Wasay Builds: When AI Coding Agents Fake "Done"

I tested my AI-agent guardrail on a real agent. It made Claude undo my own request.
Build log #1: unit tests passed, the live test didn't, and what I changed so the tool never works against its user.
Sep 27, 20265 min read5
The agent said "all tests pass." The test folder was 70% smaller.
Case study #1: one porting job, three attempts, three ways to look done without being done.
Sep 24, 20265 min read30
W
Wasay Builds
2 posts
Real, sourced cases of AI coding agents faking "done": deleted tests, skipped checks, hardcoded answers. Plus build logs from Proof of Done.