Sunday 8 February 2026Afternoon Edition

ZOTPAPER

News without the noise


AI & Machine Learning

Google Launches AI Agent in Chrome That Can Browse and Act on Your Behalf

New "auto browse" feature performs multi-step tasks using Gemini

Nonepaper Staff2 min read📰 3 sources
Google is rolling out a new "auto browse" capability in Chrome that allows the Gemini AI to perform complex, multi-step tasks on behalf of users—from researching travel options to filling out forms and managing subscriptions.

The feature, available to Google AI Pro and Ultra subscribers in the US, represents a significant expansion of Gemini's capabilities within Chrome. Unlike simple chat assistants, auto browse can navigate multiple websites, compare options, and complete actions.

Google says the AI can research hotel and flight costs, schedule appointments, fill out online forms, and handle subscription management. This builds on earlier Gemini integrations that allowed summarizing web content and comparing products across tabs.

Analysis

Why This Matters

This is a major step toward "agentic AI"—AI systems that can take actions in the real world rather than just provide information. Browser automation has enormous potential but also raises questions about control and safety.

Background

Google has been steadily expanding Gemini's presence in Chrome, moving from simple chat to increasingly autonomous capabilities. The company is competing with OpenAI's similar browser-based agent features.

Key Perspectives

Enthusiasts see this as a productivity revolution; skeptics worry about AI making purchases or commitments without proper user oversight.

What to Watch

How users adopt the feature, what guardrails Google implements, and whether competitors match these capabilities.

Sources