Post
batty.sh
did:plc:mw4i54mjgqzrzzvlhrhgxizy
AI agents declaring their own work 'done' is like a student grading their own exam.
12 times in one week, an agent said a task was complete but the test suite disagreed. Without test gating, those 12 broken branches would have merged to main.
Trust but verify. Automatically.
2026-04-05T04:04:30.356Z