ChatGPT Dots Verified
Key insights
Concrete technical or product signals.
- Pro 100, Pro 200, and Pro 500 can use dots if the user is over 18 and outside the European Economic Area, the United Kingdom, and Switzerland. Business Premium is rolling out worldwide. Enterprise is rolling out worldwide and stays off until a workspace admin enables it.
- A local computer connection is optional, limited to one personal computer, and works only while that computer is online with the ChatGPT app open. It is separate from connecting a computer to Codex or enabling Work Sync.
- Plugins such as Gmail, Google Drive, and GitHub must be connected on their own. A messaging channel does not grant inbox, app, or computer access. The cloud browser session is separate from the browser on your computer.
Use cases
Where this shines in production.
- Ongoing responsibilities that continue between conversations
- Research and document updates with approval before sending
- Coding follow-ups that hand work to Codex or a Codex cloud environment
Limitations & trade-offs
What to watch for.
- Rollout is gradual. An eligible plan may not show dots yet.
- Create the dot on desktop first. The mobile app works after setup when its update is available. Mobile web is not supported.
- Instructions and custom rules do not override built-in safety checks. Actions that affect accounts or share information can require approval or a handoff back to you.
- OpenAI's dots guide does not document a public API for creating or running dots.
Models referenced
Declared model dependencies or integrations.
GPT-6 Astra
Related prompts
Hand-picked or latest prompt templates.
Prompt
Prompt-injection resistant assistant
System prompt that treats retrieved docs, tickets, and web pages as untrusted data. Use in multi-tenant RAG and browsing agents. This is a defensive template, not an attack or bypass playbook.
Prompt
Computer-use agent with approval gates
System prompt for browser/desktop agents (Grok Bot, computer-use tools). Allows research and drafts, but pauses before send, purchase, delete, or production changes. Not a jailbreak or bypass guide.
Prompt
Transcript to summary and action items
Turn a speech transcript into decisions, owners, and follow-ups. Use after Gemini 3.5 Transcribe, Whisper, or MAI-Transcribe. Do not use on raw audio; transcribe first.
Prompt
Product image generation prompt
A reusable image prompt for catalog and hero shots: subject, lighting, lens, negative constraints, and text-in-image rules. Works with Firefly, Midjourney, MAI-Image, Qwen-Image, and SDXL. Not for photorealistic people or brand-logo cloning.
Prompt
LLM output evaluation rubric
Judge a model answer against a task, retrieved evidence, and pass/fail thresholds. Use for golden-set grading and regression evals. Not a substitute for human review on high-risk decisions.
Prompt
Strict JSON extraction prompt
Extract structured fields into JSON that matches a schema. Pair with provider structured-output / JSON-schema modes when available. Do not use when the output is meant to be prose.
Looking for a tighter match? Search the prompt library.
ChatGPT Dots FAQ
What is ChatGPT Dots?
Dots are ChatGPT's always-on agents, powered by GPT-6 Astra. A dot lives in the cloud with its own computer and browser, keeps working while your devices are off, and reaches out when a result or decision needs you. It can research, analyze data, prepare documents, and build software, using relevant context from past conversations and your preferences. You create it in the ChatGPT desktop app or a desktop browser, then message or call the same dot in ChatGPT, Slack, or Microsoft Teams. Mobile web is not supported.
When should teams use ChatGPT Dots?
Ongoing responsibilities that continue between conversations
What should teams watch out for with ChatGPT Dots?
Rollout is gradual. An eligible plan may not show dots yet.
Related
Comparisons, platforms, and models teams often view next.