Run evaluators against a Pipecat WebRTC deployment (manual room URLs, v1)
Evaluators
Run Evaluator Pipecat
Execute evaluators against an agent running on Pipecat / Daily.co WebRTC. Each scenario entry carries its own pipecat_room_url and optional token.
POST
Run evaluators against a Pipecat WebRTC deployment (manual room URLs, v1)
Authorizations
API Key Authentication. It should be included in the header of each request.
Body
Schema for the run_scenarios_pipecat endpoint, which runs scenarios using Pipecat WebRTC.
Total runs: one per entry in scenarios (no frequency multiplier on this endpoint).
Response
ID of the result
ID of the agent
Status of the result
Available options:
pending, running, completed, failed Whether the scenario ran as text or not
Example:
false
Examples:
{
"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
}Example:
"2025-02-25T21:00:01.990052Z"