List QA cohort results

List the scored calls of a QA cohort.

GEThttps://api.tried.com.au/qa/cohorts/{id}/results

Returns every result in the cohort, newest call first. To keep the list small, call.transcript_with_tool_calls is always an empty array here; use Get QA result for the transcript.

Request#

Field	Type	Required	Description
`id`	string	Yes	QA cohort ID, for example `qa_cohort_2c4e6a8b0d1f3e5a7c9b1d3f`.

Example request#

curl https://api.tried.com.au/qa/cohorts/qa_cohort_2c4e6a8b0d1f3e5a7c9b1d3f/results \
  -H "Authorization: Bearer $TRIED_API_KEY"

const res = await fetch("https://api.tried.com.au/qa/cohorts/qa_cohort_2c4e6a8b0d1f3e5a7c9b1d3f/results", {
  headers: { Authorization: `Bearer ${process.env.TRIED_API_KEY}` },
});
const results = await res.json();

import os, requests

res = requests.get(
    "https://api.tried.com.au/qa/cohorts/qa_cohort_2c4e6a8b0d1f3e5a7c9b1d3f/results",
    headers={"Authorization": f"Bearer {os.environ['TRIED_API_KEY']}"},
)
results = res.json()

Response#

200 OK

[
  {
    "qa_result_id": "qa_result_7a9c1e3b5d7f9a2c4e6b8d0f",
    "qa_cohort_id": "qa_cohort_2c4e6a8b0d1f3e5a7c9b1d3f",
    "call_id": "call_5e7a9c1b3d5f7e9a2c4b6d8f",
    "score": 50,
    "resolved": true,
    "override": null,
    "effective_resolved": true,
    "criteria": [
      {
        "name": "Confirms the booking",
        "passed": true,
        "explanation": "Every quoted phrase appears in the call."
      },
      {
        "name": "Offers a reminder",
        "passed": false,
        "explanation": "1 of 4 keywords found (appointment). Mock scorer passes at 50%."
      }
    ],
    "summary": "Mock QA: 1 of 2 criteria met.",
    "metrics": [
      {
        "metric": "latency",
        "value": 880,
        "score": 100,
        "passed": true,
        "details": {
          "e2e": {
            "p50": 880,
            "p90": 1240,
            "p95": 1240,
            "p99": 1240,
            "max": 1240,
            "min": 610,
            "num": 6,
            "values": [
              610,
              790,
              880,
              880,
              940,
              1240
            ]
          },
          "threshold": 60,
          "judge": "heuristic"
        }
      },
      {
        "metric": "sentiment",
        "value": 100,
        "score": 100,
        "passed": true,
        "details": {
          "user_sentiment": "Positive",
          "threshold": 60,
          "judge": "heuristic"
        }
      }
    ],
    "weighted_score": 80,
    "passed": true,
    "effective_passed": true,
    "wer_corrections": [],
    "questions": [
      "Do you have anything on Thursday afternoon?"
    ],
    "created_timestamp": 1792395060000,
    "call": {
      "call_id": "call_5e7a9c1b3d5f7e9a2c4b6d8f",
      "agent_id": "agent_4b7e2c9a1f3d5e8b0c6a2d1f",
      "agent_name": "Clinic receptionist",
      "call_type": "phone_call",
      "start_timestamp": 1792308600000,
      "duration_ms": 142000,
      "disconnection_reason": "user_hangup",
      "user_sentiment": "Positive",
      "call_successful": true,
      "e2e_p50": 880,
      "transcript_with_tool_calls": []
    }
  }
]

The response is a JSON array of results.

Field	Type	Description
`qa_result_id`	string	Result ID, prefixed `qa_result_`.
`score`	number	Percent of criteria passed, 0 to 100.
`resolved`	boolean	Whether the caller's issue was resolved: the judge's verdict, or in mock mode the call's success flag (score of 50 or more when there is none).
`override`	string or null	Human label: `pass`, `fail` or `null`. Set with Update QA result.
`effective_resolved`, `effective_passed`	boolean	`resolved` and `passed` with the override applied. `effective_passed` falls back to `resolved` when `passed` is `null`.
`criteria`	object[]	Per criterion: `name`, `passed`, `explanation`.
`metrics`	object[]	Per metric judge: `metric`, `value`, `score` (0 to 100, or `null` when not applicable), `passed` and `details` (includes the `threshold` used and `judge`: `llm` or `heuristic`).
`weighted_score`	number or null	Criteria (100 for pass, 0 for fail) and applicable metric scores, averaged by weight.
`passed`	boolean or null	`weighted_score` is at or above the cohort's `pass_threshold`.
`wer_corrections`	object[]	Human transcript corrections used for the `wer` metric.
`questions`	string[]	Up to 20 questions the user asked in the call.
`call`	object or null	Call summary: ID, agent, type, start time, duration, disconnection reason, sentiment, success, median end-to-end latency (`e2e_p50`, ms) and `transcript_with_tool_calls`. `null` if the call was deleted.

Errors#

Status	When
`401`	Missing or invalid API key.
`403`	The key's IP allowlist or scopes reject the request. This route needs the `analytics` scope.
`404`	No cohort with that ID in the workspace: `QA cohort <id> not found`.
`429`	Rate limit exceeded. See Rate limits.

See Errors for the body format.

Retell compatibility#

Retell's public API reference has no AI QA endpoints, so this route has no Retell SDK equivalent.