Google has revamped Chrome with a groundbreaking feature driven by its AI model, Gemini. This enhancement enables the web browser to complete tasks autonomously, combining user requests with sophisticated artificial intelligence.
Google introduced the “auto browse” functionality, initially available exclusively to desktop users of Chrome, targeting subscribers of Google AI Pro and AI Ultra services.
Auto browse provides an interactive experience through a sidebar within Chrome that hosts the Gemini AI assistant. Users can converse with the assistant, allowing it to carry out tasks directly on web pages.
Gemini can effectively execute tasks with the auto browse feature in Chrome.
With auto browse, Gemini performs various actions such as clicking buttons, entering text, and navigating through web pages. Users simply type what they would like the AI to do in the sidebar, and Gemini acknowledges with a prompt stating, “Task started.”
A user might instruct Gemini to shop for themed party supplies on Etsy. After providing the website, party type, and budget, Gemini searches Etsy, compiles items into a shopping cart, and alerts the user when the cart is ready for review.
Additionally, Gemini seeks out discount codes and can access Google Password Manager to facilitate account logins on various websites.
A task executed by the Gemini-driven auto browse feature in Chrome.
Additionally, Chrome features a “Take over task” button at the top of the browser for user intervention if the AI deviates from the intended task.
This addition aligns with Google’s ongoing commitment to integrating AI into its products, showcasing a shift toward more integrated digital assistance in everyday web tasks.