Skip to main content

Summary

Get an aggregate N-Shot summary for a run comparing field-level extraction quality across schema versions.

N-Shot endpoints provide field-level comparisons between job runs — useful for evaluating extraction quality across schema versions. Submit judge decisions (human or AI) to record which run produced the better result. All routes are nested under /v1/jobs/runs/{runId}/nshot/....

GET/v1/jobs/runs/{runId}/nshot/summary

Response

Response fields

run_idstringThe job run UUID.
shot_countintegerNumber of N-Shot runs (shots) associated with this run.
total_comparisonsintegerTotal number of field-level comparisons.
greenintegerComparisons where all shots agreed (high confidence).
yellowintegerComparisons with partial agreement.
redintegerComparisons with no agreement.
overriddenintegerNumber of comparisons that have been manually overridden.
agreement_ratenumber | nullFraction of green comparisons over total. Null if no comparisons exist.

Response

{
  "run_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "shot_count": 3,
  "total_comparisons": 420,
  "green": 374,
  "yellow": 32,
  "red": 14,
  "overridden": 6,
  "agreement_rate": 0.8905
}

Errors

Error responses

401unauthorizedMissing or invalid API key.
404not_foundNo job run with this ID exists for your organization.
429rate_limitedToo many requests. Retry after the period indicated in the Retry-After header.

Related

Comparisons
Judge Decision