×
Microsoft is testing AI-powered file search for Windows 11
Written by
Published on
Join our daily newsletter for breaking news, product launches and deals, research breakdowns, and other industry-leading AI coverage
Join Now

Microsoft has begun testing AI-powered search functionality in Windows 11, allowing dev channel Insiders with Copilot Plus PCs to search local files using natural language queries.

Key features and requirements: The new semantic indexing capability enables more intuitive file searches across Windows settings and common file formats.

  • The feature works offline thanks to Neural Processing Unit (NPU) chips in Copilot Plus computers
  • Currently supports searching through Windows settings and files in JPEG, PNG, PDF, TXT, and XLS formats
  • Functions across multiple search interfaces including Settings, File Explorer, and the taskbar

Implementation details: Microsoft has established specific parameters for the AI search rollout.

  • Users must configure searchable locations through Settings > Privacy & security > Searching Windows
  • An “Enhanced” option allows for whole-machine indexing
  • The feature will initially launch on Snapdragon-powered Copilot+ PCs, with Intel and AMD support coming later
  • Available in six languages: Chinese, English, French, German, Japanese, and Spanish

Expanded functionality: Microsoft is simultaneously enhancing other AI-powered features within Windows 11.

  • The Click to Do feature now includes additional AI writing tools
  • A new “Refine” option within the Rewrite menu provides grammar correction capabilities
  • Future updates will extend search capabilities to cloud storage services like OneDrive

Looking ahead: While this initial rollout is limited to specific hardware configurations and file types, Microsoft’s gradual expansion plans suggest a broader vision for AI-integrated Windows functionality that could reshape how users interact with their files and system settings.

Microsoft opens testing for Windows AI search

Recent News

New framework prevents AI agents from taking unsafe actions in enterprise settings

The framework provides runtime guardrails that intercept unsafe AI agent actions while preserving core functionality, addressing a key barrier to enterprise adoption.

Leaked database reveals China’s AI-powered censorship system targeting political content

The leaked database exposes how China is using advanced language models to automatically identify and censor indirect references to politically sensitive topics beyond traditional keyword filtering.

Study: Anthropic uncovers neural circuits behind AI hallucinations

Anthropic researchers have identified specific neural pathways that determine when AI models fabricate information versus admitting uncertainty, offering new insights into the mechanics behind artificial intelligence hallucinations.