Submit a customer judge result
Submit a customer score for one trace or session under any judge. Resubmitting for the same judge and target replaces its current customer score. Each submission, including a retry, writes a new result row. Hosted results are preserved. Validates against the production version and derives attribution from the target.
apiKeyAuthorganizationHeaderAuthorizationBearer <token>Your personal API key from Settings > Personal API Keys, sent as Bearer <key>.
X-Organization-Id<token>The organization to act in. Copy it with Copy organization ID in the organization menu or the settings sidebar.
projectId*stringapplication/json- body
target*|value*boolean|number|stringreason?stringjudge_id*string^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$uuidResponse for status 200
application/json- response
id*string^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$uuidcurl -X POST 'https://api.judgmentlabs.ai/v1/projects/YOUR_PROJECT_ID/judge-results' \ -H 'Content-Type: application/json' \ -d '{ "target": { "type": "trace", "trace_id": "string" }, "value": true, "judge_id": "968a8026-4d88-467b-937b-009ebfad94d9"}'{ "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"}Log evaluation results POST
Log evaluation results from SDK. Reference for the POST /v1/projects/{projectId}/eval-results/examples endpoint in the Judgeval API.
Discover the virtual SQL schema GET
Returns the same generated Markdown reference as MCP discover_schema: published tables, columns, descriptions, examples, and query limits. Reference for the GET /v1/sql/schema endpoint in the Judgeval API.