Advertisment

OpenAI launches Operator AI to automate online tasks

OpenAI's new AI agent, Operator, uses the Computer-Using Agent (CUA) model to navigate websites, click buttons, and fill out forms without needing developer APIs.

author-image
Social Samosa
New Update
dv

OpenAI has rolled out Operator, a general-purpose AI agent capable of controlling web browsers to automate tasks like booking travel, making restaurant reservations, and shopping online. Currently available as a research preview for U.S. users on the $200 ChatGPT Pro plan, the feature will soon expand to other subscription tiers and international users. Powered by OpenAI’s GPT-4o model and trained to interact with websites like a human, Operator promises to streamline tasks through a dedicated browser window while respecting business terms.

d
Operator’s home screen. Image Credits:OpenAI

 

The new AI agent utilises a Computer-Using Agent (CUA) model, combining vision capabilities and reasoning abilities from OpenAI’s advanced models. This allows Operator to navigate websites, click buttons, fill out forms, and interact with front-end elements without relying on developer-facing APIs. The user interface offers a transparent view of actions being performed, with users still able to control their screens during operation.

OpenAI’s collaboration with major companies like DoorDash, eBay, Instacart, Priceline, StubHub, and Uber ensures that Operator complies with the terms of service for these platforms. As OpenAI continues to refine Operator, it aims to make this functionality available to a wider range of users and further enhance the AI’s ability to perform real-world tasks.

Open AI Open AI Operator Task automation