ChatGPT Maker OpenAI Introduces AI Agent Operator
To get started, users can simply describe the task they want to do and Operator can handle the rest.
Sam Altman – the CEO of OpenAI which developed ChatGPT – has introduced a general-purpose artificial intelligence (AI) agent named Operator.
The OpenAI announcement made on January 23, 2025, reveals that Operator uses its own browser to look at a webpage and interact with it by typing, clicking, and scrolling.
However, this AI agent is currently being released as a research preview with some limitations and will be developed further after taking feedback from users. “Operator is one of our first agents, which are AIs capable of doing work for you independently—you give it a task and it will execute it,” OpenAI said in its statement.
The company claims that Operator can be asked to handle a wide variety of repetitive browser tasks such as filling out forms, ordering groceries, and even creating memes.
The ability to use the same interfaces and tools that humans interact with on a daily basis broadens the utility of AI, helping people save time on everyday tasks while opening up new engagement opportunities for businesses.
Operator is now available to Pro users in the U.S. at operator.chatgpt.com while the company plans to expand it to Plus, Team, and Enterprise users and integrate these capabilities into ChatGPT in the future.
Operator—powered by a new model called Computer-Using Agent (CUA)—combines GPT-4o’s vision capabilities with advanced reasoning through reinforcement learning. CUA is trained to interact with graphical user interfaces (GUIs)—the buttons, menus, and text fields people see on a screen.
It can “see” (through screenshots) and “interact” (using all the actions a mouse and keyboard allow) with a browser, enabling it to take action on the web without requiring custom API integrations.
If it encounters challenges or makes mistakes, Operator can leverage its reasoning capabilities to self-correct. When it gets stuck and needs assistance, it simply hands control back to the user, ensuring a smooth and collaborative experience.
While CUA is still in early stages and has limitations, it sets new benchmark results in WebArena and WebVoyager, two key browser use benchmarks.
To get started, users can simply describe the task they want to do and Operator can handle the rest. Users can choose to take over control of the remote browser at any point, and Operator is trained to proactively ask the user to take over for tasks that require login, payment details, or when solving CAPTCHAs.
Moreover, users can personalize their workflows in Operator by adding custom instructions, either for all sites or for specific ones, such as setting preferences for airlines on Booking.com.
According to OpenAI, Operator lets users save prompts for quick access on the homepage, ideal for repeated tasks like restocking groceries on Instacart. Similar to using multiple tabs on a browser, users can have Operator run multiple tasks simultaneously by creating new conversations, like ordering a personalized enamel mug on Etsy while booking a campsite on Hipcamp.
Meanwhile, OpenAI has been selected as part of a team that the U.S. President Donald Trump has formed to lead an ambitious $500-billion AI project called Stargate.
The team that will support Trump in the project includes Sam Altman, founder of ChatGPT-maker OpenAI, Oracle Chairman Larry Ellison, and SoftBank CEO Masayoshi Son.
