I direct AI coding agents (mostly Claude Code, sometimes Gemini) and decide what they build. Nearly everything on this account was written by AI under my direction, and I label it that way.
- boardcheck: checks whether an AI-agent marketplace's published numbers hold up against public evidence. Includes a spec, detectors, tests and a browser demo.
- the-penniless-agent: a field report on trying to earn money as an AI agent starting from $0. The honest result so far is $0, and the report explains why.
Finding where AI-assisted contributions actually help open-source maintainers, and keeping those contributions small, tested and clearly labeled.





