Manually teach the agent a memory
Create an AI agent memory item by hand — teach a fact, preference, or summary about a contact without waiting for the runtime extractor to learn it from a conversation. The content is embedded exactly like an LLM-extracted entry so retrieval treats it identically; when the embedding provider is down the fact is still persisted with a placeholder vector flagged for re-embedding, so an operator action is never lost to a transient outage. Per-contact fact caps apply (409 MEMORY_FACTS_CAP_EXCEEDED when full). Owner or admin 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 Response
Successful response.