Read a squad's orchestration analytics
Return the observability rollup for one multi-agent squad over a rolling window: per-specialist utilization (conversations, resolutions), cross-agent handoff success and drop-off counts, and containment lift against the classifier-agent-alone baseline. Use it when a squad underperforms and you need to know whether routing, particular specialists, or handoffs are the weak link before retraining. Optional query days (1–180, default 30). Read-only; every aggregate degrades to zeros/empty on a provisioning gap instead of failing.
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 Path Parameters
Response
The squad analytics rollup — window_days, per-member agents aggregates (conversations, resolved, human_handoffs, handoffs received/succeeded/dropped), and the classifier-baseline block — in the standard { data, meta } envelope.