Get Journey Path Results

(v2)

GET

Retrieves how the test cases simulated from a journey's goldens went: for each test case, the path it was generated for and the path the conversation actually took, plus each metric's results per path. Use it to find the branches where your LLM app strays from the journey or fails its metrics.

GET/v2/journeys/{journeyId}/paths

curl -X GET "https://api.confident-ai.com/v2/journeys/{journeyId}/paths" \
  -H "CONFIDENT_API_KEY: <PROJECT-API-KEY>"

200

{
  "success": true,
  "data": {
    "testCases": [
      {
        "testCaseId": "<TEST-CASE-ID>",
        "testRunId": "<TEST-RUN-ID>",
        "name": "Refund request, verified",
        "journeyStateIds": [
          "<JOURNEY-STATE-ID>"
        ],
        "journeyPath": [
          "<JOURNEY-STATE-ID>"
        ],
        "status": "COMPLETED",
        "success": true,
        "completionTime": 12.4
      }
    ],
    "metrics": [
      {
        "journeyStateIds": [
          "<JOURNEY-STATE-ID>"
        ],
        "name": "Conversation Completeness",
        "avgScore": 0.82,
        "passed": 7,
        "failed": 2
      }
    ]
  },
  "link": "https://app.confident-ai.com/project/<PROJECT-ID>/journeys/<JOURNEY-ID>",
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Path parameters

journeyIdstringRequired
The id of the journey.

Query parameters

startstring
Only include test cases last updated at or after this time, in ISO 8601 format. Send it with end, or omit both to include every test case.
endstring
Only include test cases last updated at or before this time, in ISO 8601 format. Send it with start; it must be later than start.

Response

Get Journey Path Results succeeded.

successboolean
Indicates if the request was successful.
dataobject
How the test cases generated from a journey's paths actually went: which path each conversation took, and how each path did on each metric.
Show 2 propertiesHide 2 properties
- testCaseslist of objects
  Every test case simulated from this journey's goldens in the time window, in no particular order.
  Show 8 propertiesHide 8 properties
  - testCaseIdstring
    The id of the test case.
  - testRunIdstring
    The id of the test run the test case belongs to.
  - namestring
    The name of the test case.
  - journeyStateIdslist of strings
    The path the test case's golden was generated for, as state ids in order from the root state.
  - journeyPathlist of strings
    The state the simulated conversation was in on each user turn, in order, so a state repeats while the conversation stays in it. Compare it with journeyStateIds to see where the conversation left the intended path. [] when it was not recorded.
  - statusenum | null
    Where a test case is in its run: GENERATING its output, EVALUATING its metrics, COMPLETED, or ERRORED. WAITING means an asynchronous result has not arrived yet.
    Show 5 enum valuesHide 5 enum values
    GENERATING
    EVALUATING
    ERRORED
    COMPLETED
    WAITING
  - successboolean | null
    Whether the test case passed its metrics, or null when it has no verdict yet.
  - completionTimenumber | null
    How long the test case took to run, in seconds, or null when it was not recorded.
- metricslist of objects
  Metric results for the same test cases, one entry per path and metric. Skipped and flaky metric results are left out.
  Show 5 propertiesHide 5 properties
  - journeyStateIdslist of strings
    The path these results are for, as state ids in order from the root state.
  - namestring
    The name of the metric.
  - avgScorenumber | null
    The metric's average score across the path's test cases, or null when none was scored.
  - passedinteger
    The number of the path's test cases that passed the metric.
  - failedinteger
    The number of the path's test cases that failed the metric. Results that errored count as neither passed nor failed.
linkstring
This is the URL of the resource on the Confident AI platform.
deprecatedboolean
Indicates if this endpoint is deprecated.

Built byConfident AI