Google Unleashes AI in Chrome with ‘Auto Browse’

Last year, Google fueled up its Chrome browser with its Gemini AI model. Now it’s pressing on the gas. In what the company is calling a “new era of browsing,” Google is introducing a slew of new features that further embeds its Gemini 3 model into its browser, now with a side panel capable of multitasking, integration with Google Apps, and a feature called “auto browse” that can navigate the web on a user’s command.

Google’s preferred headliner for the announcement is its new side panel, which keeps Gemini on screen as a browsing assistant across tabs. The company said that users would be able to perform separate tasks in the sidebar while keeping the browser tab open to their primary focus.

In a demonstration for the press, Google’s Vice President of Chrome, Parisa Tabriz, described the use of the sidebar. “I can have my assistant side-by-side with the content I see in my screen,” she said. “But most importantly, I can actually go ahead and start a completely new conversation on a different tab if I wanted to.”

Per Google, the feature opens up new ways to multitask directly in the browser. “Our testers have been using it for all sorts of things: comparing options across too-many-tabs, summarizing product reviews across different sites, and helping find time for events in even the most chaotic of calendars,” the company said in a blog post.

Part of that expanded multitasking includes working across the Google suite. The Gemini assistant in Chrome can connect to Gmail, Calendar, YouTube, Maps, Google Shopping, and Google Flights, and can complete tasks within these services. “For example, if you’re traveling to a conference and need to book a flight, Gemini can dig up that old email with event details, reference context from Google Flights to provide some recommendations, and later draft an email letting your colleagues know your arrival time.” In a demonstration, Tabriz explained users would be able to compose an email in Gemini and hit send without needing to leave the sidebar. 

According to Google, users will be able to enable access to any of the Google apps in the Connected Apps section of Gemini Settings.

© Google

Google has also brought along its image generation tool Nano Banana, which can now “transform images” in the browser without requiring the user to download the image. Users can give Gemini a prompt in the side panel, and it can modify the image directly in the browser.

Perhaps the most intriguing upgrade that Google announced is locked behind a paywall. Google AI Pro and Google AI Ultra subscribers will be able to use what the company is calling Auto Browse. It’s positioning it as a more powerful version of autofill, but it’s not exactly a clean analogy. Auto Browse is an agentic feature that allows users to give Gemini a multi-step task to complete on their behalf, all within the browser, across different tabs and services.

“Auto Browse actually moves from just being able to give the information to you to actually really taking control of your browser and doing things completely on your behalf,” Tabriz said. In a demonstration, she gave Gemini a prompt to re-order the same jacket that she had purchased a year prior. Gemini opened a new tab and began carrying out the task, navigating to the correct company website, logging into Tabriz’s account, scanning through previous orders until it found one that was referenced in the prompt, and beginning the process of re-ordering.

© Google

Tabriz said Gemini would take the task as far as it could and would prompt the user any time it runs into a hurdle. It’ll also stop before finishing the transaction, requiring the user to confirm before making a purchase. Per Google, the feature will have support for Etsy, Shopify, Target, and Wayfair, so Chrome can shop across those platforms.

Google also suggested the feature could be used for the “mundane work” of doing things like researching hotel and flight costs across multiple date options for a vacation, among other tasks. “Our testers have used it for all sorts of things: scheduling appointments, filling out tedious online forms, collecting their tax documents, getting quotes for plumbers and electricians, checking if their bills are paid, filing expense reports, managing their subscriptions, and speeding up renewing their driving licenses—a ton of time saved,” it said.

Earlier this month, Google announced “Personal Intelligence” in Gemini, which can pull from just about anything you’ve done across the Google ecosystem, including Gmail, Google Calendar, the content in your Google Drive and Google Photos, and things like your YouTube watch history, Google Search history. The company said in the coming months, it’ll bring Personal Intelligence to Chrome, as well. Additionally, Chrome will be able to remember past conversations. The feature will be opt-in and will allow users to choose which apps they would like to be included in Chrome’s Personal Intelligence.

According to Tabriz, Gemini will work locally on a user’s device, but will send data back to the cloud. Features like the new side panel and Nano Banana integration will be available to Chrome users starting today. Auto Browse will also be available today for AI Pro and AI Ultra subscribers. Personal Intelligence will be available in “the coming months.”