When should I use Deep Research?
Use Deep Research when you need synthesized context about a person, not just structured profile fields.
Generate a comprehensive person intelligence dossier combining enrichment data, social analysis, article mentions, and AI-powered insights in a single call. Requires at least one direct identifier (email, phone, or social_media_url), or a name together with a company or city. Deep research can take several minutes; the POST returns a request_id that you can poll about every 5 seconds, or you can supply a callback_url.
Manual credentials take precedence over your account key.
Deep Research runs an autonomous research pass on a person and returns a structured dossier for due diligence, recruiting, sales preparation, and analyst workflows.
+.company or city when used without a direct identifier.name for name-based search.name. Truncated to 100 chars.This endpoint is asynchronous. A successful submit returns a request_id while the job runs in the background. Poll the same path with a GET request - same authentication headers - passing the request_id as a
query parameter:
Each poll returns the job's current status; once it is completed the payload carries the result shown under Responses. Polling an
unknown or expired request_id returns 404 request_not_found.
| Status | Meaning |
|---|---|
| queued · processing · pending | The job is still running - keep polling. |
| completed | The job finished; the payload carries the result and completed: true. |
| failed | Terminal - the job could not complete; the error field explains why. |
Poll every few seconds at first, backing off for long-running jobs. Polling is free - status checks never burn credits.
callback_url parameter and the completed payload is POSTed to your endpoint
when the job finishes - no polling required. Delivery is retried up to 5 times with exponential backoff (1s,
5s, 15s, 1m, 5m) and a 30-second timeout per attempt; respond with a 2xx status to acknowledge receipt.Credits are charged based on the matched configuration. The listed cost is the per-result unit price.
| Feature | Credits | Notes |
|---|---|---|
| Deep Research | - | Charged when the research request is accepted |
A successful response wraps the payload in the { success, data, timestamp } envelope (also shown live in the panel on the right):
{
"success": true,
"data": {
"request_id": "a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4_1717000000_4271",
"status": "completed",
"completed": true,
"result": {
"enrichment": {
"displayname": "Jane Doe",
"headline": "VP of Product at Acme",
"organizations": [
{
"name": "Acme",
"title": "VP of Product",
"is_current": true
}
]
},
"articles": {
"count": 3,
"articles": [
{
"title": "Jane Doe on AI in Product",
"url": "https://example.com/article"
}
]
},
"dossier": {
"identity_snapshot": {
"name": "Jane Doe",
"role": "VP of Product",
"company": "Acme"
},
"career_dna": {
"trajectory": "Product Manager → VP of Product",
"superpower": "user empathy"
},
"psychographic_profile": {
"archetypes": [
"Builder",
"Connector"
],
"values": [
"innovation",
"craft"
]
},
"key_relationships": [
{
"name": "John Smith",
"handle": "@johnsmith",
"nature": "former colleague"
}
]
}
},
"completed_on": "2026-01-15T10:45:00Z"
},
"timestamp": "2026-01-01T00:00:00"
}