Tag
Human defect detection collapses past roughly 400 diff lines, and agents blow through that in one prompt. Tier pull requests by blast radius with a deterministic CI gate instead.
September 10, 2026 AI AgentsA test written by the same agent that wrote the implementation is a mirror, not a check. Which TDD invariants survive agent authorship, and the mutation-testing gate that catches the rest.
August 18, 2026 WorkflowsMost LLM features ship on vibes — skim three outputs, merge. Here's the 40-line Python eval harness with JSON fixtures and a judge-model gate you can wire into CI today.
May 06, 2026