Skip to main content

Run Management

list_runs

List evaluation runs with filtering and pagination.
ParameterTypeRequiredDescription
page_sizenumberNoResults per page (1-100, default: 50)
page_tokenstringNoPagination token from previous response
order_bystringNoSort order (e.g., -create_time for newest first)
filterstringNoFilter expression (e.g., status="COMPLETED")

get_run

Get detailed information about a specific run.
ParameterTypeRequiredDescription
run_idstringYesThe unique run ID
Returns run details including status, progress, and metrics (if completed).

create_run

Launch a new evaluation run.
ParameterTypeRequiredDescription
agent_idstringYesAgent ID from list_agents
persona_idstringYesPersona ID from list_personas
test_set_idstringYesTest set ID from list_test_sets
metric_idsstring[]NoSpecific metrics to evaluate
options.iteration_countnumberNoIterations per test case (1-10, default: 1)
options.concurrencynumberNoParallel simulations (1-5, default: 1)
metadataobjectNoCustom metadata for tracking

Agent Management

list_agents

List all configured agents.
ParameterTypeRequiredDescription
page_sizenumberNoResults per page (1-100, default: 50)
page_tokenstringNoPagination token
order_bystringNoSort order
filterstringNoFilter by model_type, display_name, etc.

get_agent

Get detailed configuration for a specific agent.
ParameterTypeRequiredDescription
agent_idstringYesAgent ID from list_agents

create_agent

Create a new agent configuration.
ParameterTypeRequiredDescription
display_namestringYesHuman-readable name (1-200 chars)
model_typestringYesAgent type (see below)
phone_numberstringNoE.164 format for voice agents
endpointstringNoWebhook or WebSocket URL
promptstringNoSystem prompt/instructions
metadataobjectNoCustom metadata
Model Types:
  • MODEL_TYPE_VOICE - Inbound voice
  • MODEL_TYPE_OUTBOUND_VOICE - Outbound voice
  • MODEL_TYPE_CHAT - Chat/text
  • MODEL_TYPE_SMS - SMS messaging
  • MODEL_TYPE_WEBSOCKET - WebSocket

update_agent

Update an existing agent configuration.
ParameterTypeRequiredDescription
agent_idstringYesAgent to update
display_namestringNoNew name
phone_numberstringNoNew phone number
endpointstringNoNew endpoint URL
promptstringNoNew system prompt
metadataobjectNoNew metadata

Test Set Management

list_test_sets

List all test sets available for evaluation.
ParameterTypeRequiredDescription
page_sizenumberNoResults per page (1-100, default: 50)
page_tokenstringNoPagination token
order_bystringNoSort order
filterstringNoFilter expression

get_test_set

Get detailed information about a test set.
ParameterTypeRequiredDescription
test_set_idstringYesTest set ID from list_test_sets

create_test_set

Create a new test set.
ParameterTypeRequiredDescription
display_namestringYesTest set name (1-100 chars)
slugstringNoURL-friendly ID (auto-generated if omitted)
descriptionstringNoTest set description
test_set_typestringNoDEFAULT, SCENARIO, TRANSCRIPT, or WORKFLOW
test_set_metadataobjectNoConfiguration metadata
parametersobjectNoTest parameterization

Test Case Management

list_test_cases

List test cases with optional filtering by test set.
ParameterTypeRequiredDescription
test_set_idstringNoFilter by test set ID
page_sizenumberNoResults per page (1-100, default: 50)
page_tokenstringNoPagination token
order_bystringNoSort order
filterstringNoFilter expression

get_test_case

Get detailed information about a test case.
ParameterTypeRequiredDescription
test_case_idstringYesTest case ID from list_test_cases

create_test_case

Create a new test case in a test set.
ParameterTypeRequiredDescription
test_set_idstringYesTest set to add the case to
display_namestringYesTest case name
descriptionstringNoTest case description
inputobjectNoInput data for the test
expected_outputobjectNoExpected output for validation
metadataobjectNoCustom metadata

update_test_case

Update an existing test case.
ParameterTypeRequiredDescription
test_case_idstringYesTest case to update
display_namestringNoNew name
descriptionstringNoNew description
inputobjectNoNew input data
expected_outputobjectNoNew expected output
metadataobjectNoNew metadata

Metrics

list_metrics

List available evaluation metrics.
ParameterTypeRequiredDescription
page_sizenumberNoResults per page (1-100, default: 50)
page_tokenstringNoPagination token
order_bystringNoSort order
filterstringNoFilter expression
include_builtinbooleanNoInclude built-in metrics

get_metric

Get detailed configuration for a specific metric.
ParameterTypeRequiredDescription
metric_idstringYesMetric ID from list_metrics

Personas

list_personas

List available simulated personas for testing.
ParameterTypeRequiredDescription
page_sizenumberNoResults per page (1-100, default: 50)
page_tokenstringNoPagination token
order_bystringNoSort order
filterstringNoFilter expression

get_persona

Get detailed configuration for a specific persona.
ParameterTypeRequiredDescription
persona_idstringYesPersona ID from list_personas
Returns persona configuration including voice settings, language, and behavior.