OpenAI
Dots
Persistent agents inside ChatGPT, each with its own cloud computer and browser. They keep working after you close the tab, and you can watch the screen while they do.
Announced at DevDay on 29 September 2026, dots are OpenAI's answer to the problem that a chat session ends. Each dot runs on GPT-6 Astra and is given a cloud computer and browser of its own, kept separate from yours unless you connect them. It can hold several projects at once, reach more than 4,000 apps through plugins, send progress updates and ask questions mid-task. You reach it in ChatGPT on desktop, web and mobile, or message it in Slack and Teams. The watchable screen matters more than it sounds: you can look at what the agent is doing rather than waiting for a verdict.
Best for
Long-running work you want to hand over and check on, rather than supervise turn by turn.
Watch out
The machine is OpenAI's, not yours, so the sandbox is their design and not something you can inspect or harden. Rollout is uneven: Pro and Business Premium in eligible markets, with Pro excluded in the EEA, Switzerland and the UK at launch, and Enterprise, Edu and Healthcare behind an admin-enabled beta. OpenAI's own line is that dots can still make mistakes and consequential work should be reviewed.