How a Team's AI Coding Flow Should Be Wired
A change lands in review with everything green. The rules pass, the types check, the tests are close to the ones I'd have asked for.
A change lands in review with everything green. The rules pass, the types check, the tests are close to the ones I'd have asked for.
One evening an agent working in this repo killed an idea of mine for failing a rule. The kill was well argued and it cited the rule by line number, the way…
The first stage of my code reviewer hands the next one a two-field object: a rule id and a citation. Not its reasoning. Not the file it just read. Two fields.
I asked an agent which of three approaches to take. It gave me three — each described accurately, tradeoffs and costs and failure modes, all of it right.
A good rule set grows. Mine has grown — tested against a whole corpus of real PRs and code — into something too big to hand a model all at once, and that's…
The reviewer is the visible product: it reads a diff, applies a rule corpus tested against real PRs and code, and ships the findings worth a person's attention.
My code reviewer does far more work than it ships. Scouts cast a wide net — anything that might be a violation.
I built an eval to tell me whether my agent's skills were earning their place. For a while it said they weren't — clean, green, confident.
I told the agent fidelity came first. It optimised for cost anyway, for an embarrassing reason — cost had an estimator and a guardrail, and fidelity had a…
The goal was never a cheaper reviewer. It was finding everything that is really there while posting nothing that isn't — and that objective, not the budget…
Sakana AI shipped Fugu with a clean pitch: one endpoint that routes your task across a pool of models — calling itself recursively — and handles selection…