Series
Greenfield
Engineering, AI, and the businesses we build from scratch. Solo-narrated essay episodes on the rules, layers, and judgment calls behind working with coding agents in real codebases.
1 part · first published
Listen along
Subscribe (RSS)The Rule Lives in Your Head
Why the corrections you give your coding agent keep evaporating — and the four places a rule can live so that it stops. A story about barrel imports, a UUID that broke staging, and the moment I stopped trusting my own memory as infrastructure.
Static and Dynamic: When Each Wins
Prompts and subagents look similar from a distance — both are markdown files, both shape how the agent works. They are not the same tool. One is static, one is dynamic, and the line between them is sharper than people realize. A story about a 900-line prompt that paid for itself and a subagent that didn't.
The Subagent I Didn't Need
A confession about a subagent I wrote, ran for a month, and quietly deleted — and the broader taxonomy of agent-side artifacts that helped me see why. Five things live in a mature agent-ready repo, and they are not interchangeable. A field guide to when not to delegate.