Skip to main content
A test definition records a scenario and the expected outcome. Keep it alongside the configuration change it is intended to check.
Test creation, editing, folders, and existing invocation reads are available through the API. Running or resubmitting tests is gated by agent execution availability. Saving a test does not run it.
You need an authorized workspace credential and a specific behavior to evaluate.
Recording pending for Create and inspect a test definition. No playable video is available yet.

Recording pending: Create and inspect a test definition. Follow the written guide below.

1

Write one observable expectation

For example, require the agent to ask for a missing booking date before requesting a reservation. Include relevant chat_history and synthetic dynamic_variables.
2

Save and inspect the definition

Use Create test, then Get test. Confirm the returned type, scenario, and expected outcome. Organize related definitions with test folders.
3

Associate and record readiness

Agent configuration supports platform_settings.testing.attached_tests. Review attachment details with the agent draft. Mark execution pending until a released runner produces a completed invocation for the intended version.
Existing invocations can be read independently. Managed-model text-only publication does not remove the test execution gate; voice and custom-model publication remain unavailable.
The public contract exists, but the current execution gate prevents a new run. Do not interpret a saved definition as a passing result.
Use synthetic values and only the context needed to reproduce the behavior.