Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
| Enabled for | Public preview | General availability |
|---|---|---|
| Admins, makers, marketers, or analysts, automatically | 
Sep 21, 2025 |
- |
Business value
Improve agent accuracy and reduce testing time by enabling automated test case generation. This feature helps businesses save time and effort by streamlining test case creation, leading to faster validation cycles and fewer deployment risks. With these methods, businesses can reduce manual QA efforts, shorten go-to-market timelines, and enhance AI reliability.
Feature details
The evaluation framework in Copilot Studio enables makers to generate structured test cases using three methods:
- Extracting test cases from manual test sessions Makers can convert past manual test sessions in the test pane into reusable automated evaluation scenarios.
- Importing structured data for targeted testing Makers can upload CSV or TXT files with pre-defined test cases from FAQ files or business datasets.
- AI-Generated test cases based on agent knowledge AI dynamically generates test cases based on the agent’s topics and agent’s description.
Who can enable this? • Available to makers with Evaluation permissions in Copilot Studio. • No additional setup required; accessible directly from the Analytics tab.
Geographic areas
Visit the Explore Feature Geography report for Microsoft Azure areas where this feature is planned or available.
Language availability
Visit the Explore Feature Language report for information on this feature's availability.