What is shared, officially
The overview is explicit: an account has one cloud computer, and Bots work on it with a browser, a file system, and a terminal. Bots sign into your apps with your real logins. Approvals and ask-first rules govern what a Bot does, not which Bot can see what. A shared Bot link copies profile, skills, and routines, but recipients never get your computer, logins, or history.
So a Bot named Finance and a Bot named Marketing are two roles on one machine. Treat everything the computer is signed into as reachable by every Bot, and design your access accordingly.
Documentation: Grok Bot overview ↗ Approvals, security and privacy ↗
Why browser logins disappear
Community reports from mid-August describe Chrome profiles on the shared computer resetting daily, so sites that were signed in yesterday ask again today. The official troubleshooting page covers the symptom rather than the cause: take over, sign in manually, complete two-factor or CAPTCHA yourself, confirm the page loaded, and tell the Bot to continue. Never paste a password into the chat.
Practical consequence: prefer plugins over browser sign-in wherever a plugin exists, because plugin authentication persists in Settings, Plugins, while a browser cookie may not.
Documentation: Official troubleshooting ↗ CellCog problems tracker ↗
One thread per Bot, forever
Each Bot is a single conversation that grows without a visible context meter and, per community reports, without a clear or compact option. Near the limit the product summarizes automatically. A forum thread from September describes memory writes failing across a fleet while a state snapshot was cut short, which is what a summarization boundary looks like from outside.
Work around it by scoping Bots to jobs rather than to people. When a project ends, retire the Bot and start a new one; when a Bot's answers start losing earlier instructions, that is your signal.
Documentation: CellCog problems tracker ↗ Forum: memory writes fail fleet-wide ↗
- Nothing signed into the shared computer would be catastrophic if any Bot touched it.
- Plugins are used where they exist; browser logins are the fallback.
- Local computer execution stays disabled unless a task needs it.
- Long projects get their own Bot, and finished projects get retired.
Quick answers
Do my Bots have separate computers?
No. The official overview describes one persistent cloud computer per account, with its browser, file system, and terminal shared by every Bot you create. Separate Bots are separate conversations and roles, not separate machines or separate logins.
Can I use one Bot for sensitive accounts and keep the others away from them?
Not by using Bot boundaries. Any Bot on the account can reach a browser session another Bot signed into. If a login must stay isolated, keep it off the shared computer entirely or use a second account.
Can I clear a Bot's context or start a fresh session?
Not as of our check. Community reports, including one that cites Cursor staff confirmation on August 20, describe each Bot as a single continuous thread with auto-summarization near the limit and no user-facing clear or compact. The workaround is to create a new Bot for a new long project.
Sources & next steps
Capabilities are grounded in the documentation below. The workflow design and acceptance checks are editorial suggestions.
- Grok Bot overview ↗
- Approvals, security and privacy ↗
- Official troubleshooting ↗
- CellCog problems tracker ↗
- Forum: memory writes fail fleet-wide ↗