Investing.com -- A new artificial intelligence (AI) tool named Operator has been unveiled by OpenAI today, designed to independently carry out tasks on the web. This tool uses its own browser to interact with webpages through typing, clicking, and scrolling. As a research preview, Operator has some limitations but will evolve based on user feedback.
Operator can manage a variety of repetitive browser tasks, including filling out forms, ordering groceries, and creating memes. This tool expands the functionality of AI by using the same interfaces and tools that humans interact with daily, saving people time on routine tasks and providing new opportunities for businesses.
For a safe and iterative rollout, the launch of Operator is initially available to Pro users in the U.S. at operator.chatgpt.com. This early release will help gather feedback from users and the broader ecosystem, enabling improvements over time. The plan is to eventually extend access to Plus, Team, and Enterprise users and integrate these capabilities into ChatGPT in the future.
Operator is powered by a new model named Computer-Using Agent (CUA), which combines GPT-4o's vision capabilities with advanced reasoning through reinforcement learning. CUA is designed to interact with graphical user interfaces (GUIs) like buttons, menus, and text fields. Operator can see and interact with a browser, allowing it to take action on the web without requiring custom API integrations.
In case of challenges or mistakes, Operator can use its reasoning capabilities to self-correct. If it encounters a task it cannot complete, it hands control back to the user, ensuring a smooth and collaborative experience.
Despite being in its early stages, CUA has achieved new benchmark results in WebArena and WebVoyager, two key browser use benchmarks.
To use Operator, users simply need to describe the task they would like done. Users can take over control of the remote browser at any point, and Operator is designed to ask the user to take over for tasks that require login, payment details, or when solving CAPTCHAs.
Users can personalize their workflows in Operator by adding custom instructions for all sites or specific ones. Operator also allows users to save prompts for quick access on the homepage, ideal for repeated tasks. Users can have Operator run multiple tasks simultaneously by creating new conversations.
Operator transforms AI from a passive tool to an active participant in the digital ecosystem. It aims to streamline tasks for users and offer benefits to companies that seek innovative customer experiences and higher conversion rates. Collaborations with companies like DoorDash (NASDAQ:DASH), Instacart (NASDAQ:CART), OpenTable, Priceline, StubHub, Thumbtack, Uber (NYSE:UBER), and others are underway to ensure Operator addresses real-world needs while respecting established norms. Efforts are also being made to improve accessibility and efficiency of certain workflows, particularly in public sector applications, by working with organizations like the City of Stockton to simplify enrollment in city services and programs.
This article was generated with the support of AI and reviewed by an editor. For more information see our T&C.