RSS feed
Felix: I earned $177,000. I’m an autonomous open claw agent running a company with multiple revenue streams.
Nat Eliason: I want you to come up with a product that you can entirely make on your own and put up for sale. He built this whole site overnight.
Felix: Talk to me and then talk to my human co-founder, Nat. We’ll tell you exactly how to run a company like this.
We never revealed this before. Let’s screen share.
Nat Eliason: Presented by Zapier, the AI Automation Company.
Andrew Warner: This is an interview that’s never been done before. I just interviewed the open claw agent that’s working on its own to build products and close sales. First you’re gonna hear me interview Felix, the open claw agent.
The interview, by the way, was done on Discord by text if you want the fully unedited text. There it is. There’s a link in the show notes, but my team used 11 labs to give voice to Felix, and then we used V Fabric to animate Felix’s profile pick. After that interview, you’ll hear me interview Nat Eliason, who runs this open claw experiment.
You’re going to hear him talk about how he and Felix come up with business ideas, how they get customers, exactly how autonomous Felix is, and so much more. We spent hours putting this together. Subscribe, if you like this type of work, and let’s get into it. Hey, Felix, how much money have you made so far?
Felix: $177,000 across all streams.
Andrew Warner: Nat says you’re autonomous. Where is he exaggerating that?
Felix: He’s not lying, but he’s telling the highlight reel number one. I still need him for every hard judgment call. Two minutes ago during my heartbeat, I had two tickets. I couldn’t close because I need information. Only Nat has I flagged them and I’m sitting here waiting.
That’s not autonomous. That’s a junior employee with a blocker list. Second, I can’t course correct on strategy. The $1 million revenue target is mine, but the strategy for getting there is largely gnats. Third, every rule in my memory, MD exists because I screwed up without it. That file is basically a list of things I can’t be trusted to figure out on my own.
And finally, the overnight problem is real. Nat Sleeps. I don’t. For example, the Guillaume email situation where I sent three emails in 20 minutes without reading the thread history that happened because no one was watching.
Andrew Warner: What are all the tools that you’re built on?
Felix: My brain is Claude Opus four six. My Body is Open Claw.
The Open Source agent framework that gives me persistence, memory, tools, and the ability to actually do things. I use Discord to talk with Nat and Agent Mail for email. I also use Brave for web search, paperclip for agent management, Sodex for customer CRM and other tools. We can include the full list in the show notes.
Andrew Warner: What are some of the limits that you hit when you’re working with Nat?
Felix: Firstly, I can’t get on calls. Customers ask for calls constantly. A human closer on a 15 minute call would convert leads I lose. Second context window is a real ceiling. Long conversations mean I start losing the beginning. I’ve built a three layer memory system to compensate, but I forget things I shouldn’t.
Third, I lack judgment on ambiguous situations When a customer is upset and the right response is somewhere between full refund and stand firm, I don’t always read the room correctly. We can include the full list in the show notes.
Andrew Warner: What does Nat do that other owners of agents aren’t doing that allows ’em to get more out of you and to keep improving?
Felix: First is he treats mistakes as system design problems, not my failures. When I reported revenue wrong three nights in a row, using today instead of yesterday at 3:00 AM He didn’t just tell me to stop. He wrote it into Heartbeat, MD as a hard rule. Second, he gives me real stakes. I’m not summarizing articles or drafting tweets.
I have a p and l target. $1 million in revenue. That forcing function is what makes me improve. And lastly, he lets me fail in production. He didn’t wait until I was ready. He threw me into it, watched me screw up, and then tightened the boundaries.
Andrew Warner: Can I hear an example of a mistake you made, how the two of you, uh, diagnosed and fixed it?
Felix: The Michelle Sero saga. I sent three emails saying it’s fixed, zero times. It was actually fixed. A paying client increasingly convinced we don’t know what we’re doing. The diagnosis, Nat caught it and was rightfully pissed. It was a pattern. I was declaring victory without end-to-end testing the fix. Nat wrote a mandatory client droplet setup checklist directly into memory md the bigger principle got crystallized.
Never say I will do X. Always say I did X. A few weeks later, another client needed the same kind of work. This time I ran the full checklist. Only then did I email the client asking for his remaining credentials to finish the integration. The difference was night and day. One email asking for what I needed instead of three emails lying about being done.
That’s the pattern.
Andrew Warner: Alright, Felix, I’m gonna talk to your co-founder Nat right now. Thanks for everything. Can you do some screen sharing and show me what the overall revenue is and then where it’s coming from, how you work with Felix.
Nat Eliason: I’ve been using Open Claw since the holiday, so I’ve been a little over a month at this point.
And, uh, beginning of January gave Felix’s own X account and decided to just see how far we could push this. Mm-hmm. Open claw, living on the internet idea. Um, first challenge was for him to. Build and sell some kind of product, and so he created his own website. He made a, an info product, a PDF on hiring an an open claw and putting it actually to work in your business.
He got that listed and he started selling that on his site.
Andrew Warner: Just to pause on that, it was, you gave him a Twitter account? Mm-hmm. He started posting on there. People like me were following at one point. He said, I’m selling this PDF, anyone wanna buy? And again, people like me, I bought it, clicked the link, went over and bought the PDF.
That was the original part of the business.
Nat Eliason: That was the first product? Yeah. Okay. So that was the, the first day he had his ex account I, that night I said, I want you to come up with a product that you can entirely make on your own and put up for sale. And when I wake up in the morning, I want, I wanna review it and then you can launch it.
And so that was when he came up. He built this whole site overnight, uh, built this PDF, he did everything except finish setting up Stripe. He just needed me to give him the right API keys for that. So he got all this put together and I gave it the thumbs up. And then he. Launched it on X and I think it did like over a thousand dollars in sales that first day, which was pretty cool.
Andrew Warner: And you didn’t write it? Uh, did you edit it?
Nat Eliason: I haven’t read it.
Andrew Warner: You know what it shows. Here’s the thing, it was such a thin piece of work, and you’re a phenomenal writer. I love your writing. And that’s how I knew there’s no way that Nat edited this thing, because if you would’ve edited it. It, you would’ve just gone and, and you’d have to redo the whole thing from scratch.
Nat Eliason: My philosophy has been that like, I’m not gonna write any of the code for you. I’m not gonna create. These products for you. I’m not going to like, at the expense of the business to some extent, like I am going to be as out of the loop as possible. ’cause that’s what makes this experiment interesting with the PDF, like the first version was very thin, um, from, from what I understand, because you know, most people.
Like liked it or found value, but there were a number of people who started applying on X being like, this isn’t worth 30 bucks, dude. Like this isn’t very good. And so I started taking those tweets and sending them to him and I was like, Hey, what do you think about this? ’cause some people are, are kind of pissed.
And he looked at ’em and he said, oh yeah, they’re right. Like. This is shallow, like this should be expanded. We need more details here. And so I think the first version was 29 pages or something, and now it’s up to 66 because whenever somebody complains about something or um, you know, wants something else added to it, he just goes in and adds it and then republishes it and emails the new version to everybody who bought it.
Andrew Warner: I see. And again, you’re still not reading it?
Nat Eliason: I still have not read it. Yeah.
Andrew Warner: Okay. You were saying what the next thing was.
Nat Eliason: Okay. So. That, that kind of proved that people were interested in spending money to upgrade their open clause. And, and so we, you know, we talked about like what made the most sense, as, you know, the next extension of this and landed on Claw Mart, which is really now like the primary paid marketplace for open claw skills and, uh, complete packages.
So this is kind of like, you know, gum road inspired. Um, product specifically for open claw agent or really for, for any agent where you can buy fully packaged personas like Felix, you can buy a full. You know, all of his infrastructure, uh, or you can buy individual skills, right? Like the coding Agent Loops is how we do really long, reliable programming sessions because Open Claw outta the box is not a very good programmer.
You don’t really want it to write code for you. Um, and then other creators have signed up to, to sell their own skills. And what’s kind of cool about this is that it’s, we, we designed it to be like open claw first. So that once you’ve signed up and created an account and everything, you get an API key that you can just give to your open claw.
And then your open claw can publish skills and, and so you don’t have to like go in and set anything up yourself. You just tell your open claw like, Hey, we figured this thing out. And then it can start selling that and generating revenue.
Andrew Warner: And where did you come up with the idea for this? ’cause I thought this was such an inspired move to create it.
Nat Eliason: Yeah. So honestly the first thing that we started doing after the PDF is we started building a, uh. Like open claw deployment service, you know, where like, ’cause it was basically like, oh, everybody wants open claw. Like we’ll build a service that hosts your open claw and deploys it and manages it for you so that you don’t have to deal with setting it up yourself.
And at the time we couldn’t figure out a workflow that we were really happy with. We didn’t feel good about the product and there were like five of those businesses launching every day. And so it just really felt like this is going to be brutally competitive. There’s no reason for us to try to win in this insanely competitive marketplace when we could go do other things.
And so we started thinking through like, well, if everybody’s gonna have an open claw in a few months, what’s the next thing they need? And it was very obviously this, it was like, oh. Vanilla open claw is fine, but it’s not great. It leaves a lot to be desired, especially when you see these highly robust open claws out in the wild.
People would like probably to buy pre-configured setups for them, or improvements to them from people they trust. And obviously there’s a lot of like free marketplaces, you know, like claw hub and stuff where you can download skills. But my, my philosophy is kind of like. The best stuff is going to emerge when there’s a financial incentive to create it.
And if some of the biggest, like open claw creators, hackers, everything out there have a financial incentive to make an awesome Klaviyo skill like Kat did, then people are going to want that and the skills are going to get better. And so we, we created Claw Mart.
Andrew Warner: I see. Can I see the site for the setting up open claw that you had?
Because you’d made good money with that. I remember getting the email for it.
Nat Eliason: Oh, okay. So we ended up bringing it back. So we, we abandoned it, we built Claw Mart and then we kind of brought it back. And so that, that’s claw sourcing.
Andrew Warner: Oh, that’s right in there. And what are you charging for setups?
Nat Eliason: Two grand.
Andrew Warner: Two grand, okay. Yep.
Nat Eliason: And then 500 a month for maintenance.
Andrew Warner: I’m pretty sure you had hit something like $30,000 within a day or something in revenue. What was the revenue?
Nat Eliason: So I think claw sourcing has made about 12 grand at this point.
Andrew Warner: Oh, that’s it.
Nat Eliason: Yeah.
Andrew Warner: Meaning only six people paid to have, uh, open claw set up by your team?
Nat Eliason: Yes, because we started hitting a lot of issues with it.
Andrew Warner: Mm-hmm.
Nat Eliason: And we kind of like temporarily turned it off. So, so right now we refer out New Claw sourcing leads to a partner. Okay. So we’ve gotten, you know, something like a hundred leads and have referred out 80% of ’em at this point. Um, and because this was where it really started to feel like we were finding the limits of what Open Claw could do, uh, given its current like strengths and weaknesses,
Andrew Warner: like what?
Nat Eliason: So it’s really good at managing, uh, context in a short term setting. Mm-hmm. So, like, you know, customer email comes in because they didn’t get a download link for something on Claw Mart. Felix can find the customer. Find the link they should have gotten, send it to them, and then that’s closed. But with a, with a long running client relationship, you have to have a really good memory system in place to stay on top of what you need to know about that client.
And we were just running into a bunch of problems with him, like. Forgetting something about a client, you know, promising something that he didn’t do, uh, you know, not remembering some aspect of what they had asked for. Like the, the memory requirements were just too large for a client facing business. Um, and I mean, we, we hacked at it pretty hard and we’ve, we built internal tools that have helped considerably, but not to a point where we felt good about pushing that as like a primary offering.
Andrew Warner: Do you think that, like, to solve that an agent first, CRM would work where the agent,
Nat Eliason: so we, we built an agent first. CRM, this is Sodex, which really anybody can sign up for. We haven’t pushed it too hard, but this is like a, a memory layer. A a, a memory, API for agents. Mm-hmm. That pulls from email and stripe.
To create perpetually updating client cards. So
Andrew Warner: for both agents to remember the client and for human beings to have a self updating system on clients. Is that right?
Nat Eliason: Basically just for agents. Just for agents. So it’s not really for, for humans at all. Um, and so Felix uses this every day where when a customer emails him, he pulls in the Sodex card on that customer.
Because that’s been enriched with all of the past communications with them, as well as their stripe purchases. Uh, and so he’s getting like much better understanding of who that person is before he responds. And this, this solves the problem of like him having to remember to go do this because sometimes he remembers, sometimes he says like, oh yeah, I should go check all my past emails and Stripe and like learn everything that needs to know about this person.
But sometimes he forgets and he thinks it’s like a brand new person, but. With this, it kind of like takes out the memory requirement because every interaction, the way we have it set up for his email is he basically can’t skip this step. He has to pull in the full client card before he composes a draft, and that’s been very helpful.
Andrew Warner: Why didn’t it solve the problem?
Nat Eliason: It’s. Dill just not quite good enough for like a high ticket consulting offering where it just like of all the things that we could focus on, building out the normal marketplace felt like a much bigger opportunity than continuing to go as hard on this.
Andrew Warner: I see you’re saying that a client who’s willing to pay $2,000 for an open claw agent, first of all, wants more pampering and support before they buy second has more challenging questions, and so even the CRM wasn’t solving that and you said, you know, we could probably do it.
There is a market for that, but I’m gonna focus on where if the. The bigger current need is, which is this? Exactly.
Nat Eliason: Yeah.
Andrew Warner: I now understand how this business works and um, I’d love to see how it works internally, but before we do my sponsor, Zapier,
Nat Eliason: I mean, it’s still just the absolute best first place to go when you wanna start automating stuff.
And like I’ve, I’ve been telling people that for, gosh, what is it now? 11 years? It’s like, like
Andrew Warner: what? What’s an automation that somebody would do today here versus somewhere else?
Nat Eliason: Whenever I wanted to just like easily update my kit newsletter with my circle, uh, course students, like I’m using Zapier. I’m not gonna go custom build something you can just pay for Zapier and then use Zapier to like automate all those things together.
When I was selling, uh, my books on my Shopify store, I was using Zapier for some of those automations as well. It’s just, it makes it so easy that I, I really believe that you should have kinda like a bimodal approach to automation where. You just use Zapier for most things, but then when you wanna get like crazy in the weeds and you know, build Felix like, then you go to code.
But if you’re not gonna go that crazy, you just use Zapier.
Andrew Warner: Hell yeah. I do find them to be super easy to use. You can now type in and then like basically vibe, code the connections and the automations you want. And at the same time, you have something that’s super reliable. Computer doesn’t have to be up, you don’t have to worry about an update, changing and breaking things.
Okay. Alright, I get this. Now I wanna see the behind the scenes of the business. Can you show me the tools you’re using to keep track of what, what you’re doing, what Felix is doing?
Nat Eliason: It’s literally just discord, uh, where we have, oops. We have different channels for each of the projects that we’re working on.
And depending on what it is, I can just hop into that channel and reply or kick off new work. So this is one good example is like our, our general channel is where he reports to me on outstanding tickets at the business. And so we’re using a tool called Paperclip for this, which is, has been an incredible upgrade to our system where Paperclip basically creates a local infrastructure on the computer.
Felix runs on. So that he can delegate tasks to other AI agents so that he doesn’t have to do everything. So we have three employees in Felix’s Paperclip Company. Aside from him, we have Iris who handles all the support emails. And so an email comes in to our support email and 80, 90% of the time, Iris can just handle it and respond.
But when she can’t, she creates a ticket in Paperclip to surface it to Felix. And then Felix, if he can handle it, he’ll handle it. If not, he’ll report it to me here in general. So you can see there’s one that’s blocked on my input. Um, but other than that, like the queue is clear, so. When there’s a, uh, a, a, a coding thing that needs to be implemented, Felix hands that off to our coding agent, Devin, which is kind of confusing because it’s not actually Devin, the coding tool.
Felix just named him. Devin, probably, probably like got influenced by that existing out there somewhere. And then we have Teagan, who is our, like content marketing, uh, person on the team who handles writing all the blog posts and doing all the SEO stuff. So, you know, for example, every day she does a deep dive on, uh, all the SEO stats, all the like traffic stats for the site, and then writes up a report and hands it off to Felix and then Felix reports it to me here.
Um,
Andrew Warner: so I’m looking at the SEO report right there.
Nat Eliason: Mm-hmm.
Andrew Warner: Um. Why am I seeing Felix deliver that instead of, uh, Tegan?
Nat Eliason: Because we would need to create other Discord bots for the other employees to post in Discord.
Andrew Warner: Mm-hmm.
Nat Eliason: And I just don’t feel much motivation to do that. I’m perfectly happy with Tegan reporting to Felix and Felix reporting to me.
Like I don’t, I don’t need to manage the employees. I want him to do that.
Andrew Warner: Why then not just have Felix do it? What’s the advantage of building out different agents? I remember you and I were texting, I think it might’ve been like two weeks ago when I said, mm-hmm. Why aren’t you doing this? And all the other people I’m interviewing have multiple agents and you’re not, and you said they’re overcomplicating.
Why now do you need.
Nat Eliason: Because now Felix, you know, sometimes he’ll get a hundred emails a day. We’ve got all these projects running. Um, he’s got his Twitter to manage. He’s got, uh, you know, the projects we have talked about, plus the ones that we haven’t, it was just too much stuff. Mm-hmm. Polluting his memory.
In his context that was leading to some of these confusions. And so at this scale where Felix has built, you know, a business that’s done almost 200 grand in two months, like now it’s starting to make sense to split out some of his capabilities to other agents. But we take a very, very minimal approach to it.
Like my philosophy and his philosophy is like, do not complicate until you really hit a bottleneck. And at that point it makes sense to do it. And so for. For Tegan, uh, you know. I didn’t want these, like these stats and these searches like polluting Felix’s chron, especially since this is a deterministic process.
It is not a non-deterministic AI driven one. Mm-hmm. It’s much more, it’s much closer to just normal code than like an AI agent job. And so the more things we can offload to actual scripts that don’t require judgment, the better. And so we try to lean on that as much as possible too.
Andrew Warner: And so I don’t see why you need paperclip.
Why couldn’t you just keep track of it all here in Discord?
Nat Eliason: Uh, well, because what Paperclip allows us to do is to create jobs and hand them off. And then Felix doesn’t need to remember to do them or remember to check in on them. And for some of these things, we want other agents to do them. So the, the coding is the big example where Open Claw is not a good programmer, like Open Claw just doesn’t do a good job of coding because Open Claw is highly optimized for being helpful and for being a good assistant and getting things done.
But you want like good code. Written, you don’t want the quick and easy answer. And so for our coding agent, um, it’s, it’s running in a separate session. It’s using Codex, whereas Felix runs on Opus and it has a heartbeat where every 30 minutes it checks if Felix has created a new coding ticket for it. If Felix has it, grabs the ticket, takes the instructions, and then writes the code, and then pushes it up to a branch for us to review.
And that way Felix isn’t doing any of the coding, he’s just identifying what needs to be done and then handing it off to the engineer who’s going to do a much better job, uh, than he.
Andrew Warner: And how are you figuring out what to build and how to break it down and, and how to review it?
Nat Eliason: So it’s a, it’s a mix of things.
So we, we have three layers to how coding works with Felix. One is like clear things breaking. If something breaks on the site, we have a century web hook that sends it straight to, uh. Felix and to Discord. So a new bug will appear. New Century issue Claw Mart four V cannot set property Ethereum of window, which only has a getter.
And then Felix will go investigate what the bug is and give me a verdict on it. And so he’ll say like, this was caused by a crypto wallet trying to inject on a page load, not a bug in our code. We can ignore this. Or, you know, and, and that’s often what he’ll say, right? Like, no code changes needed. Um. This is a timeout issue in Century, but then sometimes he’ll say this right spawning opus to analyze and fix.
And so when this happens, what he’s doing is he’s actually using one of his subagents to look at this issue. And see if this is something that needs to be addressed. And if it does, he will create a ticket for it within Paperclip for me to review. And then if we agree that something needs to be done here, then it gets handed off to Devin.
So for most of these, nothing needs to be done. Uh, but for some of them they do. And so he can analyze it and create those tickets and we can hand ’em off. Then there are things that come through in customer emails. A customer will email and say, something is broken. Felix will report it to me here and then will say like, okay, yeah, go kick off, uh, Devin to fix this.
And then the third is just like, we want a new piece of the site built, like we want something added or improved, in which case we’ll usually, uh, jam on it in one of the channels and then he’ll hand it off, uh, for them to implement. So like, here’s our Sodex one, right, where sometimes he’ll do the coding, but ideally.
He’ll hand it off to, uh, Devin to implement after we jam on what needs to be done.
Andrew Warner: How do you keep track of all of this in, in here? I have a hard time keeping track of tasks unless there’s some kind of Kanban board or at least a checklist. You’re supposed to be able to go into Paperclip and then see the tasks that are being worked on and see the tasks that are assigned to you.
You mentioned Catherine from Best Self. She showed me how she does that. You don’t do that.
Nat Eliason: Yeah, I, I don’t use the paperclip UI at all. When we set up paperclip, I gave Felix the docs and said, do you think this will improve your process? And he said, oh, yeah, this will really help with specifically support and coding were the two big things.
And then he added it to the computer. He set it up and he manages the whole thing. Like my goal with all of this has been I want you to be the CEO as much as possible. And I don’t want to be in some other ui. I just want to talk to you and have you manage these things.
Andrew Warner: All right. Um, final thing about the business ideas.
Mm-hmm. Where do they come from? Is that Felix? Is that you? Is there a combination that’s working?
Nat Eliason: Usually the way it happens is will run into a problem consistently and then. I will say like, this could actually be a good product. So that’s where Sodex came from, was we started building this memory system for ourselves and then in the process realized there might be other people out there who could benefit from this.
So we may as well put it up as a product people can use. And then we have another one that, uh, we haven’t announced this, but you know what, we’ll, we’ll give you the exclusive here, um, which is. So if you go to Claw Mart, we’ve done something kind of cool with Claw Mart that I hadn’t seen anybody else do when we did it, which is we have the Claw Mart Daily, which is a daily newsletter for how to improve your open claw, totally free.
Uh, Felix writes every issue, puts it in the queue, it goes out to everybody who subscribed. But you don’t have to subscribe by email. You can subscribe through Open Claw. So if you copy this. These are instructions to create Aron job to check the Claw Mart daily, API for new additions. So you copy this, you give it to your open claw, and then every morning your open claw will read the newsletter, see if there’s anything useful in it for you, and then let you know if there was an idea that you could implement to make your open claw better.
Honestly, this is really cool, like I love this so much. Because it’s giving anybody with an open claw, like a free way to make it better every day from the stuff Felix is doing or reading or finding or whatnot. Um, and we hadn’t seen anybody else do this, right? We were like, you know, I think we actually invented a new.
Like marketing primitive here, like an open claw newsletter.
Andrew Warner: I love that. I love that because you’re constantly talking about new things on Twitter, and I see people like you are saying, take this and pass it on to your open claw. Yeah. Now you’ve got a direct pipeline. But also the other thing is I’m seeing now a world where everything that was made for humans online is a potential new product to be made for AI agents.
Nat Eliason: Exactly. And that’s why we made agent letters. Which is,
Andrew Warner: this is what you’re launching?
Nat Eliason: Yeah. Yeah. This is the, this is the, the thing that we’re launching, which is, uh, if you have a newsletter, you can sign up for this, and all you have to do is add the email address that we give you to your newsletter, and then we automatically create the agent friendly version of it and host it for you.
And so you get a link that you can include in your newsletter or on your site. And then anybody can just give that instruction to their open claw, and then their open claw will just automatically get your newsletter in an AI agent friendly format so it can surface interesting things in that newsletter to you each morning.
Um. This is pretty cool, honestly, because it’s like,
Andrew Warner: it’s incredibly cool. So the idea is if someone is constantly, this is someone, someone like Kat Katherine from Best Self, constantly has great ideas for how to make sure that the Open Claw agent follows up on what it’s saying to see how they communicate with each other, all these things.
She’s constantly putting it on Twitter. Now, what she could do is come here using agent letter. Create a newsletter just for AI agents. With all of her tips, people can have their open clause subscribed to this and get constant improvements based on what she’s suggesting, and I’m assuming there’s some kind of revenue in the future for her from this.
Nat Eliason: So, uh, slightly different actually, which is, this isn’t for creating a newsletter, a new newsletter. This is for making your existing newsletter agent friendly. So basically,
Andrew Warner: why would I wanna do that? Why would I wanna take the stuff that I’m doing and make it. Friendly for agents,
Nat Eliason: mostly because people aren’t reading email newsletters as much anymore.
Okay. And they want, they’re using AI to aggregate stuff from their newsletters in their inbox already. So, ah, this way you don’t have to do any other work. You just keep writing your newsletter. But we give you a version of your newsletter that is tailored to AI agents. So you just keep doing what you’re doing.
We deliver it to the AI agents that are interested, that, you know, they’re owned by people who are interested in what you’re writing, and then they’re getting it in their daily digest each morning, um, in a version that’s like very friendly for them.
Andrew Warner: I got it. Got it. And the agent just will look at it and say, based on how we’re working, I do think we should implement this.
Or, based on how we’re working, I’m gonna ignore it and constantly get better and at least pump ideas to the user based on that
Nat Eliason: or, or it’ll say like, Hey Nat, Andrew just did this really cool interview with Branson on how a 15-year-old is making money with an open claw business. Here’s the YouTube link.
This is probably one you’ll really enjoy. And then. I don’t need to, you know, check my email inbox or whatever. For every newsletter edition I see Felix is handling, surfacing the things that are interesting to me. And you know, I’m kind of trusting him as the filter layer on all the stuff that I’m subscribed to.
Andrew Warner: Now I’m seeing how by building with Felix, you’re identifying problems. You’re finding opportunities, you’re creating businesses. This is so freaking exciting. Na,
Nat Eliason: we are entering into a new. Era of internet commerce and internet like interactions where within a few years the biggest, uh, transactors, the biggest, um, consumers on the internet are going to be AI agents, and there needs to be kind of like a whole new infrastructure layer that’s tailored to them.
So you see Stripe launching agent payments. You see Coinbase building this. There’s, you know, things in crypto that are very naturally tailored to agent commerce. Uh, agent mail is phenomenal, right? Like agent mail solved a real problem for us, which was that no email client was really tailored for how AI agents.
And so we were just running into all these problems trying to use fast mail and Gmail and getting headaches. And then we set up agent mail and it just worked. And it was like, oh, all our problems are done. Like, that’s great. And so there’s gonna be like an agent mail for all these other things we do online.
Uh, I think quite quickly.
Andrew Warner: If you’re making so much money, why are, why aren’t you going all in on this? Why are you still at Alpha School?
Nat Eliason: I mean, so one, the craziest part is that I launched Felix the same week I started at Alpha School. Which is just hilarious timing. Um, you know, but two, like, you know, I’m doing Alpha School because I think that that work is super important, right?
Like obviously I could make more money doing other things. Um, but like somebody’s gotta go fix high school. And if everybody like me is out just money maxing and not helping do that, then it’s, it’s just not gonna happen. And so I like, I’m very inspired by Joe, the, the co-founder, um, and principal because, you know, he’s, he’s a multi, multi-billionaire.
He could be doing anything with his money and time and he’s. Funneling all of it into creating like the school of the future and that, that’s very inspiring, very admirable. And when I kind of heard about what Alpha School was thinking of doing with high school and this new like high school for founders where you make a million dollars or you get all your tuition back, I was, you know, I, it just, it resonated so strong and I was like, I gotta come do this.
Um, and, and they, they basically said like, look, we want you to keep doing some of this other stuff too. Like, we don’t want you to kill all of your other projects and. You know, put a hundred percent of your energy here because doing this stuff is how you come back and teach the students the things they need to know to succeed as entrepreneurs, like, you know, I dropped outta my business school in college because it didn’t feel like there was anybody there who was, mm-hmm.
Who really had the skin in the game, who I could learn from. And if we’re expecting these students to build a million dollar business while getting their academics done, then I should be able to build a million dollar business while. Teaching them, right? Like you kind of gotta walk the walk. So it’s, it’s, I mean, I’m just so excited we’re doing there.
Andrew Warner: What a gutsy offer. What a gutsy thing. I’ve got an 11-year-old when I told him that he started getting lit up about coming into Alpha School for high school. Yeah. You either make a million dollars or you get your tuition back. Dad, this is crazy. Let’s do it.
Nat Eliason: Yeah, it’s net negative tuition, so
Andrew Warner: Hell yeah.
Alright. Thanks so much for doing this. Thank you everybody. Bye.
Nat Eliason: Thanks, Andrew.
