iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
OpenAI dots can keep working on a goal between ChatGPT conversations, but “always-on” does not mean unrestricted access or permission to take every action. A dot’s reach depends on the apps and optional computer access you connect, the permissions granted by those services and any workspace administrator, and the rules for the specific action. Some work can proceed independently; other work requires your approval or your direct involvement.
What a dot is—and what “always-on” means
OpenAI describes a dot as an agent in ChatGPT that can maintain responsibility for an ongoing goal and make progress between conversations. It uses its own cloud computer and the apps you choose to connect, retains context for its work, and brings results back for you to review. You set the goal and define what it may do independently; it can ask for judgment when needed.
This continuity is different from a single prompt followed by a single response. It does not, by itself, grant blanket permission to use every app, reach your local computer, or perform every possible action. Access and authority are governed by separate controls.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Who can use dots, and how setup works
As described in OpenAI’s Help Center on October 7, 2026, dots were rolling out gradually to ChatGPT Pro users in markets excluding the European Economic Area, Switzerland, and the United Kingdom. Business Premium users could access them in supported regions. Enterprise, Edu, and Healthcare users could try the beta when a workspace administrator enabled it. Eligibility and rollout can change, so check OpenAI’s current “Getting started with your dot” Help Center page for availability in your plan and region.
#1 Best Overall
Dot creation is available in the ChatGPT desktop app or desktop web. After setup, mobile access is available; mobile web is not supported, according to the same Help Center page as of that date.
Optional access to your local computer
A dot’s cloud computer is distinct from your own computer. Local computer access is optional and starts turned off. Connecting a computer and confirming “Allow access” lets the dot access files and work on that computer from its messaging channels. “Revoke access” removes that local-computer access. Turning on this connection is separate from granting access to the dot’s cloud computer.
Connected apps and their permissions
You choose which supported apps to connect and review their permissions. A dot can use existing ChatGPT connections within the permissions already granted; those plugin permissions are shared across dots, ChatGPT, ChatGPT Work, and Codex. The connected service’s own authorization also limits what is available. Disconnecting an app stops new access through that connection, but does not erase information the dot has already incorporated into its context.
What a dot may do without asking
There is no single “autonomy” switch that governs every action. OpenAI says dots have built-in defaults for actions that may proceed without confirmation, actions that require approval, and actions that must be completed by the user. Custom Rules can set supported actions to proceed independently, require approval, or be blocked. They cannot override core safeguards, required Autoreview, or the limits on proactive research.
Approval, pre-approval, and user handoff
OpenAI’s privacy, security, and safety FAQ gives examples of the distinctions: changing a password or transferring money requires you to take over; permanently deleting data or installing software may require approval each time. Some actions, such as recurring messages, may be pre-approved. Any advance approval is bounded by what you authorize: specify the recipient, content, and timing or conditions where relevant. OpenAI states, “Approving one message does not give your dot ongoing permission to contact people on your behalf.”
A general instruction to handle a task does not remove a required approval or handoff. Treat permission for a particular action as permission for that action within its stated scope, not as standing permission for similar future actions.
Rank #3
Background research is not the same as taking action
OpenAI calls background checking “proactive research.” The company says this mode can read permitted sources in already connected apps and save private notes, but cannot send messages, change app content, or control a browser or computer. If the dot later acts on information it found, that action is subject to the ordinary action rules and safety checks. Reading or preparing information in the background does not authorize sending, editing, or operating something.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Clear out junk files and repair common Windows errors3Scan for outdated or missing drivers - takes under a minutePersonal controls and Enterprise administration
Personal settings and workspace administration overlap: a user can define what their dot may access or do, while an eligible Enterprise administrator can separately limit who may use dots and which capabilities are available to the workspace. OpenAI’s “Manage dots in ChatGPT workspaces” page describes these Enterprise controls as of October 7, 2026.
| Control area | Personal user | Enterprise workspace administrator |
|---|---|---|
| Who grants access | The user connects supported apps and, optionally, a local computer. | The administrator controls workspace eligibility and capabilities; each member still completes personal setup and app connections. |
| What can be limited | Connected-app permissions, supported actions through Custom Rules, and whether the dot must ask or hand off. | Use dots (Beta), Slack and Microsoft Teams capabilities, local computer access, Custom Rules, cloud browser, cloud network, cloud computer, and a separate password-manager control. |
| How access is removed | Disconnect an app to stop new access, or revoke local computer access. Previously incorporated context is not erased by disconnecting an app. | Review workspace defaults and all direct or group roles; a role that grants access may still confer it even if another role turns it off. App authorizations and website sessions are managed separately. |
Slack, Teams, and shared channels
Enabling dots does not automatically install a Slack app or connect an individual member’s dot. Slack may require workspace app approval, and each member completes setup. Only the dot’s owner directs its work; another person’s message or mention does not start that dot. A dot’s posts in a channel are visible to that channel’s members. OpenAI’s Enterprise page said phone messaging through iMessage, RCS, or WhatsApp was unavailable for Enterprise at launch; channel support is time-sensitive and should be checked in current workspace documentation.
How to monitor, redirect, or stop ongoing work
Activity View lets you review a dot’s task description, status, and steps. You can add context, correct a misunderstanding, change direction, or stop the dot. Some completed actions may be reversible and others may not be, depending on the action and app. OpenAI cautions that dots can still make mistakes and says to review consequential work; do not assume every action can be undone.
OpenAI describes safeguards that include model safeguards, plugin permissions, Custom Rules, automatic review of certain planned actions, and safety monitoring. These measures do not eliminate the need to inspect consequential work, and approvals cannot override core safety requirements.
What happens to dot context and data
A dot may receive ChatGPT memories and recent conversation context, and its conversations can contribute to ChatGPT memory. Its own context can persist for as long as you keep the dot. Deleting a dot deletes its own context, but files and conversations created elsewhere and ChatGPT memories are managed separately. OpenAI’s FAQ says users cannot currently view, delete, or directly modify individual dot memories.
Best Value
Model improvement depends on account type and settings
OpenAI says Business, Enterprise, and Edu workspace data are not used to train models by default. On personal ChatGPT plans, the “Improve the model for everyone” setting controls whether eligible dot conversations and work may be used for model improvement. OpenAI says it does not train directly on proactive background research or the dot’s notes; information from that research may be used if it informs an eligible conversation or task, depending on the applicable settings. These are OpenAI’s stated data practices, not an independent security audit.
Other setup details that can affect use
- OpenAI’s Help Center said dots could connect to Slack and personal email, but a standalone email address for a dot was not available at launch.
- Scheduled reminders and recurring checks can be managed from the dot profile or the Scheduled section.
- Texting was described as a limited beta for some Pro users in the United States, not available in Business or Enterprise workspaces; message and data rates may apply.
- OpenAI’s September 29, 2026 announcement said the connected-app ecosystem included over 4,000 apps. This is OpenAI’s stated figure, not an independent count.
These availability and channel details are time-sensitive. Check OpenAI’s current Help Center pages, “Getting started with your dot,” “Dots privacy, security, and safety FAQs,” and “Manage dots in ChatGPT workspaces,” before relying on them.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
