RSS feed
Ryan Carson: Why isn’t every email customized for the customer? So it’s completely personal. So I’m gonna share my screen and just kinda walk you through visually how this thing works.
Andrew Warner: Ryan Carson is a three time founder and he’s building untangle, which is AI for divorce. Let’s get it 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?
Ryan Carson: Uh, 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, um, my new startup.
And then I thought, what am I doing? Why don’t I have AI write the email drips? Uh, and ended up, you mean like the series of emails? Yeah. Yeah. Okay. 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 build a workflow and I’m very happy with that.
Andrew Warner: 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. 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 wanna 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.
Ryan Carson: Exactly, exactly. Did it work and have every it, it did. Um, gimme an example. So I wanna, I wanna kinda walk your, uh, well, well before,
Andrew Warner: before you show me what you’re doing, gimme an example of like what it has been able to do for your business.
Ryan Carson: Okay, so, um, every day I have Aron job that basically looks at key marketing stats and then it passes those stats to Opus four five, 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.
Uh, yesterday. And that, that’s a whole nother fun thing I could talk about is how do you automate, uh, insight every day. Um, 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. Um, you know, you should probably do something about that.
And I was like, good idea. Opus four, five, thank you amp. Um, and I basically went and said, let’s build a custom email drip for those people. Right. Ah, okay. And so what it did is it collects, okay, these are the, you know, five, 10 people that clicked a bunch of times. Let’s put them on a, an automatic email drip that is completely customized to them, that’s highly engaged and.
And like Paul Graham says, uh, 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, to meet with you or help you in any way I can. Um, and that email went out and I immediately got a reply from one of those customers that was, uh, 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 wanna meet on a video call? Do you want me to call you? Like, I’m not gonna 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. Wow. So it’s like email automation, ai, you know, all this, uh, is beginning to work. It was really fun.
Andrew Warner: All right. Let’s see how you put it together.
Ryan Carson: Okay, so I’m gonna share my screen and just kinda walk you through visually how this thing works. Okay. And of course, I had amp build this for, for this show.
’cause I was like, I wanna, I wanna 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. Um, 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, um, or sequences. But in the past, you know, 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 their name. I want. Email number two sent on day three. You know, here’s the template.
Very primitive in the world of ai, right? So what I did, um, is build. A system that uses a, to write each of those emails. So the first thing, step one is the lead enters the system, right? So whatever your funnel is, you know, for me, um, it’s a child support calculator. That’s a, uh, a common way that people, uh, want to enter into the divorce process.
They’re trying to figure out what their child support is, right? So the lead uses the calculator or chat, right? Okay. So then what happens? So then. We create the drip campaign, uh, plus the context. So the, uh, the agent goes in and says, okay, we’re gonna enter in this email address, uh, into this campaign, and we’re gonna 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? Mm-hmm. Whatever they gave you. Plus you can actually use tools like parallel, uh, dot ai to go out and scrape the internet to find more information. You can get a lot of context on, on that customer.
So you store that context right in your database. Um, and then you put that in your email drip campaign table. So ca person comes in. Generates a lead. You store their context and you put them in, uh, a table to say that they’re an email drip. Got it. And you, and you enrich
Andrew Warner: it with information from parallel.
Ryan Carson: Exactly. You can. So the neat thing is, like for our, our, uh, lead funnels, we get a lot of valuable data about that customer, uh, without having to do that. But you could use parallel. Um, you could use the XAPI, you could use LinkedIn. There’s a lot you can do to gather enriching data, uh, for that customer. So that is step two.
Alright, step three. So we’ve got them in the funnel. We’ve created the campaign with context. We’ve put them in the database table. And now what we do is we trigger an hourly CR job. Um, so the idea is, are there any folks that are, uh, up for an email? Um, let’s go ahead and grab those and queue those to, to schedule.
This is not rocket science. Mm-hmm. Um, pretty straightforward. All right. So after, uh, the hourly CR job, um, we’re going to, all right, so a couple things. We have to normalize user profile. So you have to think about, are you, uh, sending the same email to, to multiple people? Are they on a different email drip?
Um, you know, how are we thinking about this specific email to make sure that you’re not spamming anybody? Um, pretty straightforward. Um, and then this is the key, right? So what you do is you take that user, you normalize our data, and then you take the context and then you feed it. Uh, you just make a call to your favorite LLM.
At the moment, I’m primarily using Opus four five. Um. And then you have a system prompt that says, you know, here’s the data that you have on this customer. Um, here’s the goal of this email. Um, here are the rules. Um, and 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. Um, yeah. And then you, you write this custom email that, that it feels like it’s written by a human. I mean, it’s really pretty astonishing. Um, so you queue that up. And then we’re onto, uh, step six. Then you use Resend. So there’s resend, there’s SendGrid, there’s a lot of, uh, uh, email, um, sending tools these days.
Resend is just great. I love it. I’m not being paid to say that. Um,
Andrew Warner: everyone’s using Resend. Why resend over the others?
Ryan Carson: You know, it’s funny is mm-hmm. I think they crushed it on a EO answer engine optimization. Ah, um. Because when I was talking to AMP about this, you know, like, Hey, I wanna send emails, you know, programmatically, it was like, why not resend?
So
Andrew Warner: that’s what happened to me. Like you’re talking about AMP Code, the company?
Ryan Carson: Yeah, amp. Amp suggested, you know, cloud Code probably does the same thing. It suggested Resend.
Andrew Warner: Okay, got it. It’s funny. Uhhuh,
Ryan Carson: I thought that was, that was pretty great. Um, and then, you know, using Resend or your favorite, um, you know, email sending tool, you want to check for a couple things.
Did they open it? Did they click it? Did it bounce? Um, what’s common today is often not to use open, uh, because it’ll degrade your sending score. So we just use click and bounce. Um, so we measure clicks and then we just check if any emails bounce. Um, so to do what, it’s pretty standard practice to know
Andrew Warner: whether they eng engage to, to know whether you should send the next message or to know how effective the message was.
Ryan Carson: Uh, both and it, when you get click data, you can do things like I did. Which you can layer another step on top. Right. I see. So, uh, so, you know, we had a lead come in. They used our child support calculator. Great. Uh, 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.
Um. And then boom, I, I, I got a free trial out of that today. So, um, and then of course after that email sends, then you update the campaign, uh, to say it was sent and then you, uh, load in the next one to send, um, pretty straightforward. And then finally, um, you have a nurture loop, which basically, uh, I, I have saying.
Uh, this, once someone reaches the end of an email drip, and typically email drips are, you know, five to seven emails. Mm-hmm. Typically they’re two to three days apart. So you get to the end of that and. I, I can’t remember who is, who is talking about this on a podcast. Uh, I think it was Wade from Zapier. He was on, uh, Claire V’s 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 it in a long time. Like, what do we say? How do we make it personalized? 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. And that’s also customized. Yeah, absolutely. Customized So, so customized to them. The beautiful thing is customized to them. Customized to what you’ve already said to them. Mm-hmm. Customized to what they’ve clicked. Like this is all very valuable data. Um, so all you do is you feed into the LLM every time, all the context on the previous email drips, the previous clicks.
Um, and you can generate very helpful long-term nurture loops. Um, I’ll stop sharing now. The. The beauty though is that, uh, you can deliver real value. So everybody hates marketing email drips, right? Because they’re usually spammy, they’re not actually helpful. But if you’re doing two things right, if you’re doing your a EO 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.
Uh, you can feed to the lm say, here’s everything that we’ve said to this person. Here’s the data we have on this person. Um, look through our content library and find relevant articles that will answer their questions and then suggest, um, those articles to help them. And you just get this beautiful feedback loop.
Andrew Warner: So you, 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 gonna show or is that it?
Ryan Carson: Um, that’s the primary loop. Um, but the thing I want to point out that’s very important here mm-hmm. Is that, um, probably everybody listening to this show is thinking about building an.
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, uh, statute, search case, law search, uh, child support guideline search, right?
These are very specific to divorce in Connecticut, right? But Grace writes all of our a EO content, right? Mm-hmm. 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, uh, floor tiling or, you know, snow removal. Um, you’re gonna 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.
Andrew Warner: Okay. I I’m gonna ask you to bring that back up on the screen with the whole flow chart so we can talk about it.
By the way. You mentioned, let’s do it, Zapier, they’re, they’re sponsoring this, uh, podcast. Are you using Zapier? What are you using ’em for?
Ryan Carson: Oh, I love that. That’s awesome. Um, I’ve just been a massive fan of Wade and the team and Zapier for years. I mean, and I think, gosh, Zapier’s been around for probably.
What, 15 years or something.
Andrew Warner: I feel like, honestly, between you and me, that that’s, 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, 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. ’cause I forget to update people and I’m in my own little world here in, 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, 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 amazing, who’s now been deep in their world, um, forget about their connection.
Ryan Carson: Yeah, I need to do that more. That, and it’s funny ’cause I was in SF last week and I walked by mm-hmm.
A Zapier sign, uh, and I thought, gosh, I need to, I need to use their automations more because I’m probably making a lot of things hard, uh, for me personally. So I big fan of them and the team. And I think the way Wade thinks about things is, is clever. I mean, he’s, he’s converting the entire company to AI first and really using the tools.
So, um, that’s where that, that connection came in.
Andrew Warner: Alright, 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, I know what’s actually manually sending it out. It’s resend, but what have you built internally that’s doing all this?
Ryan Carson: So, gosh, this is the beauty of the world we live in right now. So I’ve UI 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? Mm-hmm. 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 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 we open up AMP and said, I want to build an email drip.
Uh, can you,
Andrew Warner: can you do that now to show us? And essentially,
Ryan Carson: yeah. Sure.
Andrew Warner: Yeah. What are you, what are you using? Uh, to Access amp?
Ryan Carson: I use, uh. Ghosty primarily, which is, um, let me switch back to this screen.
Andrew Warner: 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?
Ryan Carson: Okay, so AMP is an amazing. Uh, coding agent. Mm-hmm. 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 Amp. Um, I’m gonna make this a little bigger.
Andrew Warner: Mm-hmm.
Ryan Carson: And so this is my coding agent, right? Okay. So what I do is I hop in here and I just start asking amp to do things right. Um, so we’ve got a, 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. Mm-hmm. Uh, this is a mode we’re actually, we’re actually using, uh, GPT five two instead of Opus four 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 gonna end up, um, uh, giving me what I want.
Um, here you can see it’s creating a task, um, and, uh, it’s gonna complete that task and, and do do what it needs to do. Now what I actually do is I actually run three of these agents at a time.
Andrew Warner: Mm-hmm.
Ryan Carson: Um, so I actually have three amps open at any one time, and I’m usually working on three different parts of the app at once.
Um.
Andrew Warner: In three
Ryan Carson: different
Andrew Warner: ghosty windows or all in the same one, right?
Ryan Carson: Yeah, yeah, yeah. Three different ones, three different ghosty windows.
Andrew Warner: Okay.
Ryan Carson: Um, and the reason why is because I could just get so much done. Mm-hmm. 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.
Yeah. I picture you
Andrew Warner: having three of them working while they’re working. You go on Twitter and you send a message out.
Ryan Carson: Yep. Okay. A little, a little life hack. That’s kind of fun. So recently I had a a x article, um, get, I think it was 1.8 million views on X. Um. It was about this new Ralph Loop where people are using a loop, a loop to, to code.
But what I actually, 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 I, 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.
Um, I took that markdown, I edited a bit, and then I, uh, I, um, went into X and I posted, and it decided to go kind of hyper,
Andrew Warner: huge,
Ryan Carson: hyper, uh, crazy. Huge, so, so that’s amp. I use it every day. I love it. Obviously I work at amp, so I’m gonna say that, but I really do think it’s, it’s one of the best coding agents in the world.
Andrew Warner: 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, or how are you breaking down the tasks? How are you giving it instructions that’s different from others?
Ryan Carson: 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? Um, so what we build is now becoming more important than how fast we build it. Mm-hmm. 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, 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, are we fast enough? Are we gonna get out built by everybody else now? Um, you know, what is the moat now? And it’s, uh, it’s disconcerting.
Andrew Warner: Isn’t, are you building the right thing about, are you getting customers?
Ryan Carson: Yeah, it should be,
Andrew Warner: but it, it’s not. Yes, 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 Isenberg 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.
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?
Ryan Carson: 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 co 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.
Andrew Warner: Mm-hmm.
Ryan Carson: At our, uh, desired cac. Right. And you build out a little script. It’s very simple. It’s Aron job, it runs at midnight, and you basically feed the right information into the model.
Mm-hmm. 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, 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?
Andrew Warner: What are you giving it? What kind of access are you giving it to help make that decision?
Ryan Carson: So, um, what I basically do is, uh, I think about. The, a couple things. Okay. So what’s happening with our, our lead magnets, um, how many, uh, visits did the, the page get? And we use, uh, uh, GA four, which has an API to get that right.
Okay. How many visits did we get?
Andrew Warner: Okay. How many visits did we get on the lead magnet? And is lead magnet, the calculator that you and I were just talking about?
Ryan Carson: Yep. Mm-hmm.
Andrew Warner: Okay, great.
Ryan Carson: And we have several of them, but, but that’s, that’s one of them.
Andrew Warner: Okay.
Ryan Carson: Um, so how many visits did you get? How many leads did you get?
So a simple conversion number on that. Yeah. 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, uh, the questions and the drop off rate between each question. Okay. That’s all in the database, right?
Andrew Warner: It’s all coming in from, um, from ga.
Ryan Carson: Um, mostly, so there’s, there’s GA four, which we use, and then in the, in our own database we have things like, uh, which question are you on in the lead magnet? Um, and we store all that in the database. Okay. So I think the, 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, 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?
Andrew Warner: Got
Ryan Carson: it. Right? And then, and then AMP says, oh, well I need to know, you 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. And then it goes and puts that data into the database. And then what you do is you go back to Theron job and you say, okay, now grab that data every day. Mm-hmm. So what you’re doing actually is like context gathering. Um, and then you, uh, you suddenly have a agent that has all the context it needs and basically is a VP of of marketing or VP of sales, you know, for 15 cents a day.
Andrew Warner: 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?
Ryan Carson: Huh? Let me think. I’m trying to re, I’m trying to remember how I got the idea for a calculator. Mm-hmm. Um, I think I talked to Amp about it. Um,
Andrew Warner: and
Ryan Carson: just say Amp. Yeah. Basically said,
Andrew Warner: yeah.
What, yeah. What would you say?
Ryan Carson: You know, I’d say amp, 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, we could cal calculate alimony, we could calculate interesting, 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. Talking. 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, got it. As fast as you can.
Andrew Warner: 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 wanna 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?
Ryan Carson: Yep. Yeah, you
Andrew Warner: are.
Ryan Carson: I basically say, what is the one or two things we must do today? Um, 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, uh, today to increase, um, your number. Um, I’m, I’m thinking the next step is, is. Not just to get the email but actually have amp implement the suggestion. Uh, 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.
Andrew Warner: What’s one type of insight or what’s one specific insight that it gave you that a human being wouldn’t have had?
Ryan Carson: Um, I think these are all. Insights that a human being would’ve had, but I would’ve had to pay a VP of marketing, you know, $250,000 a year to have that. Insight.
Andrew Warner: What type of insight is it getting you?
Because, because you, you’ve been a phenomenal marketer your whole fricking life. Like I remember actually, I totally forgot that you ran drop end. 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 drops. 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, what’s in what? I just wanna get the type of insights that you would get from it that maybe wouldn’t have occurred to you with all your experience.
Ryan Carson: Um, that’s kind of you to say that, and I’ve forgotten that. We did, uh, um, bare Naked app, which is how we built, um, public.
Andrew Warner: Think about that too. I wasn’t sure if that, if I, 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 the bare naked, which also was attention getting on top of attention getting. Okay. So that’s why I’m asking you about this. It worked,
Ryan Carson: it, it worked, it did work. Um, but the, but the, you know. As you know, most of marketing, running a company is not sexy at all and, and. All that AMP is doing for me is really reminding me of, of fairly basic, obvious things that I need to do that I haven’t done yet, and that 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. Mm. Right. That, that’s not rocket science, but it’s an actionable, valuable insight. Right, right. That, that I would’ve had to have, or I would’ve 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 consist. Okay, 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?
Um, and so I think that’s what’s really happening. Um, and it’s extremely. It’s, I just feel, I can’t believe this is real. I know. I think, um, Ilio was saying this on his Dke 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 could do to improve it.
Andrew Warner: 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?
Ryan Carson: Um, very little. Um, most of it is context on your user, um, and correct information. Um, so, so the external information I give it, uh.
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? Yeah. That are fed, you know, into the agent as a tool. So you gotta give your agent the right tools in the right context.
Um, but I don’t think you need to do as much like external enrichment as people think. Um,
Andrew Warner: but you’re not doing things like saying. 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 to have that?
I don’t.
Ryan Carson: Maybe, um, you know, and I do some enrichment, you know, on high, you know, uh, high value sales targets, for instance. Um, that’s a little different. I think, you know, basic B2C, uh, you know, lead gen, lead marketing. I think it’s probably overkill. Um, 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, 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. Um, you know, start there,
Andrew Warner: no.
Ryan Carson: Right? And then, you know, iterate and, and then eventually after a year you’ll be this machine, you know? Um, but just take step one.
Andrew Warner: Honestly, I feel like that’s a business on its own. Like 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.
Ryan Carson: There you go. Somebody take this pitch and run with it. I’ve got another
Andrew Warner: company
Ryan Carson: to build. So,
Andrew Warner: alright, Ryan, thanks so much for walking me through this. Um, and I appreciate you coming on here.
Ryan Carson: It was a blast, Andrew. You’re an amazing host and, uh, I’m excited that we could offer some value here. So thank you.
Andrew Warner: Hell yeah.
