Chrome Gets Smarter: Gemini Can Now Browse the Web for You

[harlan4096]

Google has announced a major new AI capability coming to Google Chrome. The feature, called auto browse, brings agent-style automation directly into the browser, allowing Gemini to actively interact with websites instead of just answering questions. Powered by Gemini 3, auto browse turns Chrome into something closer to a digital assistant that can do things on the web, not just help you think about them.

What is Chrome’s auto browse feature?

Auto browse is an agentic AI experience built into Chrome’s desktop version. Once enabled, Gemini appears in a sidebar on the right side of the browser, where users can chat with it and assign tasks. Instead of passively summarizing content, Gemini can now:

• Click buttons and links
  
• Scroll through pages
  
• Fill out text fields and forms
  
• Navigate multi-step workflows
  
• Interact with almost any website
  

Once a task is submitted, Gemini confirms with a simple message: “Task started.” This marks a shift from AI as an assistant to AI as an active operator inside the browser.

Real-world examples: shopping, searching, and more

Google showcased auto browse with a practical example: planning a themed party. A user can tell Gemini which site to use (for example, Etsy), what kind of party supplies to look for, and set a budget. Gemini then:

1. Visits the site
   
2. Searches for relevant items
   
3. Adds matching products to the cart
   
4. Looks for available discount codes
   
5. Prepares the checkout for review
   

Continue Reading...