user instructions

Winsage
July 14, 2026
Microsoft's design strategies continue to influence users towards its Edge browser, as revealed in a study by Dr. Harry Brignull and Cennydd Bowles, published by Mozilla. The researchers tested Windows 10 and 11 across the US, UK, India, and Germany, focusing on whether users could download, set, and maintain a default browser other than Edge without interference. Findings showed that users encountered harmful design patterns that hindered their ability to choose alternative browsers. For example, searching for "download Chrome" on Bing led to Edge promotions, and downloading Chrome triggered an Edge banner. In Windows 11, the setup prompts users to allow Edge to import data from other browsers, with the accept option more visible than the decline option. Additionally, Microsoft's Copilot and Windows Backup tool opened links in Edge regardless of the user's default browser choice, resetting the default browser to Edge during migration without consent. The study noted regional differences, with fewer harmful patterns in Germany due to the EU's Digital Markets Act, although some issues persisted. The researchers recommend eliminating these harmful design patterns and advocate for global regulatory enforcement.
Winsage
November 18, 2025
Microsoft Windows is evolving to incorporate AI agents that act autonomously, resembling digital coworkers. This shift is facilitated by the Model Context Protocol (MCP), which standardizes agent interactions with tools and data sources, ensuring secure access to system resources. Windows introduces an on-device registry of "agent connectors" for functionalities like file access and system settings, managed through an OS-level proxy that oversees identity, permissions, consent, and audit logging. The initial connectors focus on File Explorer and System Settings, defining clear capabilities and restrictions for agents. A transparent consent model allows users to manage permissions easily, promoting a user-friendly experience. The introduction of an Agent Workspace provides a dedicated environment for agents, ensuring they operate independently and with least-privileged access. Security measures include signed connectors and a standardized proxy for authentication and auditing, enabling visibility into agent actions. Windows is also expanding on-device AI processing with APIs for various functionalities, allowing agents to leverage local models securely. While Windows is not becoming an agent-first operating system, it is establishing a framework for human and agent interactions, positioning itself as a safe environment for AI operations. The foundational elements for this evolution include standard interfaces, clear permissions, isolated environments, and system-level observability.
Search