From Desktop Preview to Mobile: Auto Browse Expands
Chrome’s AI productivity tool, auto browse, is making the jump from desktop preview to Android, marking a key step in Google’s effort to automate online tasks directly in the browser. Initially introduced for Chrome on PCs in January, auto browse acts as an agentic assistant powered by Gemini that can navigate websites and complete multi-step web workflows on your behalf. Instead of manually clicking through forms and pages, users describe what they need, and the Chrome Android assistant executes the routine steps. Google says the feature will begin rolling out to Android users in late June, mirroring the desktop experience but adapted to a smaller screen. Access is limited to Google AI Pro and Ultra subscribers, and devices must run Android 12 or higher, underscoring that this is a high-end capability tailored for users who want to automate online tasks across both desktop and mobile.
How Chrome’s Auto Browse Handles Your Online Errands
Auto browse is designed to tackle tedious online errands that typically eat into your day. Within Chrome, you can simply ask Gemini to handle a task—such as finding a parking spot for a comedy show—and the assistant will pull details from your ticket confirmation, then navigate relevant sites to secure a suitable option. The AI can browse, interpret pages, and progress through steps like searching, filtering, and filling forms, all within the browser. However, it deliberately stops short of certain sensitive actions. When a workflow requires making a purchase, accessing saved credentials from Google Password Manager, or posting on social media, auto browse pauses and asks for explicit confirmation. This balance aims to keep the AI productivity tool genuinely helpful without ceding full control of your identity or finances, allowing users to stay in the loop while still offloading the repetitive parts of online errands.
Gemini in Chrome on Android: Chat, Context, and App Tie-ins
The arrival of auto browse is part of a wider Gemini Android integration inside Chrome. A new Gemini icon appears at the top right of the browser toolbar; tapping it opens a chat interface from the bottom of the screen, bringing most of the Gemini in Chrome capabilities from PCs to mobile. Beyond basic chat, users can generate images via Nano Banana, and tap into Personal Intelligence features that draw context from other Google services like Calendar and Keep. This means the Chrome Android assistant can reference your events or notes when helping automate online tasks, blurring the line between browser and system-wide assistant. Deep integration across apps and services positions Chrome not just as a window to the web, but as a control hub for everyday digital workflows, reinforcing Android as a platform built around AI-driven productivity.
Security, Requirements, and Google’s AI Automation Ambitions
Google is emphasizing security as it brings auto browse to Android. The company says the same protections used on desktop apply to mobile, including defenses against emerging threats like prompt injection. Auto browse is engineered to ask for confirmation before completing sensitive actions, such as purchases or social posts, ensuring users retain final authority even as they automate online tasks. To access Gemini in Chrome and its advanced features, including auto browse, Android devices must have at least 4GB of RAM and run Android 12 or newer. The rollout, starting in late June for eligible users, underscores a broader strategy: making Android devices smarter by embedding AI directly into core apps rather than isolating it in standalone assistants. By turning Chrome into an AI productivity tool that can plan, browse, and execute tasks, Google is betting that the future of mobile productivity lies in seamless, browser-native automation.