Execute evaluators against an agent that exposes a raw-PCM WebSocket endpoint (16 kHz, 16-bit mono). Requires chirp_data.chirp_websocket_url configured on the agent.
Documentation Index
Fetch the complete documentation index at: https://docs.cekura.ai/llms.txt
Use this file to discover all available pages before exploring further.
API Key Authentication. It should be included in the header of each request.
ID of the agent to run evaluators for
Alternative to agent ID - the assistant ID to use for this scenario
Example: "asst_1234567890"
List of evaluator IDs to run. Either scenarios, tags, or folder_path must be provided.
Example: [11, 22, 33]
To run evaluators by tag or folder, use the tags or folder_path fields instead.
List of tags to filter evaluators to run. Either evaluators or tags must be provided.
Example: ["tag1", "tag2", "tag3"]
Dot-separated folder path to select evaluators from (e.g. "Sales.Inbound").
Mutually exclusive with scenarios and tags. Requires project_id.
Project ID. Required when using folder_path (or when passing a folder path string via scenarios).
Example: 1376
The number of times each evaluator will run
Example: 1
x >= 1Label text for result
Override the phone number to use for outbound calls. Example: "+1234567890"
List of personality IDs to override for this run. If not provided, uses the scenario's default personality.
Example: [123, 456, 789]
List of test profile IDs to override for this run. If not provided, uses the scenario's default test profile.
Example: [123, 456, 789]
Using same or different phone numbers for each evaluation
same_number - same_numberdifferent_numbers - different_numberssame_number, different_numbers Override the phone number from which the agent under test receives the call during outbound runs. This allows overriding the default agent contact number for testing purposes. Example: "+1234567890"
Cap on the number of evaluator runs executed in parallel. Default: unbounded (subject to your provider's rate limits).
Use this to avoid hitting provider rate limits on large frequency or folder runs.
Example: 5
x >= 1ID of the result
ID of the agent
Status of the result
pending, running, completed, failed Whether the scenario ran as text or not
false
{
"id": 274,
"status": "pending",
"scenario": 1,
"number": null,
"inbound_number": "+11234567890",
"scenario_name": "Customer Support Call (Agent Inbound = True)",
"test_profile_data": null
}{
"id": 275,
"status": "pending",
"scenario": 2,
"number": "+11234567890",
"inbound_number": null,
"scenario_name": "Outbound Sales Call (Agent Inbound = False)",
"test_profile_data": null
}"2025-02-25T21:00:01.990052Z"