One API call. It observes, learns, and adapts — you decide.
You tell Cadreen what you want to build. It proposes the rules, connects the tools, and tells you what's ready. Then every response shows you what happened and why.
Note
You can scope Cadreen to individual users by passing
user_id — memory, preferences, and history stay isolated per person. Omit it to build a shared workspace. Each workspace is isolated by default.Choose your first call
Not sure where to start? Pick the row that matches what you are trying to do.
| I want to | Use | Why |
|---|---|---|
| Ask a question — get an answer grounded in your data | /api/v1/cadreen/chat/completions | OpenAI-compatible. Full intelligence layer — rules, memory, decision logs, tool calling. Drop into any tool that speaks OpenAI protocol. |
| Ask it to do something — refund, transfer, approve — with your rules enforced | /api/v1/cadreen/intent | Cadreen-native. Typed outcomes: answered, needs_input, blocked_by_policy, blocked_by_missing_connection, executing. |
| Set everything up — one call, describe what you need | /api/v1/cadreen/setup | Describe your purpose. Cadreen proposes connections, memory, policies, and webhooks. No manual endpoint choreography. |
| See what it can handle before you go live | /api/v1/cadreen/assess | Capability preflight. Returns what Cadreen can and cannot do for your purpose. No action taken. |
| See exactly why it decided what it did | /api/v1/cadreen/intelligence/{trace_id} | Full breakdown: which rules fired, what knowledge was consulted, why the gate decided what it did. Send this trace to support. |
Your first call — Request
POST /api/v1/cadreen/intent
Authorization: Bearer sk_cadreen_...
{"messages":[{"role":"user","content":"Refund $700 to customer 123 for order 456"}]}Response (200)
{"type":"direct","status":"blocked_by_policy","reason_code":"policy.requires_human_approval","policy_id":"pol_refund_threshold","trace_id":"cad_a2c9"}Try it live
Loading endpoints from OpenAPI spec...