LLMs are great at producing code reviews that sound right. But "sounding right" isn't the same as being useful. A review that tells you to "fix the Code Style" is correct but useless — every project applies a Code Style that may differ.
Symfony has more than 20 years of public code reviews on GitHub. Every merged PR contains comments from nicolas-grekas, stof, dunglas, xabbuh, and dozens of other reviewers from the core team and contributors. It's a goldmine of domain-specific review patterns: which arguments convince, which patterns get rejected, what the community considers good Symfony code.
The problem? No one had built a search engine to exploit it. So I did it 🤣.
The lore behind this crazy idea
This story starts at the Symfony Live in Paris. As you can imagine, this year's edition was very AI-focused. I saw quite a few talks about it and wanted to play around with this novelty, but until then I didn't have a concrete use case.
