The company says the CUA’s reasoning technique, which they call an “inner monologue,” helps the model understand intermediate steps and adapt to unexpected input. Under the hood, CUA takes screenshots of web pages and uses a virtual mouse and keyboard to navigate.

AI agents have the potential to transform industries by automating tasks, personalizing interactions, and improving efficiency.

Going forward, OpenAI plans to expand the availability of Operator beyond ChatGPT Pro to the chatbot’s other tiers. The company will also offer the agent through its application programming interface. Under the hood, OpenAI plans to add enhancements that will make Operator better at completing complex tasks.

OpenAI has launched Operator, its first AI agent capable of executing actions directly from a browser. Powered by the CUA model, it can break tasks into plans and self-correct, while also implementing safeguards against harmful or illegal activities.

Operator is an AI that can interpret visual cues on a screen—such as buttons, menus, and text fields—and use those cues to execute tasks.

So-called "computer use agents" are expected to be a major leap in AI that will allow bots to actually complete tasks on your behalf.