Opera is testing Browser Operator, a new AI agent that performs tasks within the browser. “Today we want to give you a preview of Browser Operator, an AI agent that can get stuff done for you in the Opera browser,” the company wrote in a post. 

According to Opera, Browser Operator can carry out actions like purchasing products, filling out forms, and gathering information from websites without requiring users to navigate or input data manually. “Browser Operator takes AI out of the chatbot and integrates it directly into the browsing flow,” it wrote. 

Unlike traditional AI chatbots that process user inputs externally, Browser Operator works directly within the browser. Opera claims that Browser Operator is designed to make browsing more efficient, allowing users to focus on other activities while the AI handles routine web tasks.

With AI-powered automation becoming a major trend in web browsing, Opera also claims this tool removes the need for cloud-based AI processing. The AI agent is currently in Feature Preview, expected to launch soon, and is part of its AI feature drop program. It will be accessible through the Opera sidebar and command line.

How Browser Operator works

Instead of relying on external cloud-based servers, Browser Operator runs locally on users’ devices. Opera says the AI tool uses the browser’s Document Object Model (DOM) Tree and layout data to understand webpage content. It can access an entire webpage at once, without needing to scroll.

To initiate a task, users can enter a command. For example, if a user wants to book a concert ticket, Browser Operator will navigate the website, select the preferred option, and proceed with the booking. However, for security-sensitive actions such as entering payment details or confirming an order, the Browser Operator will pause and request manual input.

Opera says users remain in control throughout the process. They can review each step taken by the AI, intervene at any point, or cancel tasks instantly.

Privacy and security concerns

Given increasing concerns about AI and user privacy, Opera highlights that no browsing data, keystrokes, or screenshots are sent to its servers. Everything happens locally on the user’s device. The AI does not access profile details or stored passwords, and it won’t interfere with login sessions.

This local-first approach differs from AI-powered assistants like OpenAI’s ChatGPT-based Operator, which relies on cloud processing. 

How does Browser Operator compare to other AI-powered browsers?

Opera is not alone in integrating AI into web browsing. The competition is heating up as multiple companies experiment with browser-native AI agents. OpenAI has released its Operator, available to ChatGPT Pro users. This AI tool can browse the web and perform similar agent tasks. Last week, Perplexity said it will introduce Comet, its web browser, soon. 

Opera already offers Aria, an AI-powered side panel that helps users search the web, generate text, and answer queries. However, Browser Operator takes a different approach—moving beyond chat-based AI assistance to direct task execution within the browsing environment.

‍