List clustered knowledge gaps for a knowledge base
Aggregate the low-confidence and escalated turns of the agents that link this knowledge base over a look-back window into clustered questions, so you can see WHAT callers keep asking that the KB cannot answer and prioritise the next article to write. Query params: days (look-back window, default 30), limit (max clusters, default 10), and agent_id (narrow to a single agent’s traffic). Returns an empty clusters list when no agent links the KB. Read-only; any role that can read agents.
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 gap report — kb_id, days, agent_ids, total_low_confidence, total_escalations, and the clustered questions with sample phrasing — in the standard { data, meta } envelope.