I still believe in having humans do PRs. It's far cheaper to have the judgement loop on the AI come before and during coding than after. My general process with AI is to explicitly instruct it not to write code, agree on a correct approach to a problem and if the project has any architectural components a correct architecture then once we've negotiated the correct way of doing things ask it to write code. Usually each step of this process takes multiple iterations of providing additional information or challenging incorrect assumptions of the AI. I can get it much faster than human coding with a similar quality bar assuming I iterate until a high quality solution is presented. In some cases the AI is not good enough and I fall back to human coding but for the most part I think it makes me a faster coder.