OpenAI Launches New ChatGPT Agent with Virtual Browser Capabilities

A stylized camera shutter or aperture design overlaid on a pixelated background. The design features a black geometric pattern resembling a flower or star shape with six segments arranged around a hexagonal center, set against a vibrant royal blue background. The interior of the aperture design contains a pixelated mosaic pattern in warm flesh tones.

Introduction to the New ChatGPT Agent

OpenAI has introduced a new agent for ChatGPT, which utilises a virtual browser to complete tasks and can generate downloadable files, specifically PowerPoint presentations and Excel spreadsheets. This feature is part of OpenAI’s ongoing efforts to turn its nearly three-year-old chatbot into a money-making product.

The new ChatGPT agent brings together aspects of OpenAI’s web-browsing Operator and its long-processing deep research features. It can switch between interacting with a visual browser, where it can click around like Operator does, and a text-based browser, where it can process loads of websites like deep research does.

Capabilities and Limitations

The agent can fill out online forms, use a programming terminal, and make calls to public APIs. However, it is not a full replacement for the Microsoft suite of workplace tools. The release is part of OpenAI’s ongoing efforts to turn its nearly three-year-old chatbot into a money-making product.

The rollout of the ChatGPT agent is coming first to Pro, Plus, and Team subscribers, starting with Pro users. Enterprise and Education subscribers will likely receive access to the feature later in the summer. At launch, Pro users are generally capped at 400 agent prompts a month, with 40 prompts allowed for the other tiers of paying users.

Future Developments

OpenAI wants to integrate memory with the ChatGPT agent eventually, but it won’t be part of the initial launch. The company is taking an extra precaution due to potential security risks, such as prompt injection attacks.