Dots by OpenAI

Dots by OpenAI are always on agents that live inside ChatGPT and are powered by GPT-6 Astra. Each dot is given its own cloud computer and its own browser, connects to over 4,000 apps through plugins, and can work toward your goals 24/7. The agent is reachable in ChatGPT on desktop, web, and mobile, and it can also be messaged in Slack and Teams. According to the product description, dots learn your preferences from feedback and bring you finished work to review, while Custom Rules, Activity View, and auto review are provided to keep you in control. Dots is rolling out now to Pro and Business Premium. The tagline frames the product plainly: always on agents built to handle everything. That framing is the context for why Dots exists. A conventional assistant interaction is bounded by the session — you ask, you get a response, and the work pauses until you come back. Dots is described instead as working toward your goals 24/7, with an environment of its own. The stated feature set — a cloud computer, a browser, plugin connections, always-on operation, and review controls — reads as a response to work that is continuous rather than conversational. It also speaks to a second problem that appears in the description: when an agent acts on its own, you need ways to shape its behavior and see what it has been doing. That is why Custom Rules, Activity View, and auto review are listed alongside the agent itself. Because availability is limited to Pro and Business Premium at launch, the product is positioned for people who already pay for ChatGPT and want more than a chat window. The first capability group is the always-on operation itself. Each dot has its own cloud computer and browser, and can work toward your goals 24/7. Those three facts belong together. Because the computing environment sits in the cloud rather than on your device, the dot is not dependent on your machine being awake, and because it has a browser, it has a way to act in the same places work normally gets done on the web. The 24/7 framing is the point of the whole product: the agent keeps moving toward a goal outside a single sitting, rather than only answering when you message it. For the user, this is the difference between an assistant that replies and an agent that progresses. It also explains why the product is described as being built to handle everything, and why control features are treated as a necessary companion to autonomy rather than an add-on. The second capability group is connectivity. Dots connect to over 4,000 apps through plugins, according to the product description. In practice, that plugin layer is what lets a dot reach past ChatGPT itself and work with the external tools a goal depends on, instead of remaining confined to a single conversation. The number matters because the range of apps dictates the range of work an agent can be pointed at: the more services it can connect to, the more of a real workflow a dot can cover. Combined with its own browser, plugin access means a dot is not limited to what it can reason about — it has routes into the systems where the actual tasks live. For a user delegating ongoing work, this is what turns an agent into something that can operate across the tools they already use. The third capability group is how you reach the agent. The description states that you can message or call your dot in ChatGPT on desktop, web, and mobile, or message it in Slack and Teams. That spread of surfaces matters for a product built around always-on work. If a dot is running continuously, you need to be able to check in, add instructions, or answer a question from wherever you happen to be, rather than only from one machine. Covering desktop, web, and mobile keeps the same agent reachable through the ChatGPT surfaces you already use, and adding Slack and Teams brings it into the messaging tools where teams already collaborate. The result is that dot work can be folded into existing communication habits instead of requiring a separate application. The fourth capability group is learning and delivery. Dots learn your preferences from feedback, and the agent brings you finished work to review. Those two statements describe a loop: you respond to what a dot produces, the dot takes that feedback on board, and the output it returns is framed as finished work rather than an intermediate draft. For the user, this changes the rhythm of using an assistant. Instead of correcting the same things repeatedly, feedback is expected to shape how the agent approaches later work, and the review step keeps a human in the position of accepting results. The description places this alongside the control features, which suggests delivery and oversight are meant to operate together. The fifth capability group is explicit control, named as Custom Rules, Activity View, and auto review. The description says these keep you in control. Each addresses a different part of supervising an autonomous agent. Custom Rules give you a way to define how a dot should behave, so its operation reflects your requirements rather than defaults. Activity View gives you a window onto what the agent has been doing while it worked, which matters when the work happened without you watching. Auto review adds a review step into the process. Taken together they answer the obvious question that always-on agents raise — what happens while I am not looking — by giving you rules upfront, visibility during, and review after. The overall approach follows from those pieces. A dot is powered by GPT-6 Astra, runs on its own cloud computer, and has a browser, which is the operating environment. Plugins to over 4,000 apps are the connections. ChatGPT on desktop, web, and mobile, plus Slack and Teams, are the interfaces through which you message or call it. Feedback is the learning channel, and Custom Rules, Activity View, and auto review are the supervision layer. The product description presents this as one arrangement: an agent that is always on, equipped to operate, connected to your tools, reachable where you already are, and supervised by you. That combination — not any single capability — is what Dots is described as offering. The benefits stated or directly implied are about continuity and oversight. Work toward your goals no longer depends on you being present to drive each step, because a dot can work 24/7 on its own cloud computer. You are not forced into a single tool, because the agent can be messaged in ChatGPT or in Slack and Teams. You are not left without visibility, because Custom Rules, Activity View, and auto review are named as controls. And you are not handed raw output, because the dot brings finished work to review. What the description promises is delegated progress with a defined review point, rather than either a passive assistant or an unsupervised process. Concrete workflows follow the surfaces described. You can message or call your dot in ChatGPT on desktop, web, or mobile to give it direction or check on progress. You can message it in Slack or Teams when work is coordinated in those platforms. You can set Custom Rules for how the dot should operate, then use Activity View to see what it did across the time it ran on its own, with auto review in place as the review step. And you can take delivery of finished work to review, then give feedback so the dot learns your preferences for next time. These are the interactions named in the product description, and together they form a cycle of instruction, autonomous work, inspection, review, and correction. On audience and availability, the description is specific: Dots is rolling out now to Pro and Business Premium. That places the product with paying ChatGPT plans rather than a free tier, and it accounts for the Slack and Teams messaging, which suits organizational settings on Business Premium. No integration partners beyond the 4,000-plus app plugins are named, and no pricing details beyond the plan rollout are given. The underlying technology stated is GPT-6 Astra, and the agent's environment consists of its own cloud computer and browser. Everything else about availability is simply that it is rolling out now to those two plans. The takeaway is straightforward. Dots by OpenAI takes the agent idea and makes it continuous: always on, powered by GPT-6 Astra, each dot equipped with its own cloud computer and browser, connected to over 4,000 apps through plugins, and working toward your goals 24/7. Reaching it is meant to be easy — message or call in ChatGPT on desktop, web, and mobile, or message in Slack and Teams — and supervising it is meant to be explicit, through Custom Rules, Activity View, and auto review, with finished work delivered for your review and feedback that teaches the dot your preferences. That combination of autonomy and control is the product's core proposition for Pro and Business Premium users.