Tech Analysis
OpenAI's Dots: Always-On Agents That Work on a Computer of Their Own
September 2026
At its DevDay on September 29, OpenAI introduced Dots: agents that stay on, keep working on a task after you've stopped talking to them, and do it on a computer of their own. Here's what they are, how you set the rules for them, and who can use them today.
What's new
- Each dot gets its own cloud computer and browser, so work continues when your laptop is closed
- You reach a dot through ChatGPT, Slack or Teams once it's set up
- Plugins connect it to more than 4,000 apps
- It runs on GPT-6 Astra, and can do background research through read-only connections
- It's rolling out on Pro, Business Premium and Enterprise plans in eligible markets, and OpenAI's help documentation labels it beta
How you set the rules
A lot of the design is about delegation: you decide how much a dot does on its own.
- Default rules decide when a dot acts alone and when it asks for a go-ahead
- Custom rules let you allow, require approval for, or block specific actions
- An activity view, plus the ability to open the dot's cloud computer and watch it work
- Access to your own computer is optional and starts switched off
One detail from OpenAI's documentation is easy to miss: a dot's cloud computer doesn't inherit your VPN, your browser sign-ins or your device policies, so reaching some sites can mean signing in on that separate computer. Early coverage of the keynote also says that, for supported logins, a dot can use saved passwords without exposing them to the model.
Where a dot fits
A dot is one way to get AI working for you: on a cloud computer the provider runs. The other is on your own device. They suit different jobs, and plenty of people will use both.
Cloud agent (like Dots)
Suited to work that has to keep going. It runs when your devices are off, can reach thousands of apps through plugins, and can use the largest models.
On-device AI
Suited to jobs on a file or recording you already have. It works offline and needs no accounts, though it's limited to what the device can do and uses smaller models.
Four questions for choosing the right tool
- Does the task need to keep running while my device is off?
- Does it need to work across several apps and accounts?
- Or can it work on a single file I give it?
- Are there actions I'd want to approve myself?
The first two point toward a cloud agent like a dot. If the answer to the first is no and the job fits on one file, a tool on your own device is often enough.
What's still to see
This is based on OpenAI's announcement and early coverage. We haven't tried Dots ourselves, so we can't say how they perform day to day. They're in beta and rolling out gradually, so the details may change as more people use them.
Frequently asked questions
What are OpenAI's Dots?
Always-on agents announced at OpenAI's DevDay on September 29, 2026, powered by GPT-6 Astra. Each dot has its own cloud computer and browser and keeps working on a task after the conversation ends.
Who can use Dots?
According to coverage of the launch, they are rolling out in ChatGPT on Pro, Business Premium and Enterprise plans in eligible markets. OpenAI's help documentation labels the feature beta.
Can a dot control my own computer?
Only if you allow it. Access to your own computer is optional and starts switched off.
Where does a dot do its work?
On a cloud computer and browser of its own, which is why it can keep going when your devices are off. You reach it through ChatGPT, Slack or Teams.
Can I see what a dot is doing?
Yes. There's an activity view, and you can open the dot's cloud computer and watch it work.
Try Offgrid Studio
Four iOS apps that put on-device AI to work for you.
More from Offgrid Studio
Also read: Amazon Blocked Meta's AI Shopping Agent. PayPal Signed It Up Two Days Later. and I'm Not Afraid of AI. Twenty Years of Maintenance Taught Me Why.