I'm thinking about drip campaigns. Here's how I'm customizing it. Um, how I'm thinking about getting new customers in the door. That kind of stuff doesn't seem to be getting as much attention. Is it because no one, no one's paying attention to it, or it's just not flashy enough for us to talk about?

A Uh, I think because marketing is the real work and people don't like to talk about it. Um, you know, actually your go to market strategy and your acquisition and your funnel and your CAC and your LTV, you know, these are actually the real business things that we all need to be thinking about. They're a little less sexy and a little, a little less exciting. Um, so I'll tell you this. I, I think the loop that I, I, you know, briefly mentioned is actually probably the most valuable thing I could talk about today, which is Every day, create, just go to amp, go to cloud code, go to your favorite agent and say, I want an email every day with key with one to two key actions I should take to acquire more customers at our, uh, desired CAC. Right. And you build out a little script. It's very simple. It's a cron job. It runs at midnight and you basically feed the right information into the model. And then you say the model, write me an email with your thoughts on our stats and what we should do today to increase our signups, to create our engagement, to increase our numbers. And actually that loop has led me, you know, very quickly to optimizing the business, you know, in a, in a real way versus like what features should I build?

AI assessment note: “I think because marketing is the real work and people don't like to talk”

Q Um, and just basically said, yeah, what would you say?

A You know, I'd say, yeah, like we need to capture leads. What's, what should we do? Um, and I'm pretty sure it sort of said, well, you know, we, we could calculate, you know, child support. Cal calculate alimony. We could calculate, we could create a roadmap for divorce. Um, And I was like, okay, let's explore that. And it turns out calculating child support is extremely complex and difficult. Um, and you have to have all the right tools, but we've built those because that's what a Tangle does. Um, so I think the lesson here is go talk to your agent. Um, and then iterate and then measure and then iterate and measure, um, as fast as you can.

AI assessment note: “I'd say, yeah, like we need to capture leads. What's, what should we do?”

Q All right. So a lead comes in. That's this top, uh, top left. You start sending them drip. What's the tool? What's the software that you use to send all this out beyond? I know what's actually manually sending it out. It's recent, but what have you built internally? That's doing all this.

A So gosh, this is the beauty of the world we live in right now. So I've you, I use amp to build all of this, uh, infrastructure, right? So literally all I did is I opened up amp. And, uh, untangle is a next JS app, right? So it's all on TypeScript. Um, and for those of you listening and watching that don't feel like you're deeply technical, don't have a computer science degree, then it's okay. Like you, you live in a world now where you have amp and cloud code and all these tools that are the best engineer you can imagine, and they can build. You just have to talk to the, to the agent and ask it to help you. So now I have a computer science degree and I've been coding for 25 years. Yes. So. I have a slight advantage in that, but all I did is open up amp and said, I want to build an email drip.

AI assessment note: “I use amp to build all of this, uh, infrastructure, right?”

Q What's the advantage of using AMP? I know you, you tend not to talk about AMP, even though you're, you're connected very closely to them. Um, but what's the advantage of using them?

A Okay. So, AMP is an amazing, uh, coding agent. Um, so there's a lot of choices people have here. They can use, if they like a visual environment, like an IDE, they can use VS code or they can use cursor and, and, um, they have their own agents. Um, but in VS code, for instance, you can use AMP if, if you like that. Uh, I am more of a command line interface type of guy. Like I like the cleanness of this. So what I'm gonna do is start up. Um, I'm gonna make this a little bigger. And so this is my coding agent, right? So what I do is I hop in here and I just start asking him to do things. Right. Um, so we've got, uh, you know, usually I do actually use whisper flow for this. So I'll say something like, Have a look at our email drip system and tell me how it works from a technical perspective, uh, and then create a markdown file so I can share that. All right. So, um, amps gonna go off and do that. I'm actually, uh, secretly showing you a new feature. If you see deep here, uh, this is a mode. We're actually, we're actually using a GPT five, two instead of Opus four or five. So a little bit of inside baseball there. Um, so what's happening is it's cranking. It's thinking about stuff and it's going to end up, um, uh, giving me what I want. Um, here you can see it's creating a task, um, and, uh, it's going to complete that task and, and do, do what needs to do. Now, what I actually do…

AI assessment note: “I am more of a command line interface type of guy. Like I like the cleanness”

Q Okay. And so you're just going into it and you're saying, this is my vision. I want you to start creating it. How are you thinking about the way that it's getting it to create? How are you breaking down the tasks? How are you giving it instructions? It's different from others.

A So I think this is the crux of the situation. This is the most important question that all of us are dealing with. You know, we live in a world now where effectively code is free. It's at least very cheap, right? Um, so what we build is now becoming more important than how fast we build it. Um, And I think this is honestly creating a crisis, right? Where all of us who can build are saying, what should I build? Am I building the right things? You know, am I, am I building the right things quickly enough? So the way I look at it is, um, I use fizzy, which is a, uh, 37 signals new app for my backlog. I add things to my backlog. And then, uh, when I realized, okay, these are some features I want to build out. Um, what I do then is I create a product requirement doc, uh, PRD. Um, and then I take that PRD and I break it down to user stories. And then I use the Ralph loop to build those, build that feature. And sometimes I'll do up to three at a time, and then I'll come back and look and say, okay, is this the right thing? Um, but I'm just trying to be vulnerable in the sense that Everybody's dealing with this question of, are we building the right things? Are we fast enough? Are we going to get out built by everybody else now? Um, you know, what is the moat now? And it's, uh, it's disconcerting.

AI assessment note: “I create a product requirement doc... break it down to user stories”