AI agents, with our team behind them
Your agent on a machine of its own: mail, Telegram, browser. We set it up with you, watch it, and keep it current.
What one does for you
Forward an invoice from your phone
The table comes back in Telegram. The agent has a mailbox of its own and only listens to senders you allow.
A brief at six, read at nine
Schedule the job and read the result over coffee. It runs on a machine nobody closes, with a run cap so it cannot overspend.
A form filled in Chrome, while you watch
Chrome is on the machine and its screen is visible from your dashboard: the agent browses, fills in, screenshots.
Who does what
| Basic | PRO | |
|---|---|---|
| Setting the agents up | You do, from the starter files and the masterclasses. | We do: the brief, the allowlist, the schedules, wired to your mail and Telegram. |
| Keeping them running | We watch the machine and the agent, so nothing breaks. | We keep them current and fix what misbehaves. |
| What we may do to your agent | «Propose, I decide». A change waits for your approval; nothing reaches the machine before it. | «Apply for me». Our changes go on the machine as they are made, every one listed. |
| Masterclasses | The whole library of recordings, every new one as it lands. | The library, plus the live room every week with a question to the author. |
| Backups | Daily snapshots, about a week kept. | Daily snapshots, about a week kept. |
| A call with the team | An hour one to one, bought when you need it. | Half an hour every quarter, included. |
| Price | €39 per month | €79 per month |
How it goes
-
Choose Basic or PRO
Pay by card. Nothing is set up until you ask for the machine on your dashboard.
-
The machine arrives set up
Claude Code, a mailbox, Telegram waiting for a token, Chrome. Sign in to your Anthropic account from the browser terminal.
-
Share the agent's folder
On the Projects tab you decide what our team may do: read and propose, or apply. You can change it any time.
-
Send it the first job
A mail to its address from yours. On PRO we write the brief with you; on Basic we watch the diaries and propose fixes.
Basic or PRO
The computer is the same. What PRO adds is us doing the setting up, the live room, and a call every quarter.
Basic
The same computer, the whole masterclass library, and backups that run themselves
€39 per month
€397.80 per year
€33.15 a month, billed once a year, 15% off
- Agents you set up, watched by us so nothing breaks
- Masterclasses: Full
- Backups: Daily
PRO
Everything in Basic, plus the recordings live and half an hour with the team every quarter
€79 per month
€805.80 per year
€67.15 a month, billed once a year, 15% off
- Agents we set up and keep current
- Masterclasses: Full, with live participation
- Backups: Daily
- Personal consultation: Once a quarter
Full comparison, Start included, and every question people ask before ordering
Before you order
What is an agent here, concretely?
Claude Code on a Linux machine of its own, with a mailbox, a Telegram bot and a real Chrome browser wired up for it. It gets a job by mail from a sender on your list, works, and replies; it can answer in Telegram and fill in forms in Chrome while you watch its screen from your dashboard. A run cap and a timeout keep a loop from spending your Anthropic budget overnight.
Do I need to know how to code?
No. The terminal is in your browser and the machine arrives with the starter files the cases were built from. On PRO we write the agent's brief and wire it up with you; on Basic you follow the masterclasses, which are the same cases walked through on camera by the people who built them, and we watch that nothing breaks.
What do you see of my data?
Only the folder you share, and only in the mode you chose. A project on the Projects tab is one folder on your machine, usually the agent's own; you decide per folder whether our team may read it and propose, or apply, and you can take that back at any time. Nothing else on the machine is looked at in the ordinary course of business (clause 8 of the Terms of Service).
What does «we watch it» mean on Basic?
The folder you share keeps its history on our git server, so we read the agent's diaries and its instructions rather than logging in to your machine. When something is wrong or could be better, we put a change forward; it waits on your server page and nothing reaches the machine until you approve it.
What does PRO add on top?
We set the agents up rather than watching you do it: the brief, the allowlist, the schedules, the mail and Telegram wiring. Our changes can go straight on to the machine, every one listed and reversible. You are in the room when a masterclass is recorded, with a question to the author, and half an hour with the team is included every quarter.
Which Claude plan do I need?
Your own Anthropic account, on a Claude Pro or Max plan rather than API billing: that is what Claude Code is priced for, and an agent working through the night costs far more per token on the API. We never see the key and add no markup.
How soon does the first agent run?
The machine is usually ready within a few hours of your asking for it on the dashboard, with Claude Code and the starter agent on it. The first real job is a mail from you to its address; on PRO we agree that first job with you.
Can I stop?
Whenever you like. The machine runs to the end of the period you paid for, and on that day it and its backups are deleted, so copy off what you need first.
Can you build a whole workflow for my company?
Yes, as a project of its own rather than a plan: several machines, or ongoing work across a team. Ask for a quote on the price list and say which systems it has to touch.