Introducing Operator
📰 OpenAI News
OpenAI introduces Operator, an AI agent that can perform tasks on the web using its own browser
Action Steps
- Explore Operator's capabilities and limitations
- Try Operator as a Pro user in the U.S.
- Provide feedback to refine and improve Operator
- Integrate Operator into workflows and applications
Who Needs to Know This
Product managers and software engineers can leverage Operator to automate repetitive browser tasks, while data scientists and AI researchers can explore its capabilities and limitations
Key Insight
💡 Operator's ability to interact with web interfaces broadens the utility of AI, saving time on everyday tasks and opening up new engagement opportunities for businesses
Share This
🚀 Introducing Operator: an AI agent that can perform tasks on the web using its own browser! 🤖
Key Takeaways
OpenAI introduces Operator, an AI agent that can perform tasks on the web using its own browser
Full Article
# Introducing Operator | OpenAI
[Skip to main content](https://openai.com/index/introducing-operator#main)
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
OpenAI
Table of contents
* [How Operator works](https://openai.com/index/introducing-operator#how-operator-works)
* [How to use](https://openai.com/index/introducing-operator#how-to-use)
* [Ecosystem & users](https://openai.com/index/introducing-operator#ecosystem-and-users)
* [Safety and privacy](https://openai.com/index/introducing-operator#safety-and-privacy)
* [Limitations](https://openai.com/index/introducing-operator#limitations)
* [What's next](https://openai.com/index/introducing-operator#whats-next)
January 23, 2025
[Product](https://openai.com/news/product-releases/)
# Introducing Operator
A research preview of an agent that can use its own browser to perform tasks for you. Available to Pro users in the U.S.
[Go to Operator(opens in a new window)](https://operator.chatgpt.com/)
Loading…
Share
_**July 17, 2025 update**_ _: Operator is now fully integrated into ChatGPT as ChatGPT agent. To access these updated capabilities, simply select “agent mode” from the dropdown in the composer and enter your query directly within ChatGPT. As a result, the standalone Operator site (operator.chatgpt.com) will sunset on in the coming weeks._
* * *
Today we’re releasing [Operator(opens in a new window)](https://operator.chatgpt.com/), an agent that can go to the web to perform tasks for you. Using its own browser, it can look at a webpage and interact with it by typing, clicking, and scrolling. **It is currently a research preview**, meaning it has limitations and will evolve based on user feedback. Operator is one of our first agents, which are AIs capable of doing work for you independently—you give it a task and it will execute it.
Operator can be asked to handle a wide variety of repetitive browser tasks such as filling out forms, ordering groceries, and even creating memes. The ability to use the same interfaces and tools that humans interact with on a daily basis broadens the utility of AI, helping people save time on everyday tasks while opening up new engagement opportunities for businesses.
To ensure a safe and iterative rollout, we are starting small. Starting today, Operator is available to [Pro](https://openai.com/chatgpt/pricing/) users in the U.S. at [operator.chatgpt.com(opens in a new window)](https://operator.chatgpt.com/). This research preview allows us to learn from our users and the broader ecosystem, refining and improving as we go. Our plan is to expand to Plus, Team, and Enterprise users and integrate these capabilities into ChatGPT in the future.
## How Operator works
Operator is powered by a new model called [Computer-Using Agent (CUA)](https://openai.com/index/computer-using-agent/). Combining GPT‑4o's vision capabilities with advanced reasoning through reinforcement learning, CUA is trained to interact with graphical user interfaces (GUIs)—the buttons, menus, and text fields people see on a screen.
Operator can “see” (through screenshots) and “interact” (using all the actions a mouse and keyboard allow) with a browser, enabling it to take action on the web without requiring custom API integrations.
If it encounters challenge
[Skip to main content](https://openai.com/index/introducing-operator#main)
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
OpenAI
Table of contents
* [How Operator works](https://openai.com/index/introducing-operator#how-operator-works)
* [How to use](https://openai.com/index/introducing-operator#how-to-use)
* [Ecosystem & users](https://openai.com/index/introducing-operator#ecosystem-and-users)
* [Safety and privacy](https://openai.com/index/introducing-operator#safety-and-privacy)
* [Limitations](https://openai.com/index/introducing-operator#limitations)
* [What's next](https://openai.com/index/introducing-operator#whats-next)
January 23, 2025
[Product](https://openai.com/news/product-releases/)
# Introducing Operator
A research preview of an agent that can use its own browser to perform tasks for you. Available to Pro users in the U.S.
[Go to Operator(opens in a new window)](https://operator.chatgpt.com/)
Loading…
Share
_**July 17, 2025 update**_ _: Operator is now fully integrated into ChatGPT as ChatGPT agent. To access these updated capabilities, simply select “agent mode” from the dropdown in the composer and enter your query directly within ChatGPT. As a result, the standalone Operator site (operator.chatgpt.com) will sunset on in the coming weeks._
* * *
Today we’re releasing [Operator(opens in a new window)](https://operator.chatgpt.com/), an agent that can go to the web to perform tasks for you. Using its own browser, it can look at a webpage and interact with it by typing, clicking, and scrolling. **It is currently a research preview**, meaning it has limitations and will evolve based on user feedback. Operator is one of our first agents, which are AIs capable of doing work for you independently—you give it a task and it will execute it.
Operator can be asked to handle a wide variety of repetitive browser tasks such as filling out forms, ordering groceries, and even creating memes. The ability to use the same interfaces and tools that humans interact with on a daily basis broadens the utility of AI, helping people save time on everyday tasks while opening up new engagement opportunities for businesses.
To ensure a safe and iterative rollout, we are starting small. Starting today, Operator is available to [Pro](https://openai.com/chatgpt/pricing/) users in the U.S. at [operator.chatgpt.com(opens in a new window)](https://operator.chatgpt.com/). This research preview allows us to learn from our users and the broader ecosystem, refining and improving as we go. Our plan is to expand to Plus, Team, and Enterprise users and integrate these capabilities into ChatGPT in the future.
## How Operator works
Operator is powered by a new model called [Computer-Using Agent (CUA)](https://openai.com/index/computer-using-agent/). Combining GPT‑4o's vision capabilities with advanced reasoning through reinforcement learning, CUA is trained to interact with graphical user interfaces (GUIs)—the buttons, menus, and text fields people see on a screen.
Operator can “see” (through screenshots) and “interact” (using all the actions a mouse and keyboard allow) with a browser, enabling it to take action on the web without requiring custom API integrations.
If it encounters challenge
DeepCamp AI