Google is launching a new “auto browse” feature inside Chrome that can perform multi-step tasks on your behalf. The Gemini AI-powered capability is coming to Google AI Pro and Ultra subscribers in the US, and can do things like research hotel and flight costs, schedule appointments, fill out online forms, manage subscriptions, and more.
Google says that while using auto browse, Gemini can identify decorations inside of a photo you’re looking at, find similar items on the web, add them to your cart, apply discount codes, all while staying within your budget. If a task requires you to log into an account, Gemini can also use the browser’s password manager to log in.
Along with this change, Google has moved Gemini in Chrome from a pop-up window to a panel anchored to the right side of your screen. It now supports integrations with Gmail, Calendar, Maps, Google Shopping, and Google Flights for all users, allowing it to reference information from across the apps you use, as well as perform actions within them.
“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,” Google writes.
You’ll also find Nano Banana — Google’s AI-powered image generator — in the new Gemini in Chrome panel. This feature is coming to all Gemini in Chrome users, and lets you edit an image inside your window using a text prompt.
Google has more in store down the road for Gemini in Chrome as it competes with other agentic AI browsers, including OpenAI’s Atlas and Perplexity’s Comet. Personal intelligence, an opt-in feature that first launched inside the Gemini app, gives Gemini the ability to reference your past conversations, as well as use its reasoning capabilities to analyze the data linked to your Gmail, Calendar, Photos, and search history. Google says it plans on bringing the feature to Chrome in the “coming months.”