The pull request nobody could review
An agent's 3,100-line pull request passed every test and was approved in 25 minutes. It had quietly changed how money rounds. Why AI-DLC caps the unit of work.
Field notes
Short lessons from real builds, with the client names removed and the mistakes left in. Three to six hundred words each.
Ten thousand runs a day changes the price
An agent that cost cents per run in the pilot cost far more per month at scale. Routing, caching and a budget ceiling fixed it; the ceiling mattered most.
The agent that could not say no
A support agent with no refusal path agreed to everything. The fix took an afternoon; the decision to write the refusal list should have been made on day one.
The evaluation set that measured the wrong thing
A document agent scored 94 percent on its evaluation set and failed in production. The set had been written by the team that built the agent.