OpenAI has unveiled the new ChatGPT Agent feature — a virtual assistant that can handle your computer tasks and execute complex operations. This feature is currently available to ChatGPT Pro, Plus, and Team users, with a rollout for corporate accounts expected by the end of summer.
Unlike traditional chatbots, the Agent can manage calendars, create presentations, analyze documents, make online purchases, plan meetings, and perform everyday tasks like restaurant reservations. It operates within a virtual environment with access to a browser, terminal, file system, and other tools, allowing it to autonomously process requests.
The function is built on a new model capable of interacting with multiple tools simultaneously. The development team combined efforts from the Deep Research and Operator projects, but unlike the latter, the Agent performs actions independently in a virtual environment without needing human intervention.
ChatGPT Agent can:
- Analyze calendars and schedule events;
- Create documents, spreadsheets, and presentations;
- Work with user files;
- Conduct searches and bookings via third-party services;
- Generate reports and process web data.
Before executing irreversible actions, such as sending emails or placing orders, the tool requires confirmation. Some features, including transactions, are temporarily restricted, and certain websites open in Watch Mode.
The feature is currently unavailable in the European Economic Area and Switzerland. OpenAI has not announced specific launch timelines for these regions.
This new tool emerges amid increasing competition in the AI agent space. Companies like Google, Meta, Amazon, Anthropic, and startups like Klarna are already implementing similar solutions. According to OpenAI, the ChatGPT Agent represents a step towards an AI model that not only advises but also performs actual tasks.
