MC1530742 Low
Copilot Studio - Task completion grader
Summary AI-generated
Task completion grader in Copilot Studio is now generally available, allowing evaluation of agent success in accomplishing tasks to improve reliability and outcomes.
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- MC1530748 Copilot Studio - Tool accuracy grader
- MC1531932 Copilot Studio - Custom Graders Library and Ready-to-Use Microsoft Graders
- MC1531924 Copilot Studio - Generated custom grader
- MC1531903 Copilot Studio - Evaluation for automation flows
- MC1261573 Microsoft Copilot Studio – Tool & Topic Invocation Grader
- MC1323229 Microsoft Copilot Studio - Automate web and desktop apps with computer use
Original post from Microsoft
We are announcing the task completion grader in Copilot Studio. This feature reached general availability on October 15, 2026.
How does this affect me?
This feature enables you to evaluate whether your agents successfully accomplish their intended tasks, beyond simply generating a relevant or high-quality response. This helps you to identify functional failures, improve agent reliability, and gain greater confidence that agents are delivering the expected business outcomes.
What action do I need to take?
This message is for awareness, and no action is required.
How does this affect me?
This feature enables you to evaluate whether your agents successfully accomplish their intended tasks, beyond simply generating a relevant or high-quality response. This helps you to identify functional failures, improve agent reliability, and gain greater confidence that agents are delivering the expected business outcomes.
What action do I need to take?
This message is for awareness, and no action is required.