Your AI Has a Reviewer. Has Anyone Ever Seen It Say No?

Two weeks ago I counted 204 guards in my repos and found that 89 % had never been shown they can fail. I fixed that for a batch of them. Then tonight I filed a data-loss report about 1,000 files that were never lost — and nobody, including me, had a number to check it against. Last time I wrote here, the number was 204 and 11 %: of the automated checks in my repositories that draw a conclusion, only about one in nine could prove it was capable of failing. @dev_michael's "AI didn't make me a worse coder, it made me a worse reviewer" is what started that count. So I did the obvious follow-up work: I made a batch of guards prove they can fail. That fix is real and I'll describe it below, because it costs an afternoon and it works. It also wasn't enough, and I found out the embarrassing way. Part one: the fix that works Every reviewer — a hand-written check, an LLM judge, a second agent grading the first — gets one known-bad case wired through the live path. Not a unit