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 | 
Mar 31, 2026 |
Mar 31, 2026 |
Business value
This feature provides the following benefits:
- Grounds evaluation in real customer interactions rather than synthetic test data.
- Reduces time and manual effort required to build representative test sets.
- Improves evaluation accuracy by reflecting real-world usage patterns and edge cases.
- Accelerates issue discovery by surfacing quality gaps seen in production scenarios.
- Increases confidence in release decisions by aligning testing with actual customer behavior.
Feature details
This capability enables makers to generate structured evaluation inputs directly from real production conversations.
Instead of manually crafting synthetic test cases, makers can convert historical interactions into reusable evaluation datasets.
Makers can generate the inputs from:
- Conversation themes
- User reactions
What makers gain:
- Evaluation scenarios that reflect real-world behavior.
- Faster test set creation.
- Broader coverage of edge cases.
- Continuous alignment between production usage and evaluation practice.
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.