Opera today announced Browser Operator, an AI agent that will do things on your behalf in the Opera web browser. It’s available now in limited preview and will be added to Opera One in a future AI feature drop.
“This feature we’re currently testing marks the first time a browser can use AI to perform tasks on the web and allow you to do more meaningful things with your time instead,” Opera’s Damian Trelka writes. “Browser Operator is native to the browser and makes it easy for you to remain logged in to your websites. This also makes it safe because login information isn’t sent to any third party, and additionally makes the process faster than a server-based solution. What’s more, Browser Operator does this in an efficient and intuitive experience, where you are always in control.”
Browser Operator is designed to perform tasks on your behalf. As you might in an AI chat experience, you use natural language to perform a task, Browser Operator uses Opera’s AI Composer Engine to process your request, and then complete the task in the browser. It will pause and ask you to take action if it needs to fill out a form, confirm an order, or perform some other sensitive task. You can take over at any time, of course, and review the steps Browser Operator took to complete a task.
Opera differentiates Browser Operator from other in-progress AI agents by noting that it doesn’t rely on screenshots or a video capture of a browsing session: It doesn’t need to “see” the screen, it already understands the web. It doesn’t need a virtual machine or cloud-based server. Everything stays local, in the browser, along with your logins, cookies, browsing history, and other browser data. No information–keystrokes, screenshots, personal data of any kind–is sent to Opera or cloud-based servers. Information is only sent to the websites you or the agent interact with explicitly.
During this initial feature preview phase, you can access Browser Operator from the Opera sidebar and command line. You can buy and order things online, book tickets and events, and collect information from a website to fill in a spreadsheet or a document, Opera says. When you give it a task in the form of a prompt, it will work to complete it and may need to occasionally prompt you back to provide more information or interact with a website.
Interesting stuff.