Introducing Copilot Vision: The Next Generation of AI Support in Edge
What is Microsoft Copilot Vision?
Microsoft has launched a new feature called Copilot Vision, part of its advanced AI assistant embedded in the Edge browser. This innovative feature enables the assistant to see and comprehend what is displayed on a user’s screen. The announcement was made by Mustafa Suleyman, CEO of Microsoft AI, via a post on Bluesky.
How Copilot Vision Works
Copilot Vision aims to create a ‘conversational experience’ for users. By simply clicking on the microphone icon, users can give voice commands. This allows Copilot to analyze on-screen content and provide customized feedback or guidance. For example, users can request detailed steps for cooking recipes or ask for an interpretation of a job description to help prepare for interviews. Nonetheless, Microsoft warns users to avoid depending on AI for crucial tasks like crafting resumes or important documents.
Who Can Use Copilot Vision?
Currently, the complete integration of Copilot Vision is reserved for subscribers of Copilot Pro. These users can utilize Vision not only within the Edge browser but also in applications such as Photoshop, video editing tools, and even interactive games like Minecraft. This wide application makes Copilot Vision a versatile tool for various digital tasks.
How to Get Started with Copilot Vision
For users of Edge, accessing the basic features of Vision is straightforward. After signing up through a special link on Microsoft’s website, users can start a Vision session by clicking the microphone icon in the browser. An audio cue along with a change in the browser’s color scheme indicates that the session has begun. Microsoft has made it clear that during this interaction, only Copilot’s responses are stored, with no recording of screenshots, content, or voice inputs.
Ending a Session
Users can conclude their Vision session in two ways: either manually by closing the session or by simply exiting the Edge browser. It’s important to note that Copilot Vision may not function properly on all websites, so users may experience occasional limitations.
Benefits of Using Copilot Vision
- Enhanced Interaction: The use of voice commands provides a more natural way to interact with digital content.
- Tailored Guidance: Users receive personalized feedback based on real-time content analysis.
- Support Across Applications: The versatility of Copilot Vision allows it to assist users in creative software and gaming environments, enhancing overall productivity.
