I would just create an agent that provides the reviews. Instead of saying "your MR meets some of the criteria I have in this blog post", the agent can point very clearly at the exact criteria and how the merge request meets them, and can even make improvement suggestions. At the end, the author would review the AI generated review, to make sure everything sounds (and is) right. AI can be used in good ways, and bad ways. Show them the good way.

Based on personal use there's no way 2025 capabilities would do a good job of that task. I hope to get automated CR bots in my org working soon but today, it should definitely only be brief feedback that people can choose to ignore.