OpenAI Group PBC today used its DevDay developer conference to launch Dots, a set of always-on artificial intelligence agents in ChatGPT.
The release is aimed at moving ChatGPT users beyond working one prompt at a time. Someone can hand an agent a goal and let it carry the job forward without direction at every step, even while it has several other projects going. Each agent learns its owner’s preferences from feedback. OpenAI says some of the work will show up before anyone asks for it.
GPT-6 Astra powers the agents, and each one works from a cloud computer of its own that users can open at any time to see what it is doing. More than 4,000 apps are reachable through OpenAI’s plugins. With permission, an agent can also work directly on its owner’s laptop.
Users can message or call their agent in ChatGPT on desktop, web or mobile, or reach it in Slack and Teams. Because context follows the agent between channels, a project started in ChatGPT can be passed to a team in Slack without a fresh briefing. Agents send progress updates and questions back to their owners.
OpenAI has been using the agents on its own teams. When a bug gets reported in the company’s Slack, the agents start investigating right away, and new designs are turned into working apps while staff concentrate on customer feedback.
One early tester outside the company had forgotten to bill a publication. When his agent noticed, it prepared the invoice and waited for his approval before sending it.
When nobody has handed it a task, an agent goes looking for ways to help, which OpenAI calls proactive research. Its connections to the owner’s apps are read-only during that time, so it cannot send messages or change anything.
Actions that could touch a user’s accounts or share information must first clear a check called auto-review, and a monitoring system can pause or stop an agent over a safety concern. OpenAI tells users to review consequential work because the agents “can still make mistakes.”
OpenAI also previewed specialist agents that an employer provisions with their own identity and credentials for a single defined job. Procurement and invoice processing were among the jobs tested inside OpenAI. Customers start with focused pilots, in which OpenAI engineers help define what each agent is responsible for. Microsoft Corp. is working with OpenAI so specialist agents can be managed through the governance and security controls in Agent 365.
The new service also puts OpenAI up against Meta Platforms Inc., which released its Muse personal agent in the U.S. on Sept. 8. Like OpenAI’s agents, Muse runs on a dedicated computer in the cloud. Most of what people use it for is free, Meta said, with subscriptions sold to heavier users.
Dots began rolling out today to ChatGPT Pro and Business Premium subscribers, and some accounts may wait several days for access. Pro subscribers in the European Economic Area, Switzerland and the U.K. are not included. Enterprise customers, including those on Edu and Healthcare plans, can try a beta once a workspace administrator switches it on.
One agent comes with a Pro or Business Premium plan at no extra cost. OpenAI’s help documentation says agent usage will not count against plan allowances for the first month. Terms for each plan come after that. Additional agents, and more speed or monthly capacity for existing ones, are planned for later at prices OpenAI has not disclosed.