MC1518085 High
Microsoft Copilot Studio - Improvements to agent Evaluations experience
Summary AI-generated
Enhancements to Evaluations in Copilot Studio offer richer explanations, improved validation and troubleshooting, and better dataset support to help makers optimize agent quality.
Written by Azure OpenAI (gpt-4.1) from the text of the post below. It can be incomplete or wrong; the original post is authoritative.
Similar posts
Search for more like this- MC1190188 Microsoft Copilot Studio – Increase sense of security for makers inside Copilot Studio
- MC1518233 Copilot Studio - Enhanced support for Copilot Chat agents
- MC1218332 Power Platform - Track, manage and scale Copilot adoption in PPAC new functionality
- MC1325011 Microsoft Copilot Studio - Evaluate the entirety of multi-turn conversations
- MC1403399 Microsoft Copilot Studio - Create agents optimized for Microsoft 365 and Microsoft 365 Copilot users
- MC1402296 Microsoft Copilot Studio – See a unified view of errors, warnings, and governance notifications
Original post from Microsoft
We are enhancing the Evaluations experience to help makers better understand agent quality and behavior in Microsoft Copilot Studio. This feature is now available.
How does this affect me?
The improvements will bring new capabilities that help makers identify quality issues more quickly, understand why evaluations succeed or fail, compare results across runs, and create higher quality evaluation datasets with less manual effort. Additional validation and guidance will help makers resolve configuration issues before running evaluations. New capabilities include the following:
What action do I need to take?
This message is for awareness, and no action is required.
How does this affect me?
The improvements will bring new capabilities that help makers identify quality issues more quickly, understand why evaluations succeed or fail, compare results across runs, and create higher quality evaluation datasets with less manual effort. Additional validation and guidance will help makers resolve configuration issues before running evaluations. New capabilities include the following:
- Richer explanations of evaluation outcomes will help makers understand why evaluations succeed or fail.
- Reasoning traces and cited knowledge sources will help makers understand agent behavior and grounding.
- Evaluation run comparison will help identify improvements and regressions across runs.
- Evaluations will support datasets with up to 100 test cases.
- Makers will be able to use customizable dataset and question generation.
- Makers will be able to generate datasets from configured knowledge sources.
- Single-response datasets will be supported.
- Improved validation, connection prerequisite checks, credit-limit enforcement, and actionable error messages will help makers resolve configuration issues before running evaluations.
What action do I need to take?
This message is for awareness, and no action is required.