AI Tests

Run evaluator scenarios

Changed on

Runs the selected evaluator scenarios against their test agents and creates a run batch. Returns the ID of the created batch, whose results can be listed with the test-run-results endpoints.

post/ai/tests/test_framework/v1/scenarios/run_scenarios

Request

  • Base URL: https://api.telnyx.com/v2
  • URL: https://api.telnyx.com/v2/ai/tests/test_framework/v1/scenarios/run_scenarios
  • Auth: HTTP bearer

Request body

agent_idinteger
assistant_idstring
tagsstring[]
frequencyinteger
namestring
outbound_phone_numberstring
personality_idsinteger[]
test_profile_idsinteger[]
mode'same_number' | 'different_numbers'
agent_numberstring
concurrency_limitinteger

Maximum number of concurrent simulated calls.

Example request

{
  "agent_id": 1259,
  "scenarios": [
    9512
  ],
  "tags": [
    "regression"
  ],
  "mode": "same_number",
  "concurrency_limit": 3
}

Response

Run batch created.

statusstring required

Initial status of the run batch.

idinteger required

ID of the created test-run batch whose results can be polled.

Example response

{
  "status": "in_queue",
  "id": 10119
}

Changes