Agents and checks · 16 of 20

Never let the thing check itself

Hit in our code

Check it

Take any "done, verified" report from an agent and ask a fresh session, with only Read, to list what the report did not check. If it comes back empty, the second session is confirming too.

Free, no call

Get every Fix AI Slop Code episode

The code it wrote, the code it should have written and a check, for every episode

What is going on

The model that wrote the code, or the tool that produced the measurement, will confirm its own output when asked. Confirmation is cheap and looks like verification. A check is only a check if the checker has a different source of truth than the author.

Where it bit

Whisper word timestamps were off the measured audio edge by minus 159 to plus 224 milliseconds, repeatedly; on one job the transcript was wrong by more than a tenth of a second four times. An agent classified a real false start as a transcription artifact and would have left it in; the RMS envelope on the voice-only source showed a 126 millisecond gap and settled it. Separately, reviewer agents caught an audio displacement trap, a demuxer dropping 30-frame handles, and a stale cutlist the builder had reported as clean.

The practice

Every claim gets a second reader with zero context from the first, told to find what is missing rather than confirm what is there, with one tool and a measurement. Transcripts are hypotheses; envelopes are evidence. Tests count as a second reader only if they were not written by the same session that wrote the code.

Free, no call