Short answer
- Enterprise users, including Edu and Healthcare, can try the dots beta when their workspace admin enables it. It is off by default. Business Premium has dots across all supported ChatGPT regions.
- OpenAI's admin guide puts the switch in Workspace settings > Permissions & roles: Use dots (Beta), plus separate permissions for Slack, local computer access and custom rules.
- Existing Enterprise model controls don't apply to dots. OpenAI's two admin pages disagree on Teams: one lists it beside Slack, the other calls it an invite-only alpha. Usage terms after the launch month aren't published yet.
OpenAI’s admin guide, Manage dots permissions and capabilities (in its learn docs), covers most of what admins need: the toggle, policy controls and audit records. Below: that guide, what the help center and privacy FAQ add, and our own pilot checklist.
Who can get dots
- Age: users must be 18 or older.
- No texting: the texting beta is limited to Pro users in the US, so it isn’t available in Business or Enterprise workspaces.
- Excluded workspaces: OpenAI says dots are unavailable for FedRAMP workspaces, workspaces with EKM, and workspaces with inference residency set to the UAE. HIPAA workspaces can take part if they meet the other requirements.
Turn dots on: Permissions & roles
OpenAI documents this in two places: a help center article, Manage dots in ChatGPT workspaces, and an admin guide in its learn docs. Both put it under Workspace settings > Permissions & roles, using workspace defaults or custom roles assigned to groups. There are four dots permissions:
| Permission | What it allows | Default for Enterprise |
|---|---|---|
| Use dots (Beta) | Members can use dots | Off |
| Add dots to Slack and Microsoft Teams (learn docs: Add dots to Slack) | A dot can join supported Slack or Teams workspaces and post with its own identity, where available | Not stated |
| Allow local computer access | A dot can use a member’s local files and run commands on their computer | Off |
| Use custom rules for dots | Members can add or edit rules for their dots | Off |
The other dots permissions only take effect once a member has Use dots (Beta).
- For everyone: turn on Use dots (Beta) under Permissions > Workspace default > Workspace capabilities.
- For a pilot group only: grant it through a custom role instead.
The same settings page also has:
- Cloud computer capabilities: Cloud browser use, Cloud network access and Cloud computer use. They decide whether a dot’s cloud computer can browse websites, reach online services and work in apps.
- Use password manager, under Workspace capabilities.
OpenAI says to review how these settings apply across both dots and Work Cloud before changing them.
Apps, Slack and Teams
Apps
- Dots use the workspace’s existing ChatGPT app connections.
- Set app access and allowed actions in Plugin controls, the same place as for ChatGPT.
- The privacy FAQ adds that plugin permissions are shared across dots, ChatGPT, ChatGPT Work and Codex. There is no separate dots-only plugin layer. See connected apps.
Slack
Slack setup needs three parties:
- A ChatGPT workspace owner enables Use dots and Add dots to Slack for the intended members.
- A Slack workspace owner or app manager makes sure the ChatGPT app is installed in Slack and approves app requests if required.
- Each member connects their dot to Slack from its profile.
In Slack, OpenAI says “Only the owner can direct their dot through a Slack direct message or supported channel mention. Messages from other people do not start work.”
Anyone who can see the conversation can see what the dot posts there.
Teams
OpenAI’s two admin pages disagree:
- Help center: the permission is named Add dots to Slack and Microsoft Teams, and lets a dot join supported Teams workspaces “where available.”
- Learn admin guide: “Microsoft Teams access is limited to an invite-only alpha.”
Until they agree, plan an Enterprise rollout on Slack and treat Teams as available only if it shows up for you. Phone messaging through iMessage, RCS or WhatsApp is unavailable for Enterprise at launch, per the help center.
Local computers and data residency
- Separate machines. A dot’s cloud computer is separate from a member’s laptop. Local sign-ins, VPN access and device policies don’t carry over to it.
- Local work needs a connected computer that is online, with ChatGPT open and access enabled.
- Some policies block local access. The learn admin guide says: “If any cloud policy has enforce_residency enabled, local computer access is unavailable for dots. Work Cloud remains available.” The help center words it differently: local access is unavailable in workspaces with Codex or ChatGPT Work policies that target a specific operating system.
- Cloud work still runs. Either way, dots can keep working on their cloud computers when the cloud capabilities are on.
- No residency support in the beta. “During the Enterprise beta, dots do not support data residency or inference residency.” Workspaces opt in after acknowledging that, and enabling dots doesn’t make their data or processing residency-compliant.
- Local access is its own opt-in. OpenAI’s local-access guide says to enable it separately for Work and for dots, under Use Dots in Permissions & roles.
What the admin controls do and don’t cover
| Area | Admin control | Caveat |
|---|---|---|
| Access | Grant or revoke dots through workspace permissions | To revoke, remove Use dots (Beta) from the workspace default and from every role a member has; one granting role is enough to keep access. Apps and website sessions are separate. |
| Cloud and local computers | Cloud browser use, Cloud network access, Cloud computer use, Use password manager, local computer access | Cloud controls apply to dots even when Work Cloud is off. Local access is off by default and blocked by some workspace policies. |
| Messaging | Add dots to Slack and Microsoft Teams | OpenAI’s pages disagree on whether Teams is generally available |
| Connected apps | Available apps and allowed actions in Plugin controls | Shared with ChatGPT, ChatGPT Work and Codex |
| Custom rules | Turn member rules on or off | When off, saved rules don’t apply, but default rules and explicit user instructions still do |
| Models | None | Enterprise model controls and defaults don’t apply to dots |
| Usage and adoption | Analytics API for available adoption metrics | Usage terms after the first month aren’t published yet |
| Audit | Compliance API records of user messages and dots’ replies | OpenAI says to confirm record coverage before relying on it for an audit |
- Turning custom rules off doesn’t remove the safety floor. In OpenAI’s words, default rules “still apply when custom rules are off.”
- It also doesn’t mean every action needs confirmation. Review capability and app approval settings as well. See custom rules.
Points that matter for governance
-
Training. OpenAI’s privacy FAQ says Business, Enterprise and Edu data is not used for training by default. It also says human review may occur in limited circumstances, including safety-related cases.
-
Deleting a dot doesn’t delete everything. It removes only the dot’s own context.
- Files, Codex threads and ChatGPT conversations it created are stored separately and are not deleted.
- ChatGPT memories remain.
- Disconnecting a plugin stops new access but doesn’t remove what the dot already holds.
- OpenAI’s admin guide suggests reviewing saved memories and reset options when handling sensitive data or offboarding. See memory and reset.
-
Built-in guardrails apply everywhere.
- Changing a password or transferring money always requires the user to take over.
- Auto-review checks certain actions, such as sending an email, before they happen. The admin guide says “Drafting a message does not authorize sending it.”
- Prompt-injection protections reduce the risk but, in OpenAI’s words, “do not eliminate” it.
What’s still unannounced
- Usage terms after the first month. The help center now describes an allowance for deeper work with extended limits for the first month. See pricing and usage.
- Prices for adding more dots or scaling one up.
- Whether Teams is generally available for Enterprise, since OpenAI’s two admin pages disagree.
- Availability and pricing for specialist dots.
Specialist dots
The announcement also previews specialist dots:
- Own identity and IT-provisioned hardware.
- Pilots first. OpenAI says they are “starting with focused enterprise pilots” and that a Microsoft Agent 365 integration is in progress.
- No public sign-up path or availability date in the sources we track.
- Separate preview. The primary dot described on the rest of this site is not part of it.
A rollout checklist for admins
| Step | What to decide | Why |
|---|---|---|
| 1. Pilot group | A custom role with Use dots for a small group of users who are 18 or older and comfortable reviewing agent work | You can grant dots through a role instead of the workspace default, and Enterprise access is a beta. |
| 2. Cloud computer scope | Which of Cloud browser use, Cloud network access and Cloud computer use the pilot needs | These settings are shared with Work Cloud, so check both before you change them. |
| 3. Plugin scope | Which apps and actions are allowed in Plugin controls | Permissions are shared with ChatGPT, Work and Codex, so a change affects all four. |
| 4. Custom rules | Whether members may write rules, plus a written default such as asking before any external email | Turning rules off makes saved rules stop applying, while default rules still apply. |
| 5. Local computer access | Whether to opt in at all, and whether your Work or Codex policies block it | Local access is off by default, and residency or OS-targeted policies disable it for dots. |
| 6. Channels | The Slack and Teams permission plus the ChatGPT app in your Slack workspace | Teams availability is unclear, and the ChatGPT permission alone doesn’t install anything in Slack. |
| 7. Oversight | A weekly Activity View review with pilot users, plus a Compliance API coverage check | Activity View is the user-side record, and OpenAI says to confirm Compliance API coverage before an audit. |
| 8. Offboarding | Reset dots and disconnect apps when people leave | Disconnecting an app doesn’t erase what a dot already holds. |
Related reading
Availability (plans and regions) · Custom rules and connected apps (how individual users control what a dot can do)
ChatGPT dots prompts to try
-
Watch Slack for bug reports
Investigates each new bug report in a Slack channel and prepares a fix, without posting.
-
Route updates by channel
Routine progress stays in ChatGPT; decisions and risks reach you in Slack.
-
Keep a sales proposal current
Keeps a proposal in step with the latest emails and call notes, showing every change.
Official sources
Every product fact on this page was checked against the pages below. Last verified . Spot something out of date? Tell us.
- OpenAI Manage dots in ChatGPT workspaces — OpenAI Help Center Accessed Oct 10, 2026
- OpenAI Manage dots permissions and capabilities — ChatGPT Learn Accessed Oct 10, 2026
- OpenAI Local computer access for Work Cloud and dots — ChatGPT Learn Accessed Oct 10, 2026
- OpenAI Control your dot — ChatGPT Learn (Stop work) Accessed Oct 10, 2026
- OpenAI Introducing dots — Get started and specialist dots Accessed Oct 10, 2026
- OpenAI Getting started with your dot — Plans and texting Accessed Oct 10, 2026
- OpenAI Dots privacy, security, and safety FAQs Accessed Oct 10, 2026
- OpenAI ChatGPT Release Notes — Meet your dot Accessed Oct 10, 2026
Questions people ask
Are ChatGPT dots on by default for Enterprise workspaces?
No. OpenAI says Enterprise users can try the beta when their workspace admin enables it, and that it is initially turned off by default.
Where is the admin setting to enable dots?
In Workspace settings > Permissions & roles. OpenAI's admin guide says to enable Use dots (Beta) under Workspace default > Workspace capabilities, or grant it to specific groups through a custom role.
Do our model controls and defaults apply to dots?
No. OpenAI's admin guide says Enterprise model controls and defaults do not apply to dots. Review dots access and capability permissions directly in workspace settings.
Can employees use their dot in Microsoft Teams?
It's unclear. OpenAI's help center names the permission Add dots to Slack and Microsoft Teams, while its learn admin guide says Teams access is limited to an invite-only alpha. Slack is the safer channel to plan on.
Is our workspace data used to train OpenAI models?
OpenAI's privacy FAQ says Business, Enterprise and Edu data is not used for training by default. It also says human review may occur in limited circumstances.
Can employees text their dot?
No. OpenAI says the texting beta is limited to Pro users in the US and is not available in Business or Enterprise workspaces.
What are specialist dots?
A preview OpenAI describes as having their own identity and IT-provisioned hardware, starting with focused enterprise pilots. OpenAI says a Microsoft Agent 365 integration is in progress.