OpenAI previews Operator, an agent that controls a browser
Operator uses a visual computer-use model to click, type, and scroll through web tasks, handing control back for logins, payments, and sensitive actions.
What happened
Event details
OpenAI released Operator as a U.S.-only research preview for Pro users. Its Computer-Using Agent interpreted browser screenshots and used mouse and keyboard actions to complete tasks such as booking, shopping, and form entry. Operator could run multiple tasks, but it paused for user takeover or confirmation around credentials, payments, and higher-impact actions. It demonstrated practical interface control before the market converged on broader work agents.
Assessment
Why it matters
Operator established browser control as a product capability, while leaving the larger task of research, coding, files, and finished deliverables to later agents.