Get test run

Read one test run with its full simulated transcript and the judge's verdict.

GEThttps://api.tried.com.au/get-test-run/{id}

Returns one test run with the full transcript of the simulated conversation, including tool calls and node transitions. Runs are created by Create batch test.

Request#

Field	Type	Required	Description
`id`	string	Yes	Path parameter. The `test_run_id`.

Example request#

curl https://api.tried.com.au/get-test-run/test_run_5e6f7a8b9c0d1e2f3a4b5c6d \
  -H "Authorization: Bearer $TRIED_API_KEY"

const id = "test_run_5e6f7a8b9c0d1e2f3a4b5c6d";
const res = await fetch(`https://api.tried.com.au/get-test-run/${id}`, {
  headers: { Authorization: `Bearer ${process.env.TRIED_API_KEY}` },
});
const run = await res.json();

import os, requests

run_id = "test_run_5e6f7a8b9c0d1e2f3a4b5c6d"
res = requests.get(
    f"https://api.tried.com.au/get-test-run/{run_id}",
    headers={"Authorization": f"Bearer {os.environ['TRIED_API_KEY']}"},
)
run = res.json()

Response#

200 OK

{
  "test_run_id": "test_run_5e6f7a8b9c0d1e2f3a4b5c6d",
  "batch_test_id": "batch_test_2c3d4e5f6a7b8c9d0e1f2a3b",
  "test_case_definition_id": "test_case_8f7e6d5c4b3a29180f1e2d3c",
  "test_case_name": "Reschedule appointment",
  "agent_id": "agent_3e4f5a6b7c8d9e0f1a2b3c4d",
  "status": "pass",
  "transcript": [
    { "role": "agent", "content": "Hi Sam, thanks for calling. How can I help?" },
    { "role": "user", "content": "I have a booking on Tuesday at 3pm and want to move it to Thursday morning." },
    { "role": "tool_call_invocation", "tool_call_id": "tc_1", "name": "check_availability", "arguments": "{\"day\":\"Thursday\"}" },
    { "role": "tool_call_result", "tool_call_id": "tc_1", "content": "{\"slots\":[\"Thursday 10am\"]}" },
    { "role": "agent", "content": "I can move you to Thursday at 10am. Does that work?" },
    { "role": "user", "content": "Yes, thanks. Goodbye." }
  ],
  "explanation": "The agent offered Thursday 10am and confirmed the change.",
  "error": null,
  "duration_ms": 41200,
  "created_timestamp": 1760850000000,
  "completed_timestamp": 1760850041200
}

Field	Type	Description
`test_run_id`	string	Run ID, prefix `test_run_`.
`test_case_name`	string	Name of the test case when the run was created.
`status`	string	`pending`, `running`, `pass`, `fail` or `error`.
`transcript`	array	Items in order. `agent` and `user` items have `content`. `tool_call_invocation` has `tool_call_id`, `name` and `arguments`. `tool_call_result` has `tool_call_id` and `content`. `node_transition` has `former_node_id` and `new_node_id`.
`explanation`	string or null	The judge's reason for `pass` or `fail`. In mock mode it starts with `Mock judge:`.
`error`	string or null	Why the run failed to complete, when `status` is `error`.
`duration_ms`	integer or null	How long the run took, including judging.
`completed_timestamp`	integer or null	Unix ms when the run finished.

Errors#

Status	When
`401`	Missing or invalid API key.
`403`	The key's IP allowlist or scopes reject the request. This route needs the `agents` scope.
`404`	`Test run <id> not found`.
`429`	Rate limit exceeded. See Rate limits.

See Errors for the body format.

Retell compatibility#

Same path and method as Retell. The response shape differs: Tried returns test_run_id, transcript and explanation instead of Retell's job and snapshot fields.