create_agent_response_test_route
Create tests that validate an ElevenLabs agent's replies against success and failure examples, success conditions, and simulated user scenarios.
Instructions
Create Agent Response Test
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | ||
| type | No | ||
| environment | No | ||
| chat_history | No | ||
| evaluation_model | No | ||
| failure_examples | No | Non-empty list of example responses that should be considered failures | |
| parent_folder_id | No | ||
| success_examples | No | Non-empty list of example responses that should be considered successful | |
| tool_mock_config | No | Simulation/preview-side config: tools are identified by IDs, resolved to names at runtime. | |
| dynamic_variables | No | Dynamic variables to replace in the agent config during testing | |
| success_condition | No | ||
| success_conditions | No | List of prompts that evaluate whether the simulation was successful. If provided, all criteria are evaluated and merged into a final result. Capped at the maximum number of evaluation criteria. | |
| simulation_scenario | No | Description of the simulation scenario and user persona for simulation tests. | |
| tool_mock_overrides | No | Test-specific response mocks, keyed by tool ID. Applied ahead of the tool's shared mocks and only within this test. Only take effect for tools that are mocked (see tool_mock_config). | |
| simulated_user_model | No | ||
| simulation_max_turns | No | Maximum number of conversation turns for simulation tests. | |
| tool_call_parameters | No | ||
| check_any_tool_matches | No | ||
| simulation_environment | No | ||
| from_conversation_metadata | No | ||
| conversation_initiation_source | No | Enum representing the possible sources for conversation initiation. |