To carry out tasks on the web, Operator uses a new model called Computer-Using Agent (CUA), which combines GPT-4o's vision skills with more advanced reasoning. That combination lets it interact with the menus, controls, and text fields on a web page without the need for a custom API.

OpenAI announced that it is launching a research preview of Operator, an AI agent that can take control of a browser and perform tasks.

It can also ask follow-up questions to further personalize the tasks it completes, such as login information for other websites. Users can take control of the screen at any time.

ChatGPT maker OpenAI has unveiled a new AI assistant which can carry out tasks on the internet independently once instructed by the user. Called Operator, it is what is known as an AI agent – AI tools which can autonomously carry out a specific task given to them by the user.

OpenAI has announced 'Operator,' an AI agent designed to perform web-based tasks autonomously using its own browser. Currently available as a research preview for Pro users in the United States, the tool aims to automate everyday activities such as filling out forms,