{Do you know}Evaluate test sets with multiple graders in Copilot Studio
.png "{Do you know}Evaluate test sets with multiple graders in Copilot Studio")
Hello Everyone,
.png)
Today I am going to share my thoughts on the evaluation test sets with multiple graders in Copilot Studio.
.png)
Let's get started.
Yes – Copilot Studio now supports evaluating a single test set with multiple graders in one run. This is listed as a Public preview in the 2025 release wave 2 plan, with availability starting February 8, 2026.
What it does:
- You can attach several graders to the same test set, such as general quality, text similarity, and exact match.
- Each grader can have its own pass criteria.
- When you run the evaluation, Copilot Studio applies all selected graders to every test case in that run.
- Results show up as separate columns per grader, plus an evaluation summary with aggregated results.
Why this helps:
- You can assess different aspects of agent quality in one execution instead of rerunning the same test set multiple times.
- Microsoft's guidance also recommends combining multiple evaluation approaches rather than relying on a single grading method.
Related limits and setup:
- Test sets can contain up to 100 test cases.
- You can create test sets by generating them in Copilot Studio, importing a .csv or .txt file, writing cases manually, or using production data themes.
If you're trying to use it in the product:
- Go to your agent's Evaluation page.
- Create or open a test set.
- Add multiple graders for the test.
- Define pass thresholds for each grader.
- Run the evaluation and compare the grader-specific result columns and summary.
That's it for today.
I hope this helps.
Malla Reddy Gurram aka @UK365GUY
Published on:
Learn more