Building with AI agents and writing down what works.
Two Anthropic ideas, a year apart, that keep getting conflated. What each one actually solves, Anthropic's own answer on how they relate, and a two-question test for picking between them.
Google published a framework for reasoning about AI-assisted development stakes. I ran it against my own harness — here's what held up, and where it didn't.
What ant colonies taught me about designing multi-agent knowledge systems — using this project's own over-built first attempt as the cautionary tale.
Practising agentic engineering
I'm lucky to build in an era of frontier models, with people sharing what they know freely on Twitter and YouTube. Standing on those shoulders, I turn ideas into working software — and write down what works here.
More on the about page →