A computer of its own
It runs in the cloud with a browser and apps: it keeps working with your phone off and the tab closed.
Personal agents · updated 16 October 2026
Within seven weeks OpenAI, SpaceXAI and Meta launched the same idea: an assistant with a computer of its own, working for you around the clock and calling you only when a decision is needed. Here is what they really do, what they cost and how to use them without handing over the house keys.
What sets them apart
A chatbot answers when you write. An agent carries out multi-step tasks. An always-on agent goes further: it has a permanent workspace and keeps going while you are away.
It runs in the cloud with a browser and apps: it keeps working with your phone off and the tab closed.
It remembers preferences, people, deadlines and the thread of past conversations.
Email, calendar, documents, websites: via connectors or by using the browser as you would.
It doesn't just wait for commands: it flags, chases, proposes. It comes back to you for approvals.
The three agents
OpenAI
An agent with its own cloud computer and browser: you give it a goal, connect the apps it needs and decide what it may do alone. It keeps working after you close ChatGPT and brings back results for approval.
Sources: TechCrunch — OpenAI launches Dots · SiliconANGLE — always-on agents with their own cloud computers · Al Jazeera — OpenAI launches dots
Official site ↗SpaceXAI (xAI)
AI "teammates", each with its own cloud computer, that sign into the sites and apps you use, even those without an API. Several can work in parallel, with a "chief of staff" bot coordinating them.
Sources: xAI — Introducing Grok Bot · Cybernews — Grok Bot and AI agent risks · TestingCatalog
Official site ↗Meta (Superintelligence Labs)
Meta's personal agent works in a virtual machine with a browser you can watch live: it shops, books and runs long tasks in the background, and tells you when it is done.
Sources: Axios — Meta debuts Muse · TechCrunch — Everything new coming to Muse · Wikipedia — Muse (AI agent)
Official site ↗| ChatGPT dots | Grok Bot | Meta Muse | |
|---|---|---|---|
| Cloud computer | ✓ | ✓ | ✓ (virtual machine) |
| Where you talk to it | ChatGPT, Slack, Teams | macOS and iOS apps | Meta AI app and web |
| Strength | 4,000+ connected apps | Parallel bots, routines by demonstration | Shopping and daily life |
| Control | Read-only mode, approvals | Approvals on decisions | Read/write permissions (Sentinel) |
| Entry price | ChatGPT Pro | SuperGrok | Free (US) |
Data checked on 16 October 2026. These products change weekly: check availability and prices on the official site before subscribing.
For work
For a professional or small business the value is not "doing everything alone" but clearing the busywork: sorting, reminding, preparing. The decision stays yours.
Before handing over the keys
For the first weeks the agent reads and proposes; you write, send and pay.
Messages to clients, payments, deletions, signatures: always with your explicit OK.
Where possible, a separate email and calendar, and only the connectors you really need.
An email or web page can hide orders for the agent (prompt injection). A good agent ignores them; you check the logs.
For a professional firm: confidentiality and GDPR apply to the agent too. Use business plans with data-processing agreements.
What it did, what it spent, where it went wrong. Then widen or narrow its permissions.
My opinion on where this is heading is in "Always-on agents". If you want to bring an agent into your firm or company safely, I can help.
Lumen Radio
AI-generated music

Tracklist