The inevitable has officially happened — Chrome is stepping into the world of agentic AI.

While there’s a lot of variety in AI software, all the big browser companies have recently focused on agentic browsing — each taking its own approach. Companies like Opera launched entirely new browsers built with AI at their core. Others, like Microsoft, introduced AI modes within their existing browsers instead of creating full-fledged new ones.

Interestingly, some of the biggest hits have come from non-browser companies, like Perplexity launching Comet and OpenAI launching ChatGPT Atlas. Nonetheless, what’s truly striking is that arguably the biggest player in the browser space, Google Chrome, has only now taken its first real step into agentic AI.

Chrome’s Auto Browse feature handles tasks for you

The feature can fill out online forms, schedule appointments, fill reports, and more

Google has announced a range of updates to Gemini in Chrome in a post on its The Keyword blog. Leading the pack is the most interesting update: Auto Browse. Described as “a powerful agentic experience that handles multi-step chores on your behalf,” it essentially allows the browser to act like a personal assistant by actually performing tasks for you rather than just explaining how you can perform them.

The company explains that testers have used Auto Browse for various tasks, including filling out online forms, scheduling appointments, filling reports, managing subscriptions, and more. The feature is powered by Gemini 3.0 and can also leverage its multimodal capabilities to understand and interpret images. This means you can also outsource tasks like finding specific items online based on an image and adding them to your cart once found. This isn’t any different from the agentic browsing instances we've seen in browsers like Opera's Neon, Perplexity's Comet, and ChatGPT Atlas.

However, as someone who has been testing all of these browsers, I believe Google's take on it will be a lot more polished, thanks to Gemini 3. Chrome Auto Browse is available for AI Pro and Ultra subscribers within the United States starting now.

Google Chrome is also getting the same interface we’ve seen in other AI browsers, featuring a new Gemini side panel. This effectively means you no longer need to have Gemini or any other chatbot open in a separate tab, and can instantly access AI assistance right alongside whatever you’re working on.

Although Google did add Gemini to Chrome in September 2025, the chatbot was in a floating window. With it now available in a persistent sidebar (which you can toggle on and off), you can also query your open tabs, allowing you to outsource tasks like comparing products across multiple tabs. Google's image model, Nano Banana, is also available directly in Chrome. This means you no longer need to go through the hassle of downloading an image, opening a new tab, and uploading it to Gemini. Now, you can simply type a prompt in the new side panel, explain what you'd like to do, and the edited image will be displayed right within the sidebar.

Google recently announced Personal Intelligence within Gemini, which lets it pull context from other Google apps like Gmail, Photos, Calendar, and more, and use it along with your chats and history to give you better responses. In the announcement, Google explains that it'll be bringing Personal Intelligence to Chrome in the coming months, too.

This will be a completely optional feature, and you’ll remain fully in control. You can choose whether to connect your apps, and you can disconnect them at any time. Once enabled, Personal Intelligence will allow Gemini to provide more contextually relevant answers. Google claims that Gemini in Chrome has been built with "rigorous security standards," and the company has introduced "entirely new defenses to help protect [users] from new types of online threats."