Get test execution details

Retrieves a test execution with its call executions.

GET https://api.futureagi.com/simulate/test-executions/{test_execution_id}/

Authentication

X-Api-Key API Key Required

Your Future AGI API key used to authenticate requests. You can find and manage your API keys in the Dashboard under Settings.

X-Secret-Key Secret Key Required

Your Future AGI secret key, used alongside the API key for request authentication. This is generated when you create an API key in the Dashboard.

Path parameters

test_execution_id UUID Required

The test execution ID.

Query parameters

search string Optional

Filter by scenario name, transcript content, or status.

page integer Optional

Page number. Defaults to 1.

filters string Optional

JSON-encoded filter array, e.g. [{"colId":"status","filterType":"text","type":"equals","filter":"completed"}].

row_groups string Optional

JSON-encoded array of column IDs to group by, e.g. ["scenario"].

group_keys string Optional

JSON-encoded group key values to drill into. Used with row_groups.

Response

200 OK
id string
UUID of the test execution.
run_test string
UUID of the parent run test.
run_test_name string
Parent run test name.
agent_definition_name string
Agent definition name.
status string
Status: pending, running, completed, failed, cancelled, cancelling, or evaluating.
error_reason string or null
Failure reason.
started_at datetime
ISO 8601 execution start time.
completed_at datetime or null
ISO 8601 completion time.
total_scenarios integer
Number of distinct scenarios.
total_calls integer
Total call executions created.
completed_calls integer
Calls that completed.
failed_calls integer
Calls that failed.
execution_metadata object
Execution metadata.
duration_seconds integer or null
Elapsed time in seconds.
success_rate number or null
Percentage of calls completed successfully.
calls array
Paginated call execution objects.
id string
UUID of the call execution.
status string
Call status: pending, queued, ongoing, completed, failed, analyzing, or cancelled.
duration number
Duration in seconds.
transcript array
Conversation transcript.
overall_score number
Aggregate eval score.
eval_outputs object
Eval results per configured eval.
scenario string
Scenario name.
created_at datetime
ISO 8601 creation timestamp.
created_at datetime
ISO 8601 creation timestamp.
scenario_ids array
Scenario UUIDs included.
simulator_agent_name string or null
Simulator agent name.
simulator_agent_id string or null
UUID of the simulator agent.
agent_definition_used_name string or null
Agent definition name used.
agent_definition_used_id string or null
UUID of the agent definition used.
calls_attempted integer
Total calls initiated.
calls_connected_percentage number
Percentage of calls that connected.

Errors

401 Unauthorized Optional
Invalid or missing credentials.
404 Not Found Optional
Test execution not found.
500 Internal Server Error Optional
Unexpected server error.
GET /
Authentication
REQUEST 
 
 
  
 
 RESPONSE