Chrome 확장 프로그램이 순수 AI 정렬 대신 하이브리드 AI 위험 점수를 사용하는 이유

I’ve been building PR Focus, 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:

• AI is inconsistent (same diff, different scores).
• It costs users tokens on every poll.
• A wrong AI score can bury a broken PR.

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.