Hand 80% of your work to AI. Pay for the result 
Claude Code already installed

Cloud AI agents, running 24/7

Rent a machine with Claude Code already on it: your agents work through the mail, answer in Telegram and drive a browser while you sleep.

Nearest free time

Monday, 12 October

15:00

Europe/Berlin (UTC+2)

Book this time

Also free

Your setup, one to one: which agent to build first, how to wire it to mail and Telegram, and why it misbehaves.

All free times

Your laptop stays out of it.

Forward an invoice from your phone and the table comes back in Telegram. The agent has a mailbox and a bot of its own, on a machine nobody ever closes.

Runs on its own, even while you sleep.

Schedule the job for six and read the result at nine. It sits on a machine that holds nothing but the work, so it can go ahead without asking you at every step, and a run cap keeps a loop from spending your budget overnight.

We help with the first steps and the best practices.

Run agents yourself on a Mini, or have us run them: Start, Basic and PRO carry one, two, or three managed agents. Either way, root is yours.

A typical remote computer

Linux (Ubuntu LTS), usually in a European datacentre. Basic and PRO: a server of your own, at least 4 GB, 40 GB SSD, its own IPv4. Start: a Mini, 1 GB, 10 GB, shared host, no browser.

You are the only user on that machine and root is yours, so it can be set up any way your work needs. There are two ways in: a terminal in the browser, inside your dashboard, with nothing to install on your side, or ordinary SSH once you add your key.

Latest cases

Video 26:28

Claude apologised and promised never to do it again? Do not trust promises, set up hooks

Claude apologised and promised never to do it again, and a couple of days later it all happened again. A promise lives in one conversation, and Anthropic's guide calls the rules in CLAUDE.md advice. A hook is a check Claude cannot skip: Claude Code runs it itself, before an action, after it or at the end of an answer. Where a hook is needed (deleting data, emails, putting code online, spending money), where it only slows the agents down, and the author's five working hooks: dangerous commands, emails in his name, the task log, the skeptic and a sound. The recording of the masterclass and the working kit of files that goes with it.

Slava Sazhin 30 September 2026
Video 28:22

Giving your child the right access to top AI. Building a custom web app

A child needs their own helper, not a shared chat under your login. A web app on your server goes on the phone's home screen, and Claude answers on a separate subscription. The character says what the helper is like, not what it must not do: it does not shut down a topic beyond the child's age but answers briefly and calmly, sends the child to adults about health, medicines and money, and on anything dangerous puts a mark the child cannot see, and you get a message. You read the chats, and the child knows it. The recording opens with the new Opus 5.5: which effort level for which role. The recording of the masterclass and the working kit of files that goes with it.

Slava Sazhin 23 September 2026
Video 26:40

Which model for which task, so the bill does not ruin you? Do not ask Fable 5 for a casserole recipe

There are two knobs, and usually only one gets turned: the model is the ceiling of ability, and the effort level is how thoroughly it works. Slava's own blind test and the independent FrontierCode measurement say the same thing: the line of the model matters more than the effort inside it, and max costs four times what medium does without adding accuracy. Where the model and effort pair is set, and why it belongs in one file. And a fallback for helper agents when an expensive model runs out of limit: a hook catches the refusal and moves the role to a fallback model. The recording of the masterclass and the working kit of files that goes with it.

Slava Sazhin 17 September 2026

From the blog

Contact the Combobulating team