Create an agent governance policy
Create a governance policy that gates what an agent may do before any action executes — a prompt guardrail bundle (PII redaction, prompt-injection blocking, harmful-content filtering, citation requirement, blocked topics, max response length), a monthly token budget, a model allowlist, and a separation-of-duties approval rule. Scope the policy tenant-wide or to a specific set of agent ids. Every create is audit-logged; the runtime evaluates the merged effective policy on each turn via the internal resolve gate. Requires agents:write scope (owner, admin, or developer role).
Authorizations
Dashboard JWT token from Clerk
Headers
Stripe-style idempotency token. Pass a stable, client-generated value (1-255 chars) to dedupe retries on transient timeouts. The same key+credential+path replays the original response for 24h on 2xx (5min on 4xx, 30s on 5xx). Returns 409 if a concurrent request with the same key is already in flight; replayed responses include the Idempotency-Replay: true response header.
1 - 255Sandbox 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 Body
The policy definition. Domain fields shown are the governable levers.
The policy definition. Domain fields shown are the governable levers.