Jev in production › Message and ticket triage
GitHub Action asks Jev four calibrated questions per new issue (label, spam, duplicate, needs info) and applies a label only above maintainer-set thresholds, otherwise stays silent. 78% precision on 800 closed issues at the default threshold (author).

Issue and pull request triage that stays quiet when it isn't sure.
A GitHub Action that reads every new issue and labels it — but only when it can say how sure it is. When it can't, it does nothing and tells you why.
And the part that matters, from its own first issue — a report that could reasonably be a bug or a documentation problem:
LLM triage bots return prose with no calibrated notion of certainty, so a 55% hunch and a 99% read look identical coming out. You get confident-sounding labels on issues the model never understood, and after the third wrong one you turn it off.
For the project's own README, linking back here: