Google is rolling out major updates to Gemini in Chrome, including a new side panel interface and a preview of “Chrome auto browse,” an agent-style feature designed to handle multi-step tasks on the web while keeping the user in control.
The updates are described as being built on Gemini 3 and are available in the U.S. on Windows, macOS, and Chromebook Plus, with auto browse rolling out in preview to Google AI Pro and Google AI Ultra subscribers.
What “auto browse” is meant to do
Google describes Chrome auto browse as an “agentic experience” that can take on multi-step chores by following a task you type into Gemini in Chrome.
Once started, auto browse can scroll, click, and enter text on your behalf, and Google says these actions happen on your device while also leveraging a cloud model.
In 9to5Google’s description, Gemini confirms “Task started,” then opens a new tab marked with a cursor and sparkle-style badge, while Chrome also shows an indicator in the top-right corner when auto browse is running.
How the new Gemini side panel works
Alongside auto browse, Google says Gemini in Chrome now has a new side panel experience meant to help you multitask without leaving your current tab.
TechCrunch reports that Gemini in Chrome is moving from a floating window to a persistent sidebar, where you can ask questions about the current website or other open tabs.
TechCrunch also says Gemini can treat multiple tabs opened from a single webpage as a context group, which it frames as useful for comparisons like shopping or price checking.
User control and safety checks
Google says auto browse is designed to keep users in control, and 9to5Google notes you can take over at any time during an automated task.
According to 9to5Google, auto browse can use Google Password Manager to autofill credentials, but only after the user authorizes it.
The same report adds that when shopping or posting to social media, Gemini requires the user to press the final “buy” button or “post” button.
TechCrunch similarly describes auto-browse as asking for user intervention on “data-sensitive” actions such as logging in or completing a final purchase.
Features tied to images and personal data
Google’s release notes say the Gemini in Chrome update adds deeper Google apps integration and also includes a Nano Banana feature to quickly edit images without leaving your tab.
TechCrunch describes Nano Banana as an integration that can modify an existing image using another image or product you find while browsing.
TechCrunch also says Google’s “personal intelligence” capability—described as connecting Gemini to services like Gmail, Search, YouTube, and Google Photos—will roll out in Chrome in the coming months.
As an example of what that could enable, TechCrunch says users may be able to ask Gemini about personal schedule information or have it draft an email and send it without switching into Gmail.
Availability, limits, and what’s not included
Google’s release notes say the Gemini in Chrome updates are available in the U.S. on Windows, macOS, and Chromebook Plus, and that auto browse is rolling out in preview in the U.S. for Google AI Pro and Ultra subscribers.
9to5Google also says auto browse is rolling out starting today to AI Pro and AI Ultra subscribers in the U.S., and it adds that there is a daily limit on how many agentic actions a user can take.
Google’s release notes state these Chrome updates are not yet available to Google Workspace business and education plans.
