API Reference
Result rows of a workflow
One row per prompt and model for every completed run, newest first, each dated by its run and carrying the tag names its prompt holds. Filter by run date and by tag; pass `format=csv` to download the same rows as a CSV file (columns: Date (ISO), Prompt, Tags, Model, Response, Sources, Analyzer, Score, Justification, Extracted). Raw-response workflows leave the analyzer fields empty.
AuthorizationBearer <token>
Session JWT signed with HS256. Verification pins the algorithm and rejects expired tokens, per RFC8725.
In: header
Path Parameters
domainId*string
Public UUID of the domain
workflowId*string
Public UUID of the workflow
Query Parameters
startDate?string
endDate?string
tagIds?array<string>
Keep only results whose prompt carries at least one of these tags
format?string
csv downloads a file
Value in
- "json"
- "csv"
Response Body
curl -X GET "https://example.com/api/domains/3fa85f64-5717-4562-b3fc-2c963f66afa6/workflows/7c9e6679-7425-40de-944b-e07fc1f90ae7/results"[ { "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6", "runId": "7c9e6679-7425-40de-944b-e07fc1f90ae7", "promptId": "9b1deb4d-3b7d-4bad-9bdd-2b0d7b3dcb6d", "promptText": "What are the best running shoes?", "modelId": "chatgpt", "modelName": "ChatGPT", "rawResponse": "For neutral runners, the usual picks are...", "sources": [ { "url": "https://techcrunch.com/2026/01/10/running-shoes", "title": "The best running shoes of 2026", "text": "Testers favoured the lighter midsole..." } ], "analyzerOutputType": "boolean", "analyzerOutputNumber": 7, "analyzerOutputBoolean": true, "analyzerOutputJson": { "brands": [ "Nike", "Adidas" ] }, "analyzerRawResponse": "{\"value\": true}", "executionTimeMs": 4200, "error": "Upstream timeout", "createdAt": "2026-05-25T10:30:00.000Z", "tags": [ "running", "high priority" ] }]