Per-agent coaching cards
Aggregate each evaluated agent’s official reviewer-authored QA scorecard feedback — their average score, the share of evaluations flagged for human review, the weakest scorecard criteria to drill, open auto-assigned coaching plans, and short badge chips (‘Low QA score’, ‘flagged for review’, ‘open coaching plans’). Reviewer scope (owner / admin / supervisor) may inspect any agent; a non-reviewer agent is always narrowed to their own card. Sister surface to the regression-style quality trend at GET /quality/trends and the compliance queue at GET /quality/compliance-flags. Read-only.
Authorizations
Dashboard JWT token from Clerk
Headers
Sandbox opt-in for Clerk-session-authenticated requests. Set to true to route the call through the test-mode pipeline: no real provider delivery, no credits deducted, response meta.test_mode: true. Ignored for live API keys (dv_live_sk_*) — server-to-server clients must use a test-prefixed key (dv_test_sk_*) to exercise sandbox. Test-prefixed keys unconditionally enable sandbox regardless of this header.
true, false Query Parameters
Look-back window in days over each evaluation's creation time (1–90). Defaults to 30, capped at 90; an out-of-range or non-numeric value falls back to 30.
16Restrict the rollup to one agent. Defaults to every evaluated agent (or only the caller themselves for a non-reviewer user). An over-long value falls back to the all-agents view.
200Max agent cards returned (1–50). Defaults to 50, clamped to 50; an out-of-range or non-numeric value falls back to 50.
8