Why my Chrome extension uses a hybrid AI risk score instead of pure AI sorting

A developer building PR Focus, a Chrome extension for triaging GitHub pull requests, opted for a hybrid AI risk score system rather than relying solely on an LLM. The system uses deterministic signals like CI status and PR age as the primary sorting criteria, with AI risk scores serving as tiebreakers. Failing CI always takes priority regardless of AI output.

I've been building PR Focus https://github.com/projekta2/pr-focus-landing , a Chrome extension that helps developers triage GitHub pull requests. One of the first decisions I had to make was: how do I actually sort PRs by priority? The obvious answer is "use AI to score the risk". But I didn't want to rely 100% on an LLM because: So I built a hybrid system: deterministic signals CI status + PR age form the floor, and the AI risk score is a tiebreaker on top. Failing CI always floats to the top, regardless of what the AI says. I wrote up the full decision, including the trade-offs and what it cost, in my new Build Logs repo https://github.com/projekta2/build-logs . If you're building dev tools or wrestling with AI reliability, the full log might be useful: 🔗 Why PR risk scoring is a hybrid, not a pure AI verdict https://github.com/projekta2/build-logs/blob/main/001-pr-focus-risk-scoring.md