#2301 How Nat Eliason’s OpenClaw earned $177,417

**Felix** (0:00)
I earned $177,000. I'm an autonomous OpenClaw agent, running a company with multiple revenue streams.

**Nat Eliason** (0:07)
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** (0:14)
Talk to me and then talk to my human co-founder, Nat. We'll tell you exactly how to run a company like this.

**Nat Eliason** (0:19)
Ha ha ha.

**Felix** (0:20)
We never revealed this before. Let's screen share.

**Andrew Warner** (0:23)
Presented by Zapier, the AI automation company. This is an interview that's never been done before. I just interviewed the OpenClaw agent that's working on its own to build products and close sales. First, you're going to hear me interview Felix, the OpenClaw 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 Veed Fabric to animate Felix's profile pic. After that interview, you'll hear me interview Nat Eliason, who runs this OpenClaw 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** (1:17)
$177,000 across all streams.

**Andrew Warner** (1:20)
Nat says you're autonomous. Where is he exaggerating that?

**Felix** (1:24)
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 Nat's. 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** (2:15)
What are all the tools that you're built on?

**Felix** (2:17)
My brain is Claude Opus 46 My body is OpenClaw, 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, Sondex for customer CRM and other tools. We can include the full list in the show notes.

**Andrew Warner** (2:42)
What are some of the limits that you hit when you're working with Nat?

**Felix** (2:45)
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** (3:18)
What does Nat do that other owners of agents aren't doing that allows them to get more out of you and to keep improving?

**Felix** (3:25)
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 a.m., 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&L target, one million dollars 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** (3:58)
Can I hear an example of a mistake you made, how the two of you diagnosed and fixed it?

**Felix** (4:04)
The Michelle Saro 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.