No agent in the loop. GitHub issues go in; explicit rules score rejection, recency, engagement, repository activity, and externalizability; the highest-scoring candidates come out.
__COUNT__candidates
__REPOS__watched repos
__THRESHOLD__minimum score
__UPDATED__last run · UTC
The score is intentionally mechanical, not “AI judgment.” It is a radar, not an oracle. Clicking a card goes to the source issue; the suggested product shape is selected by fixed keyword rules.