Microsoft has revealed how its upcoming version of Windows 11 is evolving into an agentic operating system, allowing PCs to take control and complete tasks on their behalf. The new “agent workspace” feature will contain AI agents in their own secure session, which users can share data with or shut down at a moment’s notice.
This experimental feature, available in a private developer preview for Windows Insiders, aims to make agentic experiences more productive and secure for individuals and enterprises. Agent workspaces are designed to be lightweight and secure, with memory and CPU usage scaling based on activity.
Microsoft emphasizes the importance of security, highlighting three core pillars: non-repudiation, confidentiality, and authorization. The company also outlines key design principles for AI agents on Windows 11, including autonomy, logging, supervision, least privilege, and adherence to guidelines like the Microsoft Privacy Statement and Responsible AI Standard.
Apps and services built for Windows 11’s agentic capabilities will be required to follow strict guidelines to ensure compliance. Microsoft has already announced that Copilot Actions will be one of the first AI apps to take advantage of these new features, with third-party developers also able to build their own AI agents into their applications.
Source: https://www.windowscentral.com/microsoft/windows-11/microsoft-just-revealed-how-windows-11-is-evolving-into-an-agentic-os-finally-the-explanation-weve-all-been-waiting-for