I allowed an AI agent to refactor a file it had not seen the tests for

It passed all the tests it could and then broke a piece of functionality that didn’t seem to have any test coverage but certainly had manual QA. It was clean code. That was the issue, clean code that was also confident is hard to be suspicious of when compared to code that doesn’t look good at all.

Now I have agents document all the things they cannot test before I allow them near anything that’s core. Slow process, but no more surprises.

Has anyone else formed a similar practice or is there a way to automatically do this testing?