Google has recently upgraded its Gemini feature in Chrome, introducing “Auto-Browse.” This innovative feature uses AI agents to complete tasks on your behalf while you focus on other activities.
To use Auto-Browse, simply give a prompt via Gemini, and the tool will take over your Chrome window. It can load new sites, navigate current ones, fill out forms or login prompts, and even edit web images without downloading them.
Auto-Browse is an effortless way to inject web context into Gemini chats, making it more helpful in various tasks such as summarizing or comparing information across multiple tabs, extracting specific information from crowded sites, or finding free time in your day while reviewing personal and work calendars simultaneously.
One of the best features of Auto-Browse is its ability to complete tasks without your input. This agentic browsing solution allows Gemini to browse for you, making it a game-changer for users who want to save time and effort.
While Auto-Browse is currently limited to Google AI Pro and Ultra subscribers in the US, it showcases the potential of Google’s AI models and their applications in everyday life.
As an example, I use Auto-Browse when working on tasks that require multiple tabs or browsers. By switching to Chrome and using Gemini, I can save time and streamline my workflow without needing to download and reupload information from multiple sources.
Source: https://www.makeuseof.com/i-finally-gave-gemini-in-google-chrome-a-shot