FruxonDocs
ApiEvaluation runs

List per-sample comparisons for an evaluation run.

Returns the per-sample comparisons for a completed run, paginated and ordered by each sample's original position in the dataset. This is the row-level detail behind the run's aggregate statistics — use it to inspect which individual cases passed or regressed.

GET
/v1/tenants/{tenant}/agents/{agent}/evaluationRuns/{evaluationRun}/samples

Authorization

Bearer
AuthorizationBearer <token>

JWT Authorization header using the Bearer scheme. Enter 'Bearer' [space] and then your token.

In: header

Path Parameters

agent*string

The unique identifier of the agent

evaluationRun*string

The evaluation run ID

Formatuuid
tenant*string

The tenant identifier

Query Parameters

PageSize?integer

The maximum number of items to return per page

Formatint32
PageToken.Skip?integer
Formatint32
PageToken.Cursor?string

Opaque cursor token from an external system (e.g. RAG API). When set, M:Fruxon.Common.Collections.PageToken.AsString returns this value directly instead of encoding Fruxon.Common.Collections.PageToken.Skip.

Response Body

curl -X GET "https://api.fruxon.com/v1/tenants/string/agents/string/evaluationRuns/497f6eca-6276-4993-bfeb-53cbbbba6f08/samples"
{
  "items": [
    {
      "sampleId": "string",
      "sampleIndex": 0,
      "parameters": {},
      "baseRevisionResult": {
        "response": "string",
        "trace": null,
        "sessionId": "string",
        "links": [],
        "executionRecordId": null,
        "status": "UNSPECIFIED",
        "humanApprovalRequestId": null,
        "messageBlocks": null
      },
      "candidateRevisionResult": {
        "response": "string",
        "trace": null,
        "sessionId": "string",
        "links": [],
        "executionRecordId": null,
        "status": "UNSPECIFIED",
        "humanApprovalRequestId": null,
        "messageBlocks": null
      },
      "llmEvaluation": {
        "score": 0,
        "overallAssessment": "string",
        "summary": "string",
        "analysis": {},
        "keyImprovements": [],
        "concernsRisks": [],
        "deploymentRecommendations": [],
        "monitoringPriorities": [],
        "errorCategory": null,
        "errorTitle": "string",
        "errorRecommendation": "string"
      },
      "systemEvaluation": {
        "baseRuntimeMs": 0,
        "candidateRuntimeMs": 0,
        "baseCost": 0,
        "candidateCost": 0,
        "runtimeAnalysis": "string",
        "costAnalysis": "string"
      },
      "baseRuntimeMs": 0,
      "candidateRuntimeMs": 0
    }
  ],
  "nextPageToken": "string",
  "totalCount": 0
}
Empty
Empty
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "instance": "string",
  "property1": null,
  "property2": null
}