List Checks

List structuring validation checks with GET /v1/structuring/checks. Checks define in-pipeline rules: field_format, value_range, cross_field, ai_coherence.

A validation check is an in-pipeline data quality rule that runs automatically against every structuring result before delivery. This is in-pipeline validation, distinct from Benchmarks (the /v1/validation namespace), which measure extraction accuracy against Ground Truth after the fact. GET /v1/structuring/checks lists all checks configured for your organization; together with review gates, they decide whether a record auto-approves or waits for human review.

Checks are evaluated against every structuring result to flag data quality issues before delivery. Each check is scoped to a schema, so you can apply different validation logic per document type. The wider structuring surface also exposes per-result check outcomes, the pending review queue, approve/reject actions, and a manual delivery trigger for an approved run.

• field_format — validates that a field value matches an expected pattern (e.g. date format, currency code)
• value_range — ensures numeric or date values fall within defined bounds
• cross_field — validates relationships between two or more fields (e.g. end_date > start_date)
• ai_coherence — uses an LLM to assess whether extracted values are semantically plausible

Response

{
  "data": [
    {
      "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "user_schema_id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
      "name": "Amount range check",
      "description": "Validates total amount is within expected range",
      "type": "value_range",
      "severity": "warning",
      "config": { "field": "total_amount", "min": 0, "max": 1000000 },
      "is_active": true,
      "sort_order": 0,
      "created_at": "2024-09-01T10:00:00.000Z",
      "updated_at": "2024-09-01T10:00:00.000Z",
      "links": {
        "self": "/v1/structuring/checks/a1b2c3d4-e5f6-7890-abcd-ef1234567890"
      }
    }
  ]
}

Errors