Field notes for people building useful AI systems.
Essays on agents, prompts, product judgment, and the operating habits that make AI work less fragile.
Browse concepts→Use ChatGPT agents like a careful operator
ChatGPT agents are useful when you give them bounded work, the right access, and clear stop points. Treat them like junior operators, not magic.
Evals as contracts: a better way to know if your agent is working
Stop thinking of evals as tests. Start thinking of them as contracts. Tests are things you run and hope they pass. Contracts are things you sign.
Why your AI pilot is stuck (and what to do about it)
The most common call I get starts with: 'We ran a pilot six months ago, it looked promising, but now everything's stalled.' Here's what's actually going wrong, and the specific moves to un...
The three prompt patterns I actually use in production
After shipping AI in four companies where wrong answers cost real money, I've stopped reaching for clever prompt engineering and started reaching for three patterns. That's it. Three.
How to build your first AI agent in an afternoon
A practical walkthrough for consultants and product people who want to go from zero to a working agent. No buzzwords, just results.