We are announcing the ability to optimize AI-driven outcomes with prompt evaluations in AI Builder. This feature will reach general availability on September 15, 2025.
How does this affect me?
This feature enables you to build a test suite to check your prompt performance across different stages of prompt development.
As you create or refine prompts, the feature analyzes the prompt structure, language, and relevance to the task. It assigns a confidence score to each test case prediction that shows the expected performance of the prompt. With this score, you receive actionable insights to improve prompt phrasing or reduce ambiguity.
What action do I need to take?
This message is for awareness and no action is required.
If you would like more information on this feature, please visit the Optimize AI-driven outcomes with prompt evaluations learn article.
Source: Microsoft
Latest Posts
- MC1558114: Microsoft Defender for Cloud Apps Adds Unified RBAC Support for App Governance to Manage Non-Human Identities

- MC1558041: OneDrive for iPad Adds Presentation Mode for PDFs

- MC1558033: Microsoft 365 Copilot Managed Runtime reaches general availability and expands app building in Copilot Cowork

- MC1558032: Microsoft Teams Mobile Adds Intelligent Call Recap for Call Queues in the Queues App







