OpenAI’s new ChatGPT agent reasons, researches, and runs its own computer

OpenAI is rolling out a new AI agent within ChatGPT that can browse the web and conduct deep research.

An AI agent is similar to an AI app that can retain extensive information about a user and an automated workflow, reasoning its way toward task completion. This new ChatGPT agent is a hybrid. OpenAI previously released an agent called Operator, which can browse the web and access tools. Another agent, Deep Research, can search the web and reason through information to produce a comprehensive report on a topic.

The new agent combines the strengths of both tools, along with ChatGPT’s built-in intelligence and conversational fluency.

OpenAI said in a press release on Thursday that the ChatGPT agent carries out tasks using its own virtual computer, “fluidly shifting between reasoning and action to handle complex workflows from start to finish.”

For example, OpenAI says the agent can analyze a user’s calendar to generate a briefing on upcoming client meetings, or plan and purchase ingredients for a dinner party. A business might ask the agent to create a slide deck based on in-depth research about a group of competing companies.

The model behind these agents is designed to contemplate new directions after starting a task. Users can approve tasks the agent wants to carry out, redirect them if they go off track, or adjust the original goal’s details.

The ChatGPT agent can run code and prompt the user to log in to websites when necessary. It might also use application programming interfaces (APIs) to access data sources, such as files stored in Google Drive.

Importantly, the agent requests permission before performing consequential actions like sending emails, submitting forms, making purchases, or handling personal information. The user can take control of the browser or stop the agent’s tasks at any time.

And the agent won’t do just anything. OpenAI says the agent rejects harmful or illegal requests. It won’t handle high-risk tasks such as financial transactions or legal advice.

The new hybrid agent launches today for ChatGPT Pro, Plus, and Team subscribers. Users can enable it by selecting “agent mode” from the tools drop-down menu within ChatGPT.