Skip to main content
Field confidence adds a 0–100 score, a short justification and source URLs to each scored field in an Intelligence result. Each score reflects how much assumption is needed to tie the value back to the target person or company. A high score means the evidence chain is strong; a low score means attribution is uncertain.

Request

Pass field_confidence: true in the request body. It works on: The option is available on each supported tier. If false or omitted, the request does not enable additional field scoring. People Intelligence xhigh can return field confidence from its research even when this option is false or omitted; entries depend on available evidence. Tier access requirements still apply.
For Company Intelligence, use /v1/companies/intelligence with a company object and company fields such as industry. Keep fields and field_confidence at the top level for single records and batches. Reuse the idempotency key only for retries of the same request; use a new key for new research. See Safe retries.

Response format

The request returns a Job, including job_id, status and charge_credits. Read GET /v1/jobs/{job_id} until it reaches a terminal status. A successful single-record Job has the researched values and enrichment_field_confidence in result. Batch records are available through GET /v1/jobs/{job_id}/items, in each item’s result. Example successful single-record Job:

Response fields

If no per-field scores are available, read enrichment_confidence_score when present. It is a record-level score, not a per-field percentage. A result column can be present with a null value; its presence alone does not mean scoring succeeded.

Nested fields (objects and object_lists)

For nested fields, enrichment_field_confidence mirrors the shape of the researched values. A request’s fields can include:
Example result excerpt:

Workflows and downloads

Workflow results and bulk Intelligence results use the same enrichment_field_confidence column. In JSON and NDJSON, the column contains an object, not a JSON-encoded string. In CSV, its cell contains compact JSON text: Nested fields retain the same structure in each format. Existing Workflow confidence settings keep their behavior. For the original request and response names, see Legacy People Intelligence and Legacy Company Intelligence. Those routes remain supported.

Confidence tiers

The 0–100 score maps to named confidence levels:

Usage tips

  • Threshold by use case: 65 or higher for cold outreach, 85 or higher for legal and compliance work.
  • The weakest link dominates: if the target has a very common name, even well-sourced fields score lower because the identity link is uncertain.