Editorial illustration for Google’s ‘Auto Browse’ agent, using Gemini 3 AI, books flights, finds apartments
Google’s ‘Auto Browse’ agent, using Gemini 3 AI, books...
Google's latest AI doesn't want to talk. It wants to drive. The company just released Auto Browse, an agent that will take control of your Chrome browser to do things like book flights and find apartments.
It works for U.S. subscribers of the AI Pro and AI Ultra plans starting today. You call it up from the Gemini sidebar. Then it clicks, scrolls, and submits forms on your behalf.
This is a distinct move. Last year's "Gemini in Chrome" could read your screen and summarize tabs. Auto Browse leaves the garage. It uses the new Gemini 3 model to actually perform tasks across the open web.
The tool, powered by Google's current Gemini 3 generative AI model, is an AI agent designed to take over your Chrome browser to help complete online tasks like booking flights, finding apartments, and filing expenses. The release of Auto Browse is part of Google's continued integration of AI features into Chrome. Last year, Google dropped the "Gemini in Chrome" mode to answer questions about what's on web pages and synthesize details from multiple open tabs. Auto Browse, which users can access by launching the Gemini sidebar in Chrome, will only be available today in the US to subscribers of Google's monthly AI Pro and AI Ultra plans.
The technical promise is straightforward: less tedious work for you. The cultural shift is not. Your browser is no longer just a tool you operate. It becomes an engine with its own driver.
You are outsourcing the friction of the modern web. The pop-up negotiation. The form filling.
The price comparison grind. In return, you surrender direct control over that process. You must trust its choices, its clicks, its interpretation of a rental listing's fine print.
Convenience has a cost. This agent requires a subscription fee, of course. It also demands a new kind of faith.
The web begins to reshape itself for these machine customers, optimizing for their logic over human intuition. Auto Browse is a useful errand runner. It is also a quiet transfer of agency from your hands to its code.
Related Reading
Browse all Google news →
Open Source Trump cracks down on Anthropic after Amazon tip; staff largely foreign
Open Source SDOF Adds Two Defensive Layers via Intent Router and StateAwareDisp
Open Source D&B rebuilds 642 million‑business database after AI agents hit limits
Related Topic NVIDIA and Google Cloud let developers scale AI from prototype to production
Market Trends
Related Topic Google tests visual 'magazine-style' UI for Gemini 3 Pro users
LLMs & Generative AI
From Archives Moltbot routes requests through OpenAI, Anthropic or Google and fills web forms
From Archives Moonshot AI launches Kimi K2.5, open‑source LLM that outperforms Opus 4.5
From Archives ADL study finds Grok most antisemitic among ChatGPT, Gemini, Claude
LLMs & Generative AI
From Archives Google's Smart Glasses Lead in Software, Yet Lag on Style, Partner Samsung
Business & Startups
Common Questions Answered
What is Google's Auto Browse agent and how does it differ from previous Gemini in Chrome features?
Auto Browse is an AI agent powered by Gemini 3 that takes control of your Chrome browser to complete tasks like booking flights and finding apartments, rather than just reading and summarizing your screen like the previous year's Gemini in Chrome feature. It actively clicks, scrolls, and submits forms on your behalf, representing a significant shift from passive screen reading to active browser automation.
Which Google subscription plans have access to Auto Browse and how do users activate it?
Auto Browse is available to U.S. subscribers of the AI Pro and AI Ultra plans starting from the release date. Users can access it by calling it up from the Gemini sidebar, where the agent will then take over browser actions to complete their requested tasks.
What are the main trade-offs users should consider when using Auto Browse?
While Auto Browse reduces tedious web tasks like pop-up negotiation, form filling, and price comparison, users must surrender direct control over the browsing process and trust the AI's choices, clicks, and interpretation of information like rental listing details. This convenience comes at the cost of giving an autonomous agent decision-making power over your web interactions.
What specific tasks can Google's Auto Browse agent perform?
Auto Browse can handle various web-based tasks including booking flights and finding apartments by autonomously navigating websites and completing necessary forms. The agent is designed to handle the repetitive and friction-filled aspects of modern web browsing that typically require manual user interaction.
