OpenAI has introduced Operator, an autonomous AI agent that directly interacts with the web, performing tasks and managing digital workflows. Now available as a research preview for ChatGPT Pro users in the US, Operator can browse the internet, click buttons, complete forms, and make purchases.
Key Features of Operator
The operator uses the new computer using agent (CUA) model, which combines GPT for Oz’s ability to process visual information with advanced reasoning taught through practice and feedback.
- The operator interacts with any site by viewing pages as screenshots and performing basic actions, eliminating the need for additional API.
- An operator automates tasks such as booking travel or ordering groceries online.
- For secure actions, the operator lets users handle sensitive steps for safety.
- Users can run several tasks in separate conversation threads.
- If an issue arises, the operator diagnoses and resolves it to complete the workflow.
Expansion Beyond Chat
Operator, together with features such as deep research and model context protocol (MCP), supports AgentTech AI by enabling Skywind’s solution to execute end-to-end actions. The model context protocol (MCP) is a system that extends the AI agent’s ability to manage and use contextual information during complex tasks. Deep research refers to an AI’s ability to automatically gather and summarize relevant information from multiple online sources.
- Workflow automation: Operator manages long-running, multi-step tasks, including gathering information, synthesizing it, and executing final actions.
Access And Availability
- Current Status: Operator is available as a research preview for ChatGPT Pro users in the US at operator.chatgpt.com
- Future Rollout: OpenAI plans to expand these capabilities to the Plus team and enterprise users.
- Limitations: although a capable operator is in early development and may meet challenges on complex interfaces or non-standard websites
An operator represents an important step toward developing AI agents that serve as personal digital assistants, saving time by automating routine web tasks.
OpenAI CEO Sam Altman predicts 2025 will be pivotal for AI agents, which automate tasks for users.
OpenAI is now taking its first substantial step in this area.
On Thursday, OpenAI launched a research preview of Operator, a general-purpose AI agent that controls a web browser and performs actions independently. US users on ChatGPT’s $200 Pro plan will first access Operator, with future expansion to Plus, Team, and Enterprise users.
“[Operator] will be in other countries soon,” OpenAI CEO Sam Altman said during a livestream on Thursday. Europe will, unfortunately, take a while.
The initial research preview is live at operator.chatgpt.com. OpenAI plans to integrate the operator into all ChatGPT clients soon.
According to OpenAI, operators can automate tasks such as booking, travel, making restaurant reservations, and shopping online. Users can select from categories such as shopping, delivery, dining, and travel, each with its own set of automation options. When users activate Operator, a window appears that displays a dedicated web browser the agent uses to complete tasks and provide explanations of its actions. Users maintain control of their screen while the Operator works in their own browser.
OpenAI states that the operator uses a computer using an agent model or CUA, which combines the vision capabilities of the GPT-4.0 model with advanced reasoning. The CUA interacts with website front ends. So it does not need developer-facing APIs to access services.
The CUA clicks buttons, navigates menus, and fills out forms on web pages like a human user.
OpenAI collaborates with companies such as DoorDash, eBay, Instacart, Priceline, StubHub, and Uber to ensure that operators comply with their terms of service.
The CUA model is trained to prompt users for confirmation before finalizing tasks with external side effects, such as submitting an order or sending an email. OpenAI writes in materials provided to TechCrunch that it has already proven useful in a variety of cases, and we aim to extend that dependability across a wide range of tasks.
OpenAI notes that the CUA is not yet reliable across all scenarios.
OpenAI notes in a support document that operators are currently unable to reliably handle many complex or specialized tasks, such as creating detailed slide shows, operating intake, integrating intricate calendar systems, or interacting with highly customized or non-standard web interface surfaces.
To ensure safety, OpenAI requires user supervision for certain tasks, such as banking transactions, even if the CUA and operator could perform them independently. For example, users must enter credit card information themselves. OpenAI states that the operator does not collect or take screenshots of any data.
On particularly sensitive websites, such as email, the operator requires active user supervision. Making sure users can reach, can directly catch, and resolve any potential mistakes. The models might make. OpenAI says in its support materials.
Although these measures limit the usefulness of the operators, they help prevent unauthorized spending. Google has adopted a similar strategy with its Project Marina AI Agent, which likewise avoids entering sensitive information like credit card numbers.
Limitations
Operator has several significant limitations.
The operator is subject to daily, task-independent rate limits, although it can perform multiple tasks simultaneously. OpenAI notes that dynamic limits are in place. Overall usage limits reset daily.
Currently, the operator restricts tasks such as sending emails or deleting calendar events for security reasons, even though the CUA is technically capable of performing these actions. OpenAI intends to expand these capabilities, but no timeline has been provided.
An operator may become unresponsive when facing complex interfaces, password fees, or capture checks. In such situations, it prompts the user to take over according to the open air
An Agentic Future
OpenAI has taken a more guarded approach to developing an AI agent than competitors such as Rabbit, Google, and Anthropic, likely due to concerns about the safety risks associated with the technology.
Allowing AI systems to take actions on the web introduces risks, such as bad actors who could automate phishing scams, DDoS attacks, or perhaps purchase tickets before others. Given ChatGPT’s widespread use, it is essential for OpenAI to implement safeguards against such exploits.
OpenAI considers the operator sufficiently safe for release in its current form as a research preview.
The operator employs tools that seek to limit the models’ susceptibility to malicious prompts, concealed instructions, and fishing efforts. OpenAI explains on its website that a monitoring system pauses execution if suspicious activity is detected, with automated and human review. Good pipelines. Continuously update safeguards.
As part of its broader effort, Operator is OpenAI’s most ambitious attempt at an AI agent.
Operator introduces features that make ChatGPT more practical similar to Siri or Alexa but demonstrates greater capabilities than previous assistants.
AI agents are positioned at the next major step in AI with the potential to transform how people use the internet and their computers, rather than only delivering and processing information; agents can, in theory, take actions and complete tasks.
With the release of OpenAI’s first practical agent, the feasibility of this vision will soon become evident
Source: OpenAI launches Operator, an AI agent that performs tasks autonomously
