Google Chrome Update: Gemini-Powered ‘Auto Browse’ and AI Workspace

Google has officially launched a major update for the Chrome browser, integrating Gemini to provide proactive assistance through "agentic" workflows. This update focuses on automating repetitive web tasks and improving information synthesis across multiple tabs.

Auto Browse: Task Automation

The standout feature is Auto Browse, an experimental tool designed to execute multi-step tasks across the web.

• Capabilities: It assists with end-to-end actions like filling out complex forms, booking appointments, and coordinating travel plans.
• Safety & Control: The agent does not operate entirely in the background; it is designed to pause for user intervention at critical steps, specifically for logins and at checkout screens to ensure manual authorization of any purchase.
• Availability: This preview is currently restricted to Google AI Pro and AI Ultra subscribers using personal accounts in the United States. It is not currently available for Google Workspace (Business or Education) plans.

Persistent Side Panel & Multi-Tab Support

The browser now features a permanent Gemini Side Panel, replacing the previous pop-up interface to allow for better multitasking.

• Multi-Tab Context: Gemini can now analyze and compare information across multiple open tabs simultaneously. This is particularly useful for synthesizing data from various sources or comparing products across different retailers.
• Future Ecosystem Integration: Google plans to enhance the side panel in the coming months by allowing Gemini to draw context from other Google services, such as Gmail, Calendar, and YouTube, to provide more personalized assistance.

In-Browser Image Editing

Chrome has integrated the Nano Banana AI model, enabling users to perform on-the-fly image edits directly within the browser. Users can modify or clean up images found on any webpage—such as removing backgrounds—without the need for external photo-editing software.