I've been building PR Focus, a Chrome extension that helps developers triage GitHub pull requests....
PR Focus implements hybrid scoring: deterministic signals (CI, age) + AI tiebreaker protects failing PRs from AI ranking errors. Avoids token costs and AI inconsistency. Production pattern: hybrid AI = reliable governance vs blind LLM trust, adopted where ranking errors matter operationally.
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.
The problem GitHub shows your pull requests in whatever order they happened to be opened —...
The problem I review a lot of pull requests. Not because I'm a reviewer by trade, but...
After posting several articles about the impact of AI on developers and sharing resources to help...
Most AI code review tools stop after producing findings. The problem is that AI can generate...
A CLI and GitHub Action that scans AI-written pull requests for sketchy patterns and posts the findings back to the PR. Advisory…
Dev log #1 Hi, I'm Denyse. I'm a software engineer, and for the past two months I've been building a...
