Vision in Microsoft 365 Copilot can analyze content shared on desktop screen and through mobile camera
[Android, Windows, iOS, Web]
Vision in Microsoft 365 Copilot helps you make faster, more informed decisions by understanding context from what you share on screen or camera. Copilot can analyze visual inputs from shared desktop screens and provide detailed insights about the content. You can also use vision on mobile during a real-time voice session to share your device camera, front or back, and ask questions about what is in front of you. Copilot analyzes the live camera feed or desktop screen in real time and provides spoken, context-aware answers grounded in work and web data.
Roadmap ID:
561037
Details:
What changed:
Copilot now processes live visual data from desktop screen sharing and mobile device cameras during voice sessions. Previously, Copilot relied on text and static data inputs only. Vision interprets the live feed in real time and delivers spoken answers grounded in work and web data, enhancing decision-making.
Why:
Analyzing visual context from screens and cameras accelerates understanding and supports faster, informed decisions without switching apps.
Try this:
Share your desktop screen in a Microsoft 365 Copilot session and ask questions about visible content.
During a voice session on mobile, activate the camera and point it at an object or document.
Ask Copilot questions about the live camera feed and listen to spoken, context-aware answers.
Why this matters:
Real-time visual analysis reduces information gaps and streamlines workflows by integrating visual context into conversations.
Business impact:
Teams can collaborate more effectively with instant insights from shared visual content across devices.
Personal impact:
You gain the ability to quickly understand and act on visual information without manual searching or switching contexts.