Use cases

OpenAI Dots Use Cases: What Teams Actually Use Them For

Dots are general-purpose agents, but concrete examples make them easier to judge. These are the five scenarios OpenAI highlighted.

Last verified: September 30, 2026 · Reviewed by AstraDot editorial desk

A general-purpose agent is hard to evaluate in the abstract. What helps is seeing a real workflow: the kind of work, the hand-offs, and the point where a person still has to decide. When OpenAI announced Dots on 29 September 2026, it described five such workflows rather than listing features. This page collects them and points to the deeper, role-by-role guides where the details matter.

All five share the same underlying abilities. Every Dot is powered by GPT-6 Astra, has its own cloud computer and a browser, can write and test code, connects to 4,000+ apps, learns from feedback over time, works 24/7, and can take on a project while handling several others. What changes between scenarios is the domain, the people who review the work, and the guardrails that make sense.

The five scenarios OpenAI highlighted

1. Developers: feedback into tested pull requests

A Dot watches recurring customer feedback, scopes small improvements and bug fixes, builds and tests them, and brings back complete pull requests with videos. The interesting part is not that code can be written, but that the loop — listen, scope, build, test, hand over — keeps running without someone relaying it by hand. Our Dots for developers guide covers the end-to-end flow, the review boundary, and how to split work safely.

2. Launch leads: materials that track a moving scope

Launch scope changes constantly, and every change ripples through documentation, messaging and internal briefs. OpenAI's launch-lead example describes a Dot revising launch materials as scope changes, so the artifacts stay consistent with the latest plan. There is no dedicated page for this role yet, but the mechanics are the same as the other use cases: the Dot drafts and updates; you approve the positioning that goes public. The explainer is the best starting point.

3. Sales: proposals that keep up with requirements

A sales lead's Dot checks customer requirements and account history against product documentation, finds what needs testing, builds a proof of concept, suggests a solutions engineer, and updates the proposal and test plan as things change. Commitments are the sensitive surface here, so approvals matter. See Dots for sales teams.

4. Content creators: transcript to published drafts

A creator's Dot learns the creator's voice, turns an interview transcript into clips, show notes and social posts for approval, carries edits across the materials, and learns what resonates. The human keeps the editorial call. See Dots for content creators.

5. Scientists: analysis that updates with evidence

A scientist's Dot learns the research question and how evidence is evaluated, reruns analyses as data arrives, investigates unexpected results, updates figures, and revises explanations while flagging what needs review. Scientific judgement stays human. See Dots for scientists.

ScenarioThe recurring workWhere a person decides
Developer Watch feedback, scope fixes, build and test Review and merge pull requests, set architecture
Launch lead Rewrite materials as scope changes Approve public positioning
Sales Compare requirements to docs, build a PoC Approve commitments and pricing
Content creator Draft clips, show notes and posts from a transcript Approve voice and final edits
Scientist Rerun analysis, update figures Interpret results and judge validity

10 things teams can use Dots for

The five scenarios above are OpenAI's examples; below are ten broader categories of work a Dot can potentially assist with, given the abilities OpenAI has described. Each description uses the same three-part frame: what a Dot can do, an example task, and the typical workflow around it.

Research

What Dots can do: a Dot is designed to gather sources, rerun analyses, and keep a running set of findings you can inspect. Example task: track a research question, rerun the analysis when new data arrives, and flag what needs review. Typical workflow: you set the question and evaluation criteria, the Dot works continuously, and you check the flagged results before they are used.

Coding

What Dots can do: a Dot can write and test code and bring complete changes back for review. Example task: watch recurring feedback, scope small fixes, build and test them, and return a pull request with a short video. Typical workflow: you provide repository context and rules, the Dot iterates on the change, and a person reviews and merges it.

Writing

What Dots can do: a Dot can potentially draft and revise documents, keep related material consistent, and carry your edits across drafts. Example task: turn an interview transcript into show notes and social posts for approval. Typical workflow: you define the voice and audience, the Dot drafts, and you approve anything that goes public.

Data analysis

What Dots can do: a Dot is designed to rerun analyses, investigate unexpected results, and update the figures that depend on them. Example task: rerun a model when a dataset refreshes and revise the accompanying explanation. Typical workflow: you set the question and how evidence is judged, the Dot updates the work, and you interpret the result.

Web research

What Dots can do: using its own browser and read-only proactive research, a Dot can gather and compare sources in the background. Example task: monitor a topic and compile a summary of new developments with links. Typical workflow: you define the scope and trusted sources, the Dot collects and summarises, and you verify before relying on it.

Browser tasks

What Dots can do: a Dot can drive its own browser to work through multi-step tasks on the web. Example task: check a set of pages for changes and record what moved. Typical workflow: you describe the target and the boundaries, the Dot runs the steps, and you inspect progress in the activity view.

Computer tasks

What Dots can do: a Dot runs on its own cloud computer, so it can perform file and app work away from your device. Example task: prepare files, run a script, and package the output. Typical workflow: you connect only the tools it needs, the Dot does the work, and you review the result before you rely on it.

Business operations

What Dots can do: a Dot can potentially handle recurring operations across the apps you connect. Example task: compare requirements and account history against documentation and keep a proposal current. Typical workflow: you set Custom Rules and approval points, the Dot keeps the work up to date, and a person signs off on commitments.

SEO

What Dots can do: a Dot can potentially help with recurring SEO work such as monitoring pages and drafting updates. Example task: track a set of target queries and draft on-page changes for review. Typical workflow: you define the targets and tone, the Dot drafts, and you approve changes before they are published.

Marketing

What Dots can do: a Dot is designed to help with campaign assets and keep them consistent as plans change. Example task: update launch materials when scope changes and prepare drafts of asset and document changes. Typical workflow: you set positioning and rules, the Dot revises the material, and you approve the public messaging.

What the scenarios have in common

Each example describes ongoing responsibility rather than a one-off request. The Dot holds context, keeps working in the background, and reports what it did through an activity view. Each also keeps a person at the decision that carries risk: merging code, approving a commitment, publishing in a voice, interpreting a result. Auto-review checks actions against your instructions, Custom Rules and safety requirements before consequential steps, proactive research uses read-only tools, and some sensitive tasks always stay with you.

Dots can make mistakes. Treat the scenarios as a map of where an always-on agent can absorb recurring effort — not as a claim that any of this runs unattended. The security and privacy guide covers the controls, and our free Agent Readiness Scorecard helps you decide which of your own workflows fit next.

Choosing your first scenario

The five scenarios are not equally easy to adopt, and the order in which a team gets value from them depends on how much of the work is already well defined. A developer loop with a fast test signal and a clear reviewer is relatively easy to start, because success and failure are visible. Content repackaging is a natural early candidate because the approval step is low-risk and the feedback is immediate. Sales and launch work sit closer to commitments, so they benefit from stricter rules and explicit sign-off. Scientific analysis demands the strongest reproducibility and review discipline of all. Whichever you choose, the pattern is the same: start narrow, keep a human at the decision, and widen only once the loop is reliable.

How to choose your first use case

Start with the workflow that already has a clear definition of done and a named reviewer, then widen from there. For a practical first assignment, see how to use OpenAI Dots; for the basics of what a Dot is and how it works, see what OpenAI Dots are.

Is your task suitable for an AI agent? Score it with the free Agent Readiness Scorecard — or estimate the running cost with the Dot cost comparator.

Source: OpenAI, Introducing dots.

Frequently asked questions

Which use cases did OpenAI actually name for Dots?
OpenAI described five situations in its launch announcement: a developer turning customer feedback into tested pull requests, a launch lead revising launch materials as scope changes, a scientist rerunning analysis and updating figures, a sales lead updating a proposal and building a proof of concept, and a content creator turning an interview transcript into clips, show notes and posts. Our use-cases hub maps them to role guides.
Are these the only things Dots can do?
No. The five scenarios are examples OpenAI gave, not an exhaustive list. A Dot has its own cloud computer and browser, can write and test code, connects to 4,000+ apps and can keep several projects moving at once, so the realistic scope is wider. See what Dots are for the full picture.
Do Dots run these workflows without any human input?
No. A Dot works continuously and reports through an activity view, but consequential actions pass through auto-review against your instructions, Custom Rules and safety requirements, and some sensitive tasks always stay with you. Read Dots security and privacy.
How do I know whether my team is ready for a Dot?
Start with the specific workflow, not the tool. Our free Agent Readiness Scorecard helps you judge which processes are candidates for an always-on agent and which still need a human in the loop.