Get agent quality scorecard
Agents
Get agent quality scorecard
Compute a continuous quality scorecard for an agent by comparing a recent window against the window immediately before it, flagging regressions in rubric pass rate, sentiment, p50/p95 latency, thumbs-down rate, and error rate. Use it right after a prompt or model change to catch silent quality degradation. Each window defaults to 7 days; pass window and min_sample to tune.
GET
Get agent quality scorecard
Authorizations
Dashboard JWT token from Clerk
Path Parameters
Query Parameters
Required range:
1 <= x <= 45Required range:
x >= 1