My experience is that basic generic agents are useless but an agent with extensive prompting about your usecase is extremely valuable.

In my case using these prompts:

https://github.com/masoncl/review-prompts

Took things from "pure noise" to a world where, if you say there's a bug in your patch, people's first question will be "has the AI looked at it?"

FWIW in my case the AI has never yet found _the_ bug I was hunting for but it has found several _other_ significant bugs. I also ran it against old commits that were already reviewed by excellent engineers and running in prod. It found a major bug that wasn't spotted in human review.

Most of the "noise" I get now just leads me to say "yeah I need to add more context to the commit message". E.g the model will say "you forgot to do X" when X is out of scope for the patch and I'm doing it in a later one. So ideally the commit messages should mention this anyway.