The AI agent is trained to interact with graphical user interfaces (GUIs) — the buttons, menus, and text fields people see on a screen — just as humans do. This gives it the flexibility to perform digital tasks without using OS- or web-specific APIs.

OpenAI says: "AI agent builds off of years of foundational research at the intersection of multimodal understanding and reasoning. By combining advanced GUI perception with structured problem-solving, it can break tasks into multi-step plans and adaptively self-correct when challenges arise. This capability marks the next step in AI development, allowing models to use the same tools humans rely on daily and opening the door to a vast range of new applications."

Sam Altman-led OpenAI says that while CUA is still early and has limitations, it sets new state-of-the-art benchmark results, achieving a 38.1% success rate on OSWorld for full computer use tasks, and 58.1% on WebArena and 87% on WebVoyager for web-based tasks. "These results highlight CUA’s ability to navigate and operate across diverse environments using a single general action space."

The world's most advanced AI company says the AI agent has been developed with safety as a top priority to address the challenges posed by an agent having access to the digital world. "We are releasing CUA through a research preview of Operator at operator.chatgpt.com⁠ for Pro⁠ Tier users in the U.S. to start. By gathering real-world feedback, we can refine safety measures and continuously improve as we prepare for a future with increasing use of digital agents."

How does AI agent works & its implications

OpenAI's agent or CUA processes raw pixel data to understand what’s happening on the screen and uses a virtual mouse and keyboard to complete actions. It can navigate multi-step tasks, handle errors, and adapt to unexpected changes. This enables CUA to act in a wide range of digital environments, performing tasks like filling out forms and navigating websites without needing specialised APIs.

Given a user’s instruction, the agent operates through an "iterative loop" that integrates perception, reasoning, and action. The AI agent establishes a new state-of-the-art in both computer use and browser use benchmarks by using the same universal interface of screen, mouse, and keyboard, says the company.

Reacting to the development, former OpenAI founding team member Andrej Karpathy says projects like OpenAI’s Operator are to the digital world as humanoid robots are to the physical world. "One general setting (monitor keyboard and mouse, or human body) that can in principle gradually perform arbitrarily general tasks, via an I/O interface originally designed for humans. In both cases, it leads to a gradually mixed autonomy world, where humans become high-level supervisors of low-level automation. A bit like a driver monitoring the Autopilot. This will happen faster in digital world than in physical world because flipping bits is somewhere around 1000X less expensive than moving atoms. Though the market size and opportunity feels a lot bigger in physical world."

AI Agent

What's OpenAI's 'Operator'? An AI agent that performs web tasks for users