Skip to content
Social Rocket

OpenAI Dots: AI agent works continuously across more than 4.000 apps

OpenAI is launching Dots, AI agents that work continuously inside ChatGPT. They run on their own cloud computers and can be connected to more than 4.000 apps via plugins.

From Social Rocket editorial team

This text was created with AI assistance and reviewed editorially before publication. All sources are linked below.

Digital workspace with multiple screens as a symbol for AI agents
Photo: Liam Charmer / Unsplash

OpenAI has introduced dots, AI agents that work continuously for ChatGPT. According to OpenAI, each dot runs on its own cloud computer, can pursue several projects at once and can be connected to more than 4.000 apps via plugins.

Relevant for marketing teams

OpenAI explicitly names content production as a use case: a dot can, for example, detect new interview transcripts, select clip candidates, prepare show notes and draft social posts for approval.

The agents can be reached via ChatGPT as well as in Slack and Microsoft Teams. According to OpenAI, proactive research running in the background is limited to read-only tools. Further actions are subject to permissions and approvals.

This shifts AI further away from individual prompts and towards ongoing workflows. We explain how such app connections are controlled in our guide to ChatGPT plugins with MCP, OAuth and your own servers.

Meta is pursuing a similar direction with Muse. Read more in our overview of the Meta Enterprise Platform.

Availability

OpenAI is initially rolling out Dots to ChatGPT Pro and Business Premium in eligible markets. According to the company, the first dot is included in these plans; more intensive work is subject to additional usage quotas.

Sources