Recommended Free Tools
OpenAI Dots are persistent AI agents inside ChatGPT: give one an ongoing goal, connect the apps it needs, and it can keep working between conversations using its own cloud computer and saved context. A Dot can take some actions within the permissions and rules you set, but it is not unrestricted: proactive background research is read-only, and sensitive actions may require your approval or direct involvement.
What are OpenAI Dots?
A Dot is an always-on agent designed to carry responsibility for a continuing task rather than answer just one prompt. OpenAI describes it as an agent that can keep making progress between conversations, track changes, and bring decisions back to you when human judgment is needed. Each Dot has a cloud computer and browser, and can use apps you choose to connect. Its cloud work can continue while your own devices are off.
As an Amazon Associate I earn from qualifying purchases.
The difference from an ordinary ChatGPT exchange is persistence: a Dot can maintain task context, resume as circumstances change, and communicate through supported channels. OpenAI says Dots are powered by GPT-6 Astra and can connect to more than 4,000 apps through its plugin ecosystem. That is OpenAI’s 2026 product statement, not an independent audit; availability and capabilities vary by integration.
OpenAI’s Help Center defines a Dot as “an always-on agent in ChatGPT that can take on ongoing responsibility and keep making progress between conversations.”
#1 Best Overall
Can a Dot work across your apps?
Yes, when the relevant supported apps are available and you grant the permissions they need. You select which services to connect and review their access. A Dot may use connected app information for assigned work and, according to OpenAI, proactive review and memory formation. The exact actions it can take depend on the particular app and the permissions granted.
Access to your local computer is separate and optional, and starts off. If you enable it, the Dot can access files and work on that computer. The desktop ChatGPT app is required to connect a local computer; you can revoke that access.
What can an OpenAI Dot do on its own?
A Dot’s autonomy depends on the kind of work, the app permissions, and the rules in effect. OpenAI distinguishes proactive background research from other assigned work:
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minute| Work mode | What OpenAI says it can do | What to keep in mind |
|---|---|---|
| Proactive background research | Review connected apps using read-only tools. | Those tools cannot send messages, change app content, or control the browser or computer. |
| Other assigned work | Take supported actions subject to app permissions, built-in checks, and your custom rules. | Some actions require approval; sensitive actions, such as changing a password or transferring money, require you to take over. |
You can inspect activity and task steps, add context, redirect the work, or ask the Dot to stop. Stopping a task does not necessarily undo actions it has already completed; reversibility depends on the action and app. Review consequential results rather than assuming every change can be rolled back. OpenAI’s announcement describes its safety measures, but those safeguards are not an independent guarantee that errors cannot happen.
Rank #3
What tasks are Dots intended for?
OpenAI’s examples illustrate the intended workflows, not independently verified performance in every connected app. They include investigating a Slack bug, turning a design into a working app, keeping a planning cycle on schedule, and drafting creator materials for approval. OpenAI also describes an early tester’s Dot preparing an invoice and sending it after the tester approved it.
OpenAI’s Help Center and ChatGPT Learn describe continuing tasks such as reviewing a calendar, doing research, setting reminders, tracking decisions and deadlines, keeping a sales proposal current as requirements change, and updating a study as new measurements arrive. These tasks suit the persistent model because new information can arrive after the initial instruction. Whether a particular Dot can perform each step depends on the connected apps and permissions.
How do you get access and create a Dot?
Access is rolling out gradually, so eligibility does not guarantee that the feature has appeared in your account. OpenAI’s current Help Center describes access for Pro users outside the European Economic Area, the United Kingdom, and Switzerland; Business Premium users across supported ChatGPT regions; and Enterprise, Edu, and Healthcare users when a workspace administrator enables the beta.
OpenAI says the first Dot is included in Pro or Business Premium at no extra cost, with an allowance for deeper work and extended limits for the first month after launch. The Help Center does not establish durable future quotas or a comparable total-work limit. Check the current account and workspace guidance before relying on access or usage limits.
Best Value
- Use desktop: Create a Dot in the ChatGPT desktop app or on desktop web. Current guidance says you cannot create one on mobile, and mobile web is unsupported.
- Define the ongoing goal: Explain the work, how it should proceed, and which decisions should come back to you.
- Connect only needed apps: Review the permissions for each supported service before granting access.
- Set boundaries and review: Specify what the Dot may do, monitor its activity, and approve or take over when needed.
Mobile can be used to continue with a Dot when the supporting update is available. Check OpenAI’s getting-started guidance for the latest availability and setup details.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.What should you know about Dot memory and privacy?
A Dot can retain conversation and plugin context for as long as the Dot exists. Deleting the Dot removes its own context, but files, Codex threads, and ChatGPT conversations it created may be stored separately. Disconnecting an app stops future access through that connection; it does not erase information the Dot has already incorporated into its context. OpenAI says users currently cannot view, delete, or directly edit individual Dot memories.
Data use depends in part on your plan and settings. OpenAI says Business, Enterprise, and Edu workspace data is not used to train models by default. On personal ChatGPT plans, the “Improve the model for everyone” setting controls whether eligible conversations and work may be used. OpenAI also says it does not train directly on proactive background research or a Dot’s private notes. Information from that research brought into an eligible conversation or task may be used depending on your settings. Its statement is: “We don’t train directly on proactive research or your dot’s notes to itself.”
Free tools Windows power users keep installed
One-click scans. No signup required.
OpenAI says existing ChatGPT app controls govern connected-app permissions and that it uses safety monitoring and safeguards against malicious instructions. For details on what disconnecting or deleting does, consult OpenAI’s Dots privacy, security, and safety FAQs.
When do Dots make sense?
A Dot may be useful when work needs to continue across conversations, depends on updates in connected apps, and benefits from having a human review important decisions. It is less suitable for work that requires unrestricted access, guaranteed accuracy, or actions you cannot safely delegate under the available permissions. The official material does not establish an independent reliability benchmark or a controlled comparison with other AI agents, so feature descriptions and company examples should not be treated as proof of consistent results.
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.
