
An inside look at the data science and evaluation systems helping teams improve agent quality at scale in Copilot Studio. The post Who evaluates the evaluators? The data science behind agent evals [https://www.microsoft.com/en-us/microsoft-copilo...
Introducing new capabilities in Microsoft Copilot Studio that help you automate your business processes by mixing AI agents and workflows. The post Automate business processes with agents plus workflows in Microsoft Copilot Studio [https://www.mi...
Custom Graders in Copilot Studio close the gap between what "correctness" measures and what organizations need from their agent evals. The post Custom graders in Copilot Studio: Setting high standards for agent evals [https://www.microsoft.com/en...
Explore Copilot Studio feature updates that support secure, scalable agent development—from enhanced agent evaluations to improved automation tools. The post New and improved: Agent evaluations, computer use, and advanced maker training [https://...
See how new updates to computer‑using agents improve UI automation with secure credentials, detailed monitoring, and scalable Cloud PC capacity. The post Computer-using agents now deliver more secure UI automation at scale [https://www.microsoft....
Explore the new and redesigned guidance hubs to help your organization plan, build, and operate agents with clarity throughout the agent lifecycle. The post New resources and guidance to plan, build, and operate enterprise-ready agents [https://w...
Agent Evaluation in Copilot Studio helps makers move from early optimism to grounded confidence as agents grow in complexity and impact. The post How to evaluate AI agents in Microsoft Copilot Studio [https://www.microsoft.com/en-us/microsoft-cop...
Now available everywhere: Build and manage Copilot Studio agents from the Integrated Development Environment you already use. The post Copilot Studio Extension for Visual Studio Code Is Now Generally Available [https://www.microsoft.com/en-us/mic...