Agents
Ask the Growth Scientist
Runs the LangGraph workflow: intent analysis, deterministic metric gathering, specialist fan-out, evidence synthesis and a structured recommendation. Works without an LLM key - the figures and the recommendation are deterministic either way, only the prose is simpler.
Authorization
HTTPBearer AuthorizationBearer <token>
JWT access token
In: header
Query Parameters
merchant_id?|
Optional merchant to act on. Must be one you are a member of.
Format
uuidHeader Parameters
X-Merchant-ID?string|null
Request Body
application/json
channel?string
Default
"web"Value in
- "web"
- "voice"
conversation_id?|
Length
length <= 64message*string
Length
2 <= length <= 2000opportunity_id?|
Format
uuidworkflow?|
Value in
- "investigate"
- "ask"
- "detect"
- "execute"
- "measure"
- "voice"
Response Body
application/json
application/json
curl -X POST "https://example.com/api/v1/agents/ask" \ -H "Content-Type: application/json" \ -d '{ "message": "string" }'{ "data": { "answer": "", "opportunity_id": "5c7fee95-8917-4b3c-8649-bbbc4ef0c4f7", "recommendation": { "action_key": "string", "alternatives_considered": [ "string" ], "confidence": 0.5, "estimated_impact": 0, "evidence": [ { "change": "string", "confidence": 0, "detail": "string", "metric": "string", "reference": "string", "source": "analytics", "value": "string" } ], "hypothesis": "", "opportunity": "string", "reasoning": "", "recommended_action": "", "requires_approval": true, "risk": "low", "summary": "string" }, "requires_approval": false, "run": { "agent_label": "", "agent_name": "string", "campaign_id": "78614b6c-fe7c-41e2-8e25-c9b3a3c91904", "channel": "string", "confidence": 0, "created_at": "2019-08-24T14:15:22Z", "decision": "string", "duration_ms": 0, "error": "string", "experiment_id": "916afd89-cac5-4339-9c59-dd068abdfa69", "finished_at": "2019-08-24T14:15:22Z", "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08", "input_text": "string", "intent": "string", "model": "string", "opportunity_id": "5c7fee95-8917-4b3c-8649-bbbc4ef0c4f7", "output": {}, "recommendation": { "action_key": "string", "alternatives_considered": [ "string" ], "confidence": 0.5, "estimated_impact": 0, "evidence": [ { "change": "string", "confidence": 0, "detail": "string", "metric": "string", "reference": "string", "source": "analytics", "value": "string" } ], "hypothesis": "", "opportunity": "string", "reasoning": "", "recommended_action": "", "requires_approval": true, "risk": "low", "summary": "string" }, "requires_approval": false, "started_at": "2019-08-24T14:15:22Z", "status": "string", "steps": [ { "action": "string", "agent_label": "", "agent_name": "string", "decision": "string", "duration_ms": 0, "error": "string", "evidence": [ { "change": "string", "confidence": 0, "detail": "string", "metric": "string", "reference": "string", "source": "analytics", "value": "string" } ], "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08", "node": "string", "result": "string", "sequence": 0, "status": "string" } ], "summary": "string", "tool_calls": [ { "agent_name": "string", "arguments": {}, "duration_ms": 0, "error": "string", "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08", "result_summary": "", "sequence": 0, "status": "string", "tool_name": "string" } ], "tools_used": [ "string" ], "total_tokens": 0, "trace_disclaimer": "This trace shows actions, tools, evidence and decisions. Internal model reasoning is never recorded or displayed.", "trace_id": "string", "trace_url": "string", "used_fallback": false, "workflow": "string" }, "suggested_followups": [ "string" ] }, "meta": {}, "success": true}