Google adds Auto-Browse to Gemini in Chrome

29 Jan 2026 Google is adding an “auto browse” capability to Gemini in Chrome that can carry out multi-step web tasks for you. The feature is being rolled out 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 — effectively automating multi-step browsing workflows on your behalf according to Google. While running auto browse, Gemini can analyze a photo on your screen, identify decorative items, find similar products online, add them to your cart, and even try discount codes while respecting a budget you set. If a task requires signing in, Gemini can use Chrome’s password manager to log in. Google has moved Gemini from a pop-up into a right-anchored panel that integrates with Gmail, Calendar, Maps, Google Shopping, and Google Flights so the agent can reference and act on data across those apps. The panel also includes Nano Banana, Google’s image generator/editor, letting users edit images in-window via text prompts. Google positions auto browse as another step toward more agentic browsing and cites competition from other agentic AI browsers like OpenAI’s Atlas and Perplexity’s Comet. It also says an opt‑in “Personal intelligence” feature — which lets Gemini reference past conversations and analyze Gmail, Calendar, Photos, and search history — will arrive in Chrome in the “coming months.” Source