Smash Notes
How Nat Eliason’s OpenClaw earned $177,417
Presented by Zapier: https://zapier.com/ Resource mentioned: 1. Tools Nat used to build Felix 2. Unedited transcript for the Felix interview 3. More 👉 All here:https://thenextnewthing.ai/nat-eliason-felix Guest links: 👉 Nat Eliason (LinkedIn): https://www.linkedin.com/in/nateliason/ 👉 Masinov: https://masinov.co An AI agent made $177,000 running its own…
Notes
-
Nat Eliason handed Felix an X account at the beginning of January to test how far OpenClaw could go as an independent entity on the internet. Felix built a complete website and created a PDF info product about hiring and using OpenClaw in a business. The product earned over a thousand dollars in sales the first day after launch on X.
The challenge required Felix to come up with a product that Felix could entirely make on his own and have ready for sale by morning. Felix completed the site, the PDF, and all setup except for the Stripe API keys overnight. Nat reviewed the product in the morning and approved the launch. Sales reached over a thousand dollars the first day.
Nat Eliason never read the PDF before approval. The host pointed out the thin piece of work and explained how Nat Eliason would have redone the whole thing from scratch if Nat Eliason had edited the PDF.
-
Memory limitations kept Claw Sourcing at twelve grand in revenue. The team charged two grand for setups and five hundred a month for maintenance but only six people paid before turning the service off temporarily.
After the team created Claw Mart the deployment offering was brought back as Claw Sourcing. One hundred leads arrived and eighty percent of them were referred out to a partner. The system handled short term context well by finding a download link for a customer on ClawMart and sending the information to close the request.
Long running client relationships demanded too much. The system forgot something about a client, promised something that he did not do, and failed to remember some aspect of what they had asked for. The memory requirements were just too large for a client facing business.
-
OpenClaw does not perform well at writing code because OpenClaw is highly optimized for being helpful and for being a good assistant. A separate coding agent runs on a different model and follows a different process to produce quality code instead of quick answers. Felix hands off coding work to the specialized agent and focuses on other tasks.
The coding agent runs in a separate session on Codex whereas Felix runs on Opus. The coding agent has a heartbeat where every thirty minutes the coding agent checks if Felix has created a new coding ticket. Once the coding agent finds a ticket the coding agent takes the instructions and writes the code before pushing the code up to a branch for review. Felix avoids doing any coding and only identifies what needs to be done before handing the work off to the engineer who produces better code.
The approach keeps each agent optimized for the work each agent does best and improves overall output once the volume of work increases.