A check where a model forms a judgement: an AI code review, a second agent grading the first. It can notice things no rule can express, such as whether a change makes sense.
It catches what computational checks can't. It also costs tokens, takes longer, can change its mind, and answers differently depending on how you ask. Run it after the cheap checks pass, never in place of them, and make it show its evidence.
Say it to your agent
“Have a fresh agent review this diff against the spec. It must quote the line and say what input breaks it. Anything it can't demonstrate goes in a separate list, and doesn't block the merge.”