Opera has transformed into the swift gun-toting Agentic AI trend, with some companies starting to utilize it to control web interfaces through commands (such as OpenAI Operator). Introducing the feature of an embedded Agent in the browser itself, known as Browser Operator.
With this feature, we can type prompts to command Opera to perform various tasks on our behalf, such as navigating e-commerce websites, searching for products, selecting colors and sizes, adding items to the cart for user review before finalizing the purchase. It can handle complex commands with multiple steps, like ordering tickets to a football match with specific conditions, seat preferences, and more.
Opera states that embedding the Agentic AI feature directly into the browser address security concerns, as there is no need to extract data from the browser. The Operator is designed to require human decision-making at crucial points, such as filling out forms or making payments.
Opera’s approach does not rely on screen captures like other Agentic AI systems but reads the DOM Tree of the browser instead, interpreting web page content without visual cues. This allows the Browser Operator to work faster than image-based reading and eliminates the need to scroll through each part of the page, as it reads the entire DOM Tree at once.
The Browser Operator feature is currently in preview status and is set to open for testing soon.
TLDR: Opera evolves into Agentic AI trend with Browser Operator feature for commanding web tasks and enhancing security by reading web content directly.
Leave a Comment