Back to services

OpenAI Dots

Dots is OpenAI's always-on AI agent, powered by GPT‑6 Astra. It has its own cloud computer and works proactively around the clock on complex projects and everyday tasks. You can collaborate with it through ChatGPT, Slack and Teams, and you stay in control of its permissions and actions.

View alternatives to OpenAI Dots
Contributor:
einverne
Suggest edit
Recent reviews

Alternatives

Website preview

Tech stack

No tech stack added yet. Sign in to suggest some

Dots is an always-on AI agent that OpenAI released on September 29, 2026. OpenAI says it learns what matters to you, keeps working on your behalf, and takes important tasks off your plate. It is powered by GPT‑6 Astra, has its own cloud computer and browser, keeps learning from your feedback, and can work toward your goals 24/7.

Key features

  • Autonomous work: Dots completes tasks using its own cloud computer, its browser and the apps you have connected. You can open its computer at any time to watch how it works. With your permission, it can also connect to and use your laptop.
  • Parallel projects: It can move several projects forward at once. You don't have to manage multiple conversation threads or direct every step.
  • Continuous learning of your preferences: It gradually learns your goals, how you think and what "done well" means to you, and delivers results the way you like them, sometimes before you even ask.
  • App connections: Its plugin ecosystem connects to more than 4,000 apps.
  • Multi-channel collaboration: You can message it or call it by voice in ChatGPT on desktop, web and mobile, and you can also reach it in Slack and Teams. Text messaging (SMS) is marked as "coming soon". Context is shared across all channels.
  • Proactive research: When you're not around, Dots uses read-only tools in your connected apps to look for ways to help in the background. It cannot send messages, change content in your apps, or control your browser or computer.
  • Specialist Dots (preview): Aimed at organizations, each specialist Dots has its own identity, credentials and system access, and takes on a clearly defined role. Early testing areas mentioned by OpenAI include procurement, invoice processing, email marketing, customer support and business contracts. It is currently rolling out as a focused enterprise pilot, and OpenAI is working with Microsoft to bring it into the governance and security controls of Agent 365.

Target users and use cases

Examples given on the official website include:

  • Developers: Dots monitors customer feedback, proposes small improvements and bug fixes, completes the build and tests, then delivers a complete PR with a demo video for review.
  • Product launch leads: When the product scope changes, Dots revises launch materials and drafts changes to assets and documentation.
  • Researchers: When new data arrives, Dots reruns the analysis, investigates anomalous results and updates the figures in the paper.
  • Sales leads: Dots reviews customer needs and account history, builds a proof of concept for a key integration, and updates the proposal and test plan.
  • Content creators: Dots finds clip-worthy segments in interview transcripts, prepares show notes, and drafts social posts for you to confirm.

Security and control

  • Each Dots runs on its own cloud computer, and your own computer and its contents are isolated from it by default unless you choose to connect it.
  • When signing in to supported websites, Dots can use saved passwords, and those passwords are never exposed to the model.
  • You can manage which apps Dots can access, and its permissions, through ChatGPT's existing app controls.
  • Dots has built-in rules for when to act on its own and when to ask for approval. With custom rules, you can allow, require approval for, or block specific actions, and you can follow its progress, including background work, in the "Activity view".
  • Actions that could affect your accounts or share information externally go through automated review. Sensitive tasks such as changing passwords are always done by you.
  • If safety monitoring detects a problem, Dots' work can be paused or stopped.
  • Content from ChatGPT Business, Enterprise and Edu workspaces is not used to improve models by default. Individual users can control whether their conversations and work with Dots are used to improve models.
  • OpenAI also cautions that Dots can still make mistakes, and important work should be reviewed by a person.

Availability and pricing

  • It is currently rolling out to Pro and Business Premium users in "eligible regions". Enterprise users (including Edu and Healthcare) can try it after a workspace admin enables the beta.
  • Your first Dots is included in the Pro or Business Premium plan at no extra charge. The plan includes a deep-work allowance, which is higher during the first month after launch.
  • Conversations with Dots do not count toward your ChatGPT usage limits. However, tasks that Dots starts or manages in Codex or ChatGPT Work still count toward limits as usual.
  • OpenAI says that in the future you will be able to add more Dots and increase each Dots' output by raising its speed or its total monthly workload.
  • Getting started: Create your first Dots in the ChatGPT desktop app or a desktop browser, connect your apps, and let it introduce itself. After initial setup, you can message it in the ChatGPT mobile app.

Things to note

  • Dots is a closed-source commercial cloud service from OpenAI, with no self-hosted deployment option.
  • Availability is limited by plan and region, and some features (such as SMS, multi-Dots collaboration and specialist Dots) are still announced-only or in the pilot stage.