Opera Browser Gets an AI Evolution: First "Task Execution" Feature

Opera, the Norwegian tech company known for its innovative spirit, is once again at the forefront of browser technology. Recently, Opera announced the launch of a program called Browser Operator The new AI agent function brings users an unprecedented browsing experience. This innovative technology is like installing an intelligent assistant to the browser that understands the user's natural language commands and proactively performs a variety of online tasks, truly transforming the browser from an information display platform to a proactive service tool.

Say goodbye to cumbersome, AI agent makes the browser "move"!

For a long time, the browser in our impression, more play a passive role in the presentation of information. We need to manually enter the URL, manually click on the link, all operations are inseparable from the user's "instructions". The Browser Operator launched by Opera tries to break this traditional model, so that the browser becomes smarter and more active.

Imagine telling your browser, "Buy me some white tennis socks, XXX brand and size L," and Browser Operator automatically completes the entire shopping process, from searching for a product, filtering sizes, adding it to your cart, to paying for it. This is no longer a scene from a sci-fi movie, but the future that Opera is working to realize.

Opera says Browser Operator is designed to free users from tedious online tasks so they can invest their valuable time in more meaningful things. Whether it's shopping online, booking a flight or hotel, or gathering information to fill out a form on a web page, Browser Operator is the perfect companion. Users can monitor the progress of a task at any time and take over or cancel it when needed, ensuring that everything is under control.

Example of usage scenarios

• Scenario 1: Easy Online Shopping For busy office workers, online shopping is convenient, but it also takes a lot of time to select products, compare prices and place orders. With Browser Operator, users can simply describe their needs, such as "Buy the latest [product type] from [e-commerce platform name] at a price around [price range] with a rating of 4.5 stars or more", and Browser Operator will automatically complete the product filtering, sorting, adding to shopping cart, and so on, Browser Operator will automatically filter, sort, add to cart, and so on, and the end user only needs to check the order information and confirm the payment.
• Scenario 2: Rapid Information Collection Researchers or data analysts often need to collect information from web pages, and manually copying and pasting is inefficient and error-prone. With Browser Operator, users can specify the type of information to be collected and the target website, for example, "Grab all today's news headlines and links about [keyword] from [news website] and save them to [specified document format]", and Browser Operator will quickly grab the relevant information and organize it into a structured document. Browser Operator can quickly capture relevant information and organize it into a structured document, greatly improving the efficiency of information collection.

Browser Operator's User Experience

Browser Operator is currently in preview mode and can be accessed through the Opera browser's sidebar and command bar. To use Browser Operator, simply enter the tasks you want it to perform for you.

For example, you can have it purchase items online, book tickets and events, or even collect information from websites to populate a spreadsheet or document.

Browser Operator will let you see how the process is progressing and the steps it is taking to accomplish the task:

When you give Browser Operator a task command in the form of a prompt word, it will start working to complete the task, and may occasionally require your input to do so, which is called "human-machine collaboration". You can then interact directly with the web page or provide more information through Browser Operator's chat interface.

For example, if you need to fill out a form, you can either enter the information directly on the web page, or provide it to Browser Operator and click "Continue" so that it can resume and complete the task.

In addition, you can cancel the task that Browser Operator is performing at any time, just by clicking the Cancel button:

Finally, when the entire task is complete, you have the option to either end the task or provide Browser Operator with further instructions detailing what you have just accomplished. A polite "thank you" is always nice 🙂 but for example, if you placed the wrong order, you can instruct Browser Operator to cancel it. Browser Operator will then understand which order you are referring to and cancel it for you.

Locally based, safety and efficiency go hand in hand

With so many vendors exploring AI proxy technologies, Opera's Browser Operator solution is unique. It utilizes a local client-based strategy, as opposed to solutions that rely on screenshots, video capture, or cloud servers.

Opera's AI agent runs directly in the user's browser environment, without the need for a virtual machine or cloud server. This localized operation not only maximizes the protection of user data privacy and ensures that sensitive data, such as user login information, is not sent to third-party servers, but also greatly improves the efficiency of task execution. Because Browser Operator directly accesses the DOM tree and browser layout data of a web page, it is able to "understand" the structure of a web page like a human being, without having to "watch" the screen pixels like an image recognition AI, thus enabling faster and more faster and more accurate operations.

What's more, Browser Operator is able to efficiently handle various pop-ups in web pages, such as common cookie consent pop-ups and validation dialogs, thanks to its ability to interact with web elements that are not visible to the user. These advantages make Browser Operator better in terms of user experience, security and efficiency.

Continuous Innovation, Opera's AI Browser Journey

Opera has always been a pioneer in browser innovation. From the earliest tabbed browsing and address bar search, to built-in VPNs, sidebar instant messengers, and the first native browser AI -- Aria -- Opera has continued to push the boundaries of what a browser can do, and is committed to providing users with an even better online experience.

Against the backdrop of the global wave of AI technology, Opera has once again demonstrated its forward-looking strategic vision. As early as 2023, Opera was the first to incorporate AI features into its browser, and continues to iterate and improve Aria's functionality through the AI Feature Drops program, with innovative features such as native LLM, image generation, and AI tab commands making their debut in Opera Browser one after another.

The launch of Browser Operator is undoubtedly another major breakthrough for Opera in the field of AI browsers. It signifies that Opera is transforming the browser from a tool to an intelligent agent that can actively serve users, leading the browser into a new era of "Agentic Browsing".

Previews are coming, the future is bright

Browser Operator is currently in the preview stage, and users can experience this cutting-edge technology through the Opera browser's sidebar and command bar.Opera plans to officially release Browser Operator in future AI Feature Drops, so that more users can experience the convenience and efficiency of the AI agent.

With the continuous development of AI technology, we have reason to believe that Browser Operator is just the beginning. In the future, AI will play an increasingly important role in browsers, bringing users a more intelligent, personalized and scenario-based browsing experience. Opera will undoubtedly continue to lead this trend of browser change.