We built an AI PR reviewer. The hard part was teaching it to say nothing.
Most AI code review tools fail the same way. They work, in the sense that comments appear on the pull request. Then you read the comments and they are 80% “consider extracting this into a helper”, “missing test coverage”, “this variable name could be clearer”, and within a couple of weeks everyone has learned to scroll past anything the bot wrote. These are not false positives. They are true and irrelevant, which costs the same attention and is harder to argue with.