AB-620: Designing and Building Integrated AI Solutions in Copilot Studio

By Microsoft · Question Mode

QuestionQ25

Test and manage agents

A team is building an agent in Copilot Studio and wants to assess its behavior before extending access.

The team requires a repeatable, consistent way to test the agent through predefined interactions. You must ensure that agent responses can be assessed consistently across multiple test runs.

What should you do?

Explanation

Copilot Studio test sets group predefined test cases, such as prompts or conversations, with expected responses or other evaluation criteria. Running the same test set repeatedly sends the same cases to the agent and produces comparable scored results, enabling consistent evaluation across test runs.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!