AI-enhance a draft system prompt
Takes an operator-drafted system prompt plus the agent type (chatbot | router | voice | workflow | custom, default chatbot) and returns an LLM-improved version — clearer edge-case handling, explicit escalation guidance, and template placeholders preserved verbatim. Backs the create-agent wizard’s AI Enhance button; runs on the platform’s internal model with a 30-second cap. Owner/admin/developer role; 30/min per-tenant rate limit.
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
{ prompt, model } — the improved prompt text plus the platform model that produced it — in the standard { data, meta } envelope.