#2295 Ryan Carson: How AI does my marketing for me

Summary

Startup Stories - Mixergy
Episode #2295: Ryan Carson: How AI Does My Marketing For Me
Date: January 26, 2026
Host: Andrew Warner
Guest: Ryan Carson (Founder, Untangle)

---

Episode Overview

In this insightful episode, serial entrepreneur Ryan Carson shares with Andrew Warner how he uses AI to automate and supercharge his startup’s marketing efforts. Centered around his new company, Untangle (an AI-driven divorce platform), Ryan explains his journey from traditional email drips to deeply personalized campaigns, powered and orchestrated almost entirely by AI agents and automation tools. The conversation offers a practical, step-by-step walkthrough—complete with technical details, real-world anecdotes, and strategic advice—showing how startups can leverage AI to acquire and engage customers more effectively and efficiently than ever before.

---

Key Discussion Points & Insights

1. The Old Way vs. The AI Way in Email Marketing

• Traditional approach: Pre-written, templated “drip” campaigns with minor personalization (like a customer’s first name).
• The AI opportunity: “Why isn’t every email absolutely customized for the customer, so it’s completely personal? Like, we can do this now.” — Ryan Carson [00:55]
• Ryan built a system where AI writes every email drip personalized to the individual user, using any contextual information available.

2. How the System Works – Technical Walkthrough

Ryan describes his end-to-end process, built with modern AI platforms and automation tools:

Step-by-Step Workflow [03:59–12:47]

• Lead Entry: User interacts with a lead magnet (e.g., a child support calculator).
• Context Gathering: Store all available data about the user; enrich with info gathered from sources like Parallel AI, LinkedIn, and the X API.
  “You can actually use tools like Parallel AI to go out and scrape the Internet to find more information. You can get a lot of context on that customer.” — Ryan Carson [05:56]
• Campaign Creation: Map collected data to a custom email drip campaign table.
• Email Generation: For every scheduled email, an LLM (Opus 4.5 or GPT-5.2) gets a system prompt, user data, interaction history, and rules.
  • Include strict guidance to prevent AI from “hallucinating” features.
  • “You do not want the LLM hallucinating features for your app. That’s always terrible.” — Ryan [07:05]
• Delivery: Use tools like Resend (preferred for its ease of use and SEO/Answer Engine Optimization), Sendgrid, etc.
• Engagement Tracking: Monitor clicks and bounces, not opens, to assess engagement.
• Drip/Nurture Loop: After sequence completion, move contact onto a long-term, context-aware monthly nurture sequence.

3. Creating Real Results with AI-Driven Insights

• Example: The AI, monitoring user engagement, spotted “five people that have clicked three different times on your email drips.”
  Ryan had the AI send a personal email offering a call, instantly resulting in a new customer:

  • “I immediately got a reply from one of those customers … and she said, I would love to meet. ... In the end, she’s like, I’m gonna sign up for the free trial.” — Ryan [02:51]

• The AI not only handles communication but also recommends actionable next steps every day.

  • “It generates an email with recommendations on what is the one thing I should do to improve my marketing funnel today.” — Ryan [01:51]

4. The Power of Specialized Vertical AI Agents

• Untangle’s AI agent “Grace” is trained and tooled specifically for the divorce niche (e.g., statute search, guideline lookup).
• Grace writes both legal content and customer emails.
• Ryan’s core advice: “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.” — Ryan Carson [13:19]

5. Automation Tools: Amp, Ghosty, Zapier, and More

• Building the Stack:
  • Amp: Advanced coding agent; Ryan uses it (within Ghosty) to build and extend his stack (NextJS, Typescript-based).
  • “All I did is open up Amp and said, I want to build an email drip.” — Ryan [16:30]
• Task Handoff: Ryan runs multiple Amp agents (through different Ghosty windows) simultaneously—delegating several engineering tasks at once.
• Integration Example: Zapier is used for connecting disparate tools and automating data flows.
  • Andrew: “They actually will have a connector into Claude that connects to all their other tools. … Zapier just pulled it together and created an email in Gmail for me.” [15:06–15:46]

6. Building & Managing with AI

• Ryan describes his workflow of ideation (using Fizzy for backlog), breaking down requirements, and using the “RALPH loop” to implement features via AI agents.
• “We live in a world now where effectively code is free, it's at least very cheap … so what we build is now becoming more important than how fast we build it.” — Ryan [21:24]

7. Daily Marketing Optimization Loop

• Ryan’s most valuable loop: An AI-generated daily email with one or two concrete marketing action items.
  • “Every day just go to Amp … and say, I want an email every day with one to two key actions I should take to acquire more customers at our desired CAC.” [24:05]
• Feeds data from lead magnets, conversion steps, and drop-offs into the AI for diagnosis and incremental improvement.
• “All you're doing is increasing your batting average … it's more likely that I'll see a good suggestion if I'm getting a smart suggestion once a day.” — Ryan [31:23]

8. Insights, Iteration, and Human Judgment

• The system surfaces valuable but often basic actions—things a human marketer might miss or neglect.
  • Ryan: “All that Amp is doing for me is really reminding me of fairly basic, obvious things that I need to do that I haven’t done yet. And that's actually very valuable.” [30:39]
• Ryan stresses the importance of context: “The agent needs context to give you valuable data.” [26:00]
• Ideas for lead magnets (like calculators) can, in fact, be generated by the AI—Ryan’s own was.
  • “I'd say, Amp, we need to capture leads. What should we do? … We could calculate child support, … create a roadmap for divorce. … It turns out calculating child support is extremely complex, and you have to have all the right tools, but we've built those.” [27:36]

9. The Future: Full Automation of Marketing Implementation

• Ryan aspires to have his AI not just suggest but actually implement its marketing recommendations—submitting PRs for real feature changes overnight.
  • “The next step is not just to get the email, but actually have Amp implement the suggestion. And then I wake up to a PR that I review.” [28:40]

10. Advice to Founders: Start Simple, Iterate

• Don’t overthink AI’s role—start with custom LLM emails, then evolve.
  • “Most people aren't even doing what I showed you … Start there and then iterate and then eventually after a year, you'll be this machine. But just take step one.” [33:05]

---

Notable Quotes & Memorable Moments

• On the promise of AI in marketing:
  “Email automation, AI—you know, all this is beginning to work. It was really fun.” — Ryan Carson [02:51]

• On context as the key to AI value:
  “You need context. The agent needs context to give you valuable data.” — Ryan [26:00]

• On AI’s marketing insight:
  “It's not rocket science, but it's an actionable, valuable insight.” — Ryan [31:23]

• On the founder’s new challenge:
  “What we build is now becoming more important than how fast we build it. … Are we building the right things quickly enough? So the way I look at it is…I'm just trying to be vulnerable in the sense that everybody's dealing with this question of are we building the right things?” — Ryan [21:24]

• On future trends:
  “Somebody should be watching this and saying … I think what we could do is create really totally customized email. … Not only that, we start to enhance it with your own data and that becomes proprietary internal information.” — Andrew Warner [34:04]

• On letting AI implement decisions:
  “The next step is … have Amp implement the suggestion. And then I wake up to a PR that I review where it’s actually done the thing that it suggested.” — Ryan [28:40]

• On AI-assisted ideation:
  “Go talk to your agent and then iterate and then measure, and then iterate and measure as fast as you can.” — Ryan [27:32]

---

Important Timestamps

• 00:55 — Ryan on why every email should be customized, the birth of his AI-driven system.
• 01:51 — Example of AI-generated email insight leading to a new customer.
• 03:59–12:47 — Ryan’s end-to-end technical demo of his AI email marketing workflow.
• 13:19 — Specialization of vertical AI agents (“Grace”), and their expanding roles.
• 14:26–16:14 — Zapier’s role in Ryan and Andrew’s automation stacks.
• 16:30–21:24 — Building infrastructure with Amp, AI coding agents, and Ryan’s workflow philosophy.
• 24:05–31:23 — How Ryan gets daily actionable marketing advice from AI and applies it for growth.
• 27:36 — Using AI for marketing ideation and iteration.
• 28:40 — Vision of AI agents implementing their own recommendations.
• 31:23 — AI surfacing basic (yet high-leverage) growth opportunities.
• 33:05–34:04 — Founders are urged to start simple, iterate, and eventually outpace competitors with sophisticated AI automation.

---

Takeaways for Founders & Marketers

• AI-driven marketing is here—and works best when fully personalized: Even basic, daily suggestions from AI can profoundly improve customer acquisition and engagement.
• Provide context: The more relevant data you feed your AI, the more actionable and effective its suggestions.
• Start small: Even simple improvements via AI quickly compound; don’t wait for “perfect,” start automating and personalizing now.
• Leverage specialized agents: Strongly tool your AI for your industry/vertical, and let it produce content, campaigns, and more.
• Aim for the “autonomous marketer”: Expect a future where AI not only tells you what to do, but does it for you.

---

Summary in a Sentence

Ryan Carson demonstrates how founders can use off-the-shelf AI tools and coding agents to build highly effective, fully personalized marketing systems—boosting customer acquisition with daily, actionable insights, without expensive hires or heavy manual work.

Transcript

[A]

Why isn't every email customized for the customer? So it's completely personal. So I'm gonna share my screen and just kind of walk you through visually how this thing works.

[B]

Ryan Carson is a three time founder and he's building Untangle, which is AI for Divorce, the next new thing presented by Zapier, the AI automation company. Ryan, before you, before you started building your own email service provider, did you even consider that you can use other people's software?

[A]

You know, I've been running startups for like 25 years, right. And email drips have been just a constant part of the business and everybody uses them. And I, you know, was setting up an email drip for Untangle, my new startup, and then I thought, what am I doing? Why don't I have AI write the email drips? And ended up.

[B]

You mean like the series of emails?

[A]

Yeah, yeah. And why, why isn't every email absolutely customized for the customer? That. So it's completely personal, like we can do this now. And so I built a workflow and I'm very happy with it.

[B]

I see. So theoretically, somebody who is going through a rough divorce might get a different message on your platform and someone who's going through an easier one might get one that's, that's softer. Someone who's been married for 10, 20 years might get one that's different from someone who's just kind of got married quickly and is trying to untangle their marriage. Got it. And you're saying I don't want to have to write 50 different drip campaigns, but all of these different people are completely different. I think I could, I could do this in AI.

[A]

Exactly, exactly. Did it work and have every. It, it did. Give me an example. So I want to, I want to kind of walk your well, before, before.

[B]

You show me what you're doing, give me an example of like what it has been able to do for your business.

[A]

Okay. So every day I have a cron job that basically looks at key marketing stats and then it passes Those stats to opus 4 or 5 and then it generates an email with recommendations on what is the one thing I should do to improve my marketing funnel today. So this happens in the background, right? And I read the email yesterday and that's a whole nother fun thing I could talk about is how do you automate insight every day? So got the email and it said, Ryan, you have, you know, these five people that have clicked three different times on your email drips. You know, you should probably do something about that. And I was like, good idea. Opus 4. 5. Thank you, Amp. And I basically went and said, let's build a custom email drip for those people, right? And so what it did is it collects, okay, these are the, you know, five, ten people that clicked a bunch of times. Let's put them on an automatic email drip that is completely customized to them. That's highly engaged and like Paul Graham says, do things that don't scale, Right? And so the email said very simply, hey, I noticed you've been clicking on our emails. Like, I'm the founder of Untangle, I'm Ryan, and I would love to meet with you or help you in any way I can. And that email went out, and I immediately got a reply from one of those customers that was clicking on her emails but hadn't signed up to the free trial. And she said, I would love to meet. I was like, okay. And so I was like, do you want to meet on a video call? Do you want me to call you? Like, I'm not going to try to sell you anything. What do you want? She said, let's do a video call. Uh, and we had a video call about an hour ago. Um, and I learned all about her situation. And in the end, she's like, I'm gonna sign up for the free trial. And so she signed up. So it's like email automation, AI. You know, all this is beginning to work. It was really fun.

[B]

All right, let's see how you put it together.

[A]

Okay, so I'm gonna share my screen and just kind of walk you through visually how this thing works. Works. Okay. And of course, I had Amp build this for. For this show because I was like, I want to. I want to be able to explain this well for Andrew and, and his audience. So what are we talking about here? All right, we're talking about AI personalized drip emails. The idea is you. You have customers or leads that you want to do something. You know, you. You send them emails over time. We call this email drips or sequences. But in the past, you would use a tool like outreach, and you would pre write each of those emails, Right? I want email one sent on day two. This is what it says. Insert their name. I want email number two sent on day three. Here's the template. Very primitive in the world of AI. So what I did is build a system that uses AI to write each of those emails. So the first thing, step one is, is the lead enters the system, right? So whatever your funnel is, for me, it's a child support calculator. That's a common way that people want to enter into the divorce process. They're trying to figure out what their child support is. So the lead uses the calculator or chat, right? Okay, so then what happens? So then we create the drip campaign plus the context. So the agent goes in and says, okay, we're going to enter in this email address into the this campaign, and we're going to insert the context for that customer. And this is the key, right? So we live in a world. Now, when you collect these leads, you have information on them, right? Whatever they gave you. Plus you can actually use tools like parallel AI to go out and scrape the Internet to find more information. You can get a lot of context on that customer. So you store that context right in your database, and then you put that in your email drip campaign table. So person comes in, generates a lead, you store their context and you put them in a table to say that they're an email drip and you match.

[B]

It with information from parallel.

[A]

Exactly. You can. So the neat thing is like for our lead funnels, we get a lot of valuable data about that customer without having to do that. But you could use parallel, you could use the X API, you could use LinkedIn. There's a lot you can do to gather enriching data for that customer. So that is step two. All right, step three. So we've got them in the funnel, we've created the campaign with contacts, we've put them in the database table. And now what we do is we trigger an hourly cron job. So the idea is, are there any folks that are up for an email? Let's go ahead and grab those and queue those to schedule. This is not rocket science. Pretty straightforward. All right, so after the hourly cron job, we're going to. All right, so a couple things. We have to normalize user profile. So you have to think about, are you sending the same email to multiple people? Are they on a different email drip? How are we thinking about this specific email to make sure that you're not spamming anybody? Pretty straightforward. And then this is the key, right? So what you do is you take that user, you normalize their data, and then you take the context and then you feed it. You just make a call to your favorite LLM. At the moment, I'm primarily using Opus 4.5. Then you have a system prompt that says, here's the data that you have on this customer. Here's the goal of this email. Here are the rules. You have to also do things like you have to specify the feature set of your app. You do not want the LLM hallucinating features for your app. That's always terrible. Then you write this custom email. It feels like it's written by a human. It's really pretty astonishing. So you queue that up and then we're on to step six. Then you use resend. So there's resend, there's sendgrid, and there's a lot of email sending tools these days. Resend is just great. I love it. I'm not being paid to say that everyone's using resend.

[B]

Why resend over the others?

[A]

You know what's funny is I think they crushed it on AEO Answer Engine Optimization. Um, because when I was talking to Amp about this, you know, like, hey, I want to send emails, you know, programmatically, it was like, why not resend?

[B]

That's what happened to me. You're talking about Amp code the company.

[A]

Yeah. Amp suggested, you know, cloud code. Probably does the same thing. It suggested resend.

[B]

Okay, got it. That's funny.

[A]

Thought that was pretty great. And then, you know, using resend, or your favorite, you know, email sending tool, you want to check for a couple things. Did they open it? Did they click it? Did it bounce? What's common today is often not to use open because it'll degrade your sending score. So we just use click and bounce. So we measure clicks and then we just check if any emails bounce.

[B]

To do what? To know whether they engage. To know whether you should send the next message or to know how effective the message was.

[A]

Both. And when you get click data, you can do things like I did, but you can layer another step on top. Right, I see. So, you know, we had a lead come in. They used our child support calculator. Great. The daily report showed me that she was engaging by clicking on multiple drips. Right. And then I realized, oh, I should add another layer of engagement on top, which is another automated email drip, which encourages them to schedule a meeting with me. And then boom, I got a free trial out of that today. Then of course, after that email sends, then you update the campaign to say it was sent and then you load in the next one to send. Pretty straightforward. Then finally you have a nurture loop, which basically I have saying once someone reaches the end of an email drip, and typically email drips are five to seven emails, typically they're two to three days apart. So you get to the end of that. And I can't remember who is talking about this on a podcast. I think it was Wade from Zapier. He was on Clairvaux show. And he said, you know, AI allows you to touch every single lead you've ever had. Infinitely, right? In the past, all of us humans, we get exhausted, right? Like, oh my God, we have 30,000 leads. We haven't emailed them in a long time. Like, what do we say? How do we make it personalized? But we live in the world of AI now. And so every single person that finishes that email drip should be put on a long term monthly nurture drip, right?

[B]

And that's also customized.

[A]

Yeah, absolutely customized. So the beautiful thing is customize to them, customize to what you've already said to them, customize to what they've clicked, right? Like this is all very valuable data. So all you do is you feed into the LLM every time, all the context on the previous email drips, the previous clicks, and you can generate very helpful long term nurture loops. I'll stop sharing now. The beauty though is that you can deliver real value. So everybody hates marketing email drips, right? Because they're usually spammy. They, they're not actually helpful. But if you're doing two things right, if you're doing your AEO strategy content correctly, which means you've created hundreds, if not thousands of articles that actually answer people's questions, then what you can do is in each of those nurture loops, you can say, you can feed to the LLM, say, here's everything that we've said to this person, here's the data we have on this person. Look through our content library and find relevant articles that will answer their questions and then suggest those articles to help them. And you just get this beautiful feedback.

[B]

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

[A]

That's the primary loop. But the thing I want to point out that's very important here is that 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 floor tiling or, you know, snow removal. 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.

[B]

Okay, I'm going to ask you to bring that back up on the screen with the whole flowchart so we can talk about it. By the way, you mentioned Zapier. They're, they're sponsoring this podcast. Are you using Zapier? What are you using them for?

[A]

I love that. That's awesome. I've just been a massive fan of Wade and the team and Zapier for years and I think, gosh, Zapier has been around for probably, what, 15 years or something.

[B]

I feel like, honestly, between you and me, that's kind of a challenge for them because we have 15 years of expectations from them as the company that connects any two other pieces of software and we forget that they are so AI driven. I'll give you an example. This morning I was thinking I would like to set up Claude cowork to connect to Grain and then from Grain, pull out my transcripts, then use that to organize an email for me to tell the team about what I've been doing that might be relevant to them because I forget to update people and I'm in my own little world here in my home here in Austin, working and I couldn't connect Claude to Grain. So I said, okay, great, that's where Zapier comes in. They actually will have a connector into Claude that connects to all their other tools. And I started working with that and then I realized, what the hell am I even doing? I now have to have Claude connect to Zapier, connect to Grain to do this weird out thing. I went right to Zapier and I said, can you do this for me? And Zapier just pulled it together and created an email in Gmail for me. And even I, someone who's now been deep in their world, forget about their connection.

[A]

Yeah, I need to do that more. It's funny because I was in SF last week and I walked by a Zapier sign and I thought, gosh, I need to use their automations more because I'm probably making a lot of things hard for me personally. So I big fan of them and the team and I think the way Wade thinks about things is clever. I mean, he's converting the Entire company to AI first and really using the tools. So, yeah, that's where that, that connection came in.

[B]

All right, so a lead comes in. That's this top, 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. 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 infrastructure. Right. So literally all I did is I opened up AMP and Untangle is a Next JS app. Right. So it's all in typescript. 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 Claude 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.

[B]

Can you, can you do that now to show us and essentially.

[A]

Yeah, sure.

[B]

Yeah. What do you. What are you using to access amp?

[A]

I use Ghosty primarily, which is. Let me switch back to this screen.

[B]

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

[A]

Okay, so AMP is an amazing coding agent. 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 they have their own agents. But in VS code, for instance, you can use AMP if you like that. I am more of a command line interface type of guy. I like the cleanness of this. So what I'm going to do is start up amp. I'm going to make this a little bigger. This is my coding agent. What I do is I hop in here and I just start asking AMP to do things right. So we've got. Usually what 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. And Then create a markdown file so I can share that. All right, so AMP is going to go off and do that. I'm actually secretly showing you a new feature. If you see deep here, this is a mode. We're actually using GPT 5.2 instead of Opus 4. 5. So a little bit of inside baseball there. So what's happening is it's cranking, it's thinking about stuff, and it's going to end up giving me what I want. Here you can see it's creating a task, and it's going to complete that task and do what it needs to do. Now what I actually do is I actually run three of these agents at a time. So I actually have 3amps open any one time. And I'm usually working on three different parts of the app at once in.

[B]

Three different ghosty windows. Or all in the same one, right?

[A]

Yeah, three different ghosty windows.

[B]

Okay.

[A]

And the reason why is because I can just get so much done. Like now I have, and sometimes I feel like three is not enough, that I have all this agent power and I'm actually not shipping stuff quickly enough.

[B]

Yeah, I picture you having three of them working. While they're working, you go on Twitter and you send a message out.

[A]

Yep, okay. A little. A little life hack. That's kind of fun. So recently I had a. A x article get. I think it was 1.8 million views on X. And it was about this new RALPH loop where people are using a loop to code. But the way I actually wrote that article was I set up RALPH locally using amp. And I said, amp, let's get this going. Help me set it up. And then at the end of that, I was like, why don't I just write an article about what we just did? And so in the same thread, I said to Amp, why don't you go ahead and write a markdown article that I can share about how we set up ralph? I took that markdown, I edited a bit, and then I went into X and I posted and it decided to go kind of hyper huge. Hyper crazy huge. So that's amp. I use it every day. I love it. Obviously, I work at amp, so I'm going to say that, but I really do think it's one of the best coding agents in the world. Okay.

[B]

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 that's different from others?

[A]

So I think this is the crux of this 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? So what we build is now becoming more important than how fast we build it. 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? Am I building the right things quickly enough? So the way I look at it is I use Fizzy, which is 37 signals new app for my backlog. I add things to my backlog and then when I realize, okay, these are some features I want to build out, what I do then is I create a product requirement doc prd 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? 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? You know, what is the moat now? And it's, it's disconcerting isn't are you.

[B]

Building the right thing about are you getting customers?

[A]

Yeah, it should be, but it's not.

[B]

I do feel like there's less excitement around how do I get customers? Like, your post about RALPH went insanely viral. And then Greg Eisenberg did an interview with you where you walked him through how you do it. The thing that I 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, 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's paying attention to it or it's just not flashy enough for us to talk about?

[A]

I think because marketing is the real work and people don't like to talk about it. Actually, your go to market strategy and your acquisition and your funnel and your CAC and your ltv, these are actually the real business things that we all need to be thinking about. They're a little less sexy and a little less exciting. So I'll tell You this. I think the loop that I briefly mentioned is actually probably the most valuable thing I could talk about today, which is every day just go to amp, go to cloud code, go to your favorite agent and say, I want an email every day with one to two key actions I should take to acquire more customers at our 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 increase our engagement, to increase our numbers. And actually that loop has led me very quickly to optimizing the business in a real way versus what features should I build?

[B]

What are you giving it? What kind of access are you giving it to help make that decision?

[A]

So what I basically do is I think about a couple things. So what's happening with our lead magnets? How many visits did the page get? And we use GA4, which has an API to get that. Right? Okay, how many visits do we get?

[B]

How many visits do we get on the lead magnet? And is lead magnet the calculator that you and I were just talking about?

[A]

Yep.

[B]

Okay.

[A]

And we have several of them, but. But that's, that's one of them. Okay, so how many visits did you get? How many leads did you get? So a simple conversion number on that. Right. And then it in your lead magnet. Ours happens to be a questionnaire, so it's got questions. Then we also feed into it the questions and the drop off rate between each question. That's all in the database, right?

[B]

It's all coming in from GA.

[A]

Mostly. So there's GA4, which we use. And then in our own database we have things like which question are you on in the lead magnet? And we store all that in the database. So I think the bigger lesson here is you need context. Like the agent needs context to give you valuable data. So what you need to do is go into amp or cloud code and say, okay, we've got this lead magnet. What information do you need in order to help us to optimize that?

[B]

Got it.

[A]

And then AMP says, oh, well, I need to know what the conversion rate is from question one to question two to question three to question four. And you go, oh, okay, build it. And then it goes, great. Then it goes and puts that data into the database. And then what you do is you go back to the cron job and you say, okay, now grab that data every day. So what you're doing actually is like context gathering. And then you. You suddenly have a agent that has all the context it needs and basically is a VP of marketing or VP of sales, you know, for 15 cents a day.

[B]

What about this? The idea for a calculator came from you, from your years of experience. Can it actually give you that kind of idea?

[A]

Let me think. I'm trying to remember how I got the idea for a calculator. I think I talked to Amp about it.

[B]

I'm just saying, basically said, what would you say?

[A]

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

[B]

So then it's coming up with an idea like that. You're saying, yes, I think I could do that. That is where I want to spend my attention. You create the calculator. You then you then get some amount of data from it, and you say, what do you need to do in order to optimize this? It starts telling you what you should give it access to. You give it access to that, and then you say to it, I want every day an email that tells me how things are. And are you also asking what are your recommendations?

[A]

Yep. Yeah. I basically say, what is the one or two things we must do today? Because as you know, like, analysis paralysis is a real thing. Right. And you could get all this data. But the truth is, you just need to make one decision today to increase your number. I'm thinking the next step is not just to get the email, but actually have Amp implement the suggestion. And then I wake up to a PR that I review where it's actually done the thing that it suggested, and then I get to review that instead.

[B]

What's one type of insight or what's one specific insight that it gave you that a human being wouldn't have had?

[A]

I think these are all insights that a human being would have had, but I would have had to pay a VP of marketing $250,000 a year to have that insight.

[B]

What type of insight Is it getting you? Because you've been a phenomenal marketer your whole frickin life. Like, I remember. Actually, I totally forgot that you ran Drop Send. I remember living in LA at the time and people were talking about how you were building in public, and you were being so open and vulnerable about it that it just was shocking and everyone paid attention. Then they would use Drop Send to share files. It was basically right Dropbox before Dropbox. And I totally forgot about it until I heard you on a podcast talk about that. So you know this stuff. I just want to get the type of insights that you would get from it that maybe wouldn't have occurred to you with all your experience.

[A]

That's kind of you to say that. And I've forgotten that we did Barenaked app, which is how we built.

[B]

Think about that too. I wasn't sure if my memory was good on that. It was. First of all, it was in public at a time when nobody was doing it, and you really showed people how to do it in public. And then you called it Barenaked, which also was attention getting on top of attention getting. Okay, so that's why I'm asking you about this.

[A]

It worked.

[B]

It worked.

[A]

It did work. But as you know, most of marketing, running a company is not sexy at all. And all that Amp is doing for me is really reminding me of fairly basic, obvious things that I need to do that I haven't done yet. And that's actually very valuable. Right. So when Amp basically read this daily email and said, oh, you have, you know, a number of customers that have clicked more than three times on these email drips. You should do something about it. Right. That. That's not rocket science, but it's an actionable, valuable insight. Right, right. That. That I would have had to have, or I would have had to pay someone to have. And you're very kind to say I'm an experienced marketer, but. But just because you have experience doesn't mean that you see opportunities consistently. Right. And all you're doing is increasing your batting average. Right. It's like, it's more likely that I'll see a good suggestion if I'm getting a smart suggestion once a day. Right. And so I think that's what's really happening. And it's extremely. It's. I just feel I can't believe this is real. I know. I think Ilya was saying this on his Dwarkesh episode, like, isn't it amazing? This is real. That, you know, predicting the next token led to this, like, Intelligence explosion. And I can have an email sent to me every day that says, hey, Ryan, here's what's happening with your marketing funnel and here's something you do to improve it.

[B]

You've just told me what you give it, that you have internal access to your data sources, your numbers, your conversions. What do you do to give it outside influence? If anything.

[A]

Very little. Most of it is context on your user and correct information. So the external information I give it is very specific. But I only had to do it once. Right. So it's the Connecticut divorce statutes, it's the Connecticut child support guidelines, it's, you know, Connecticut, Connecticut, Connecticut specific documents in markdown. Right. That are fed, you know, into the agent as a tool. So you got to give your agent the right tools in the right context. But I don't think you need to do as much like external enrichment as people think.

[B]

But you're not doing things like I want you to find these types of tweets and then analyze what they're doing that they're showing off about. No, you're not at that stage. Or do you think you'll ever need.

[A]

To maybe, you know, and I do some enrichment, you know, on high, you know, high value sales targets, for instance. That's a little different, I think. You know, basic B2C lead gen lead marketing. I think it's probably overkill. I think if you can just have some basic information on a customer with a clear value prop, you could do a lot with that. But this is the thing, most people aren't even doing what I showed you, right? They're not writing custom emails using a large language model. Start there and then iterate and then eventually after a year, you'll be this machine. But just take step one.

[B]

Honestly, I feel like that's a business on its own. Somebody should be watching this and saying, maybe you and saying convertkit is making bank. Beehive just raised a ton and they just keep growing and all they're doing is a better version of past email. I think what we could do is create really totally customized email. And then we also have network effects because we start to understand the user across multiple mailing lists. And then not only that, we start to enhance it with your own data and that becomes like proprietary internal information.

[A]

There you go. Somebody take this pitch and run with it. I've got another company to build, so.

[B]

All right, Ryan, thanks so much for walking me through this and I appreciate you coming on here.

[A]

It was a blast. Andrew, you're an amazing host and I'm excited that we could offer some value here, so thank you.

[B]

Oh, yeah.