OpenAI is moving from a commerce system to agentic AI using an operator and its computer with a CUA model. The operator can independently control a computer to complete multi-step tasks, enabling AI to interact with websites and apps on the user’s behalf.
With this new paradigm in mind, consider the following outline of OpenAI’s vision for autonomous computer tasks.
To provide better context, let’s start by focusing on the first key area:
- An operator is an AI agent designed to take control of a user’s web browser and eventually their computer to handle repetitive or complex tasks.
- The operator uses a computer running the agent CUA model, which combines GPT-4’s Visual Reasoning with Reinforcement Learning. Unlike older automation tools that require API interfaces, CUA can view the screen via screenshots and interact with graphical interfaces, as a person does.
- An operator can fill out forms, order groceries, do research, create memes, and schedule appointments.
The Shift to Agentic AI
- Operator denotes a shift from a checkbox that only talks to agents who can take action. It is built to manage long, multi-step tasks with little need for people to step in.
- A new ChatGPT Agent feature lets AI use a virtual computer to check calendars, book restaurants, and make slide decks.
- Once you set a goal, agents work on their own. For example, it could plan a weekend trip.
Present Constraints & Safety
- The operator is still in the research stage and is primarily available to pro users in the US.
- The AI pauses for human approval before any action that can be undone, like sending emails or deleting calendar events.
The agent can sometimes get stuck on streaky interfaces, capture or password fields, so it may need help from a person.
Future Outlook discusses the upcoming directions and possibilities for the Operator platform and agentic AI.
- OpenAI plans to expand the operator to the Plus team and Enterprise users.
- OpenAI positions Customer Agents as a Foundation for Progress Towards Artificial General Intelligence (AGI).
- The aim is to move from a single tool to an ecosystem in which agents work independently across multiple systems seven times.
The move to agentic AI is part of a broader trend in 2025, with companies like Anthropic and Google building similar capabilities.
At the start of this year, OpenAI CEO Sam Altman predicted 2025 would be pivotal for AI agents—tools that automate tasks and act on users’ behalf.
Building on this vision, OpenAI is now making its first real move in this area.
OpenAI has announced a research preview of Operator, an AI agent that controls a web browser and autonomously performs tasks. It will initially be available to US users with ChatGPT’s Pro subscription and will expand to Plus, Team, and Enterprise plans, with dates to be announced.
Operators will be available in other countries soon, though a specific launch date has not been announced. OpenAI CEO Sam Altman said during a live stream on Thursday that Europe will, unfortunately, take a while.
Currently, the research preview is at operator.chatgpt.com. OpenAI plans to add Operator to all ChatGPT clients soon. The operator promises to automate tasks such as booking travel, making reservations, and shopping. The interface offers categories such as shopping, delivery, dining, and travel for different automations.
When users activate Operator in ChatGPT, a dedicated web browser opens, allowing the agent to complete tasks and explain its actions. Users still control their own screen, as Operator operates in its own browser.
OpenAI explains the browser runs on a computer using an agent or CUA model, combining GPT-4o’s vision skills with advanced reasoning. The CUA attempts to interact directly with website interfaces, bypassing developer APIs.
This allows the CUA to click, navigate menus, and fill forms on web pages much like a person.
OpenAI says it’s collaborating with companies like DoorDash, eBay, Instacart, Priceline, StubHub, and Uber to ensure operators comply with their terms of service.
The CUA model is trained to ask for user confirmation before finalizing tasks with external side effects, for example, before submitting an order or sending an email, so that the user can recheck the model’s work before it becomes permanent. Open-air rights in materials provided for death crimes. It has already proven useful in a variety of cases, and we aim to extend that dependability across a wider range of tasks.
But OpenAI warns the CUA isn’t perfect. The company says it doesn’t expect the CUA to perform reliably in all scenarios just yet.
Currently, the operator cannot consistently handle many complex or specialized tasks. OpenAI adds support for tasks such as creating detailed slide shows, overseeing intricate calendar systems, or interacting with highly customized or non-standard web interfaces.
To be extra careful, OpenAI requires users to supervise certain tasks, such as banking transactions, even though the CUA and operator could handle them on their own. For example, users must enter credit card information themselves. OpenAI also says the operator does not color or screenshot any data.
On particularly sensitive websites, such as email, the operator requires active user supervision, guaranteeing users can directly catch and handle any potential mistakes the model might make, OpenAI says in its support materials.
This does limit what an operator can do, but it also helps prevent mistakes like the agent accidentally spending your mortgage payment on edgy accent chairs. Google has taken a similar approach with its Project Marina AI agent, which also avoids entering sensitive information such as credit card numbers.
Limitations
The operator does have some important limitations.
There are both daily and task-based rate limits. OpenAI says an operator can handle seven tasks at once, but there are dynamic limits on how many. There is also an AU total-usage limit that resets each day.
For security reasons, the operator will not perform certain tasks at this stage, such as sending emails or deleting calendar events, even though the CUA can. OpenAI says this may change in the future, but there is no timeline yet.
An operator can also get stuck if it encounters a complex interface, a password field, or a captcha. When this happens, it will prompt the user to take over.
An Agentic Future
Compared with competitors like Rabbit, Google, and Android, OpenAI has taken longer to develop an AI agent. This may be due to the technology’s safety risks.
When an AI system can take actions on the web, it opens the door to much more dangerous use cases from nefarious actors. You could automate AI agents who orchestrate phishing scams or DDoS attacks or have them snatch up tickets to a concert before anyone else can. Especially for a tool as widely used as ChatGPT, it’s important that OpenAI takes steps to prepare for such exploits.
OpenAI believes the operator is safe enough to release now, at least as a result review.
The operator employs tools that seek to limit the model’s susceptibility to malicious prompts, consent instructions, and prompt injection. OpenAI explains on its website that a monitoring system triggers action if suspicious activity is detected, while automated and human-reviewed pipelines continuously update safety balances.
Operator is OpenAI’s most ambitious effort so far to create an AI agent. Lastly, OpenAI launched Tasks, which gave ChatGPT basic automation features such as creating reminders and scheduling prompts to run at specific times each day. Tasks added some familiar but important features to ChatGPT, making it as practical as Siri or Alexa. However, the Operator introduces capabilities that earlier virtual assistants could not offer in AI. After ChatGPT, a new technology that will change how people use the internet and their PCs. Instead of simply delivering and processing information, agents can, in theory, take actions and actually do things.
Now that OpenAI has released its first real AI agent, we will soon see how realistic this vision actually is.
Source: OpenAI launches Operator, an AI agent that performs tasks autonomously
