OpenAI has launched “ChatGPT Dots,” a new suite of AI agents designed to assist with tasks without requiring step-by-step manual intervention. You can issue an initial instruction to a Dot and let it proceed with the task—even if you navigate away from the ChatGPT platform. These agents can work with connected applications in the background and prompt you only when your input or approval is required. OpenAI states that Dots are capable of handling a wide range of activities, from coding and research to sales, content creation, and routine daily tasks.
ChatGPT Dots Features
According to OpenAI, Dots run on the GPT-6 Astra platform, with each agent equipped with its own dedicated cloud-based computing environment and browser. They can connect to over 4,000 applications via OpenAI’s plugin ecosystem, granting them access to the services needed to complete specific tasks. Once a user sets a goal, the agent can autonomously execute the subsequent steps and handle multiple tasks simultaneously.
OpenAI’s examples include tracking recurring customer feedback, testing small code fixes, updating release materials, analyzing new research data, and revising sales proposals based on changing needs. Dot can also transform interview recordings into video clips, show notes, and social media posts, or handle everyday tasks—such as comparing food delivery options and calculating the final bill before placing an order.
After a user leaves ChatGPT, Dot can continue running in the background, returning when necessary to provide updates or seek user input. Users can interact with the agent via ChatGPT, Slack, and Microsoft Teams; voice calling is currently supported, with SMS functionality coming later.
Cloud-based computing ensures the agent remains isolated from the user’s own computer unless the user chooses to connect them. When a task requires it, Dots can utilize other devices, allowing users to monitor the agent’s operations. On supported websites, users can utilize saved passwords without exposing their credentials to the model.
Users determine Dot’s access permissions by connecting specific applications and selecting which actions Dot can handle autonomously versus those requiring user approval. Background research remains in a read-only state, preventing the agent from sending messages or modifying connected applications while working. OpenAI’s automated moderation systems monitor actions involving account or information sharing, while sensitive tasks—such as changing passwords—still require user intervention.
OpenAI says its safety systems can pause or stop a Dot if they detect malicious instructions or potentially harmful behavior. The company also notes that Dots can make mistakes, so users should check their work before relying on it for anything important. Personal ChatGPT users can choose whether their Dot conversations and work are used to improve OpenAI’s models, while Business, Enterprise and Edu content is excluded from training by default.
OpenAI is also testing Dots built for organizations, which can have their own identities and access selected company systems. Early uses include procurement, invoice processing, email marketing, customer support and commercial contracts. OpenAI is working with Microsoft to bring these agents to Agent 365.
ChatGPT Dots Availability
ChatGPT Dots are rolling out to Pro, Business Premium and Enterprise users in eligible markets. Enterprise users can access the beta when their workspace administrator enables it. OpenAI says the first Dot comes with Pro and Business Premium at no additional cost, with an allowance for deeper work and extended limits during the first month.
Conversations with a Dot do not count towards ChatGPT usage limits, although tasks that the agent starts or manages through Codex or ChatGPT Work count towards those services’ limits. OpenAI says Dots are now available across ChatGPT on web, mobile and desktop, although the initial setup currently starts through the desktop app or desktop browser. More Dots and larger workloads are planned for the future.