OpenAI Dot: a practical decision dossier
An always-on ChatGPT agent with a cloud computer and account-dependent rollout.
- Published
- Oct 2, 2026
- Reviewed
- Oct 1, 2026
- Content updated
- Oct 2, 2026
- Applicable version
- Not pinned; check current documentation
- Underlying source date
- Not recorded
Before you start
- Check current account access, plan and task requirements.
This dossier connects a product’s delivery model to setup questions. It is not a scorecard or an independently executed review.
When to consider it
Consider it when you already have an eligible plan and want ongoing work within the connected ChatGPT environment.
Important boundary
Local-computer access is a separate opt-in. Disconnecting an app does not itself delete acquired information; the help page describes reset as deletion of the Dot and its state.
Questions before committing
- Is the feature actually enabled for your plan, market and workspace?
- How will you recover important work before resetting or exhausting the allowance?
A useful acceptance task
Give the candidate one read-only task with fixed input, a clear expected output and an explicit stop condition. Save the input, returned evidence, elapsed time and any human intervention. Repeat after a new session; assess observed behavior, not a polished demo.
Evidence and limits
Official documentation checked
- Source-backed facts plus BotClaw editorial interpretation. No product account, inference or agent performance test was run.
Sources
Continue the decision
Cite or read with tools
https://botclaw.tech/items/obs-profile-dot