I'm Sohail. I run a few businesses out of Amsterdam, not with a big team but with a set of AI agents that do real work: shipping code, running ad campaigns, keeping the books, research, visuals, the day to day. This is how the whole thing fits together, written so you can copy it for your own life and business.
One agent holds the whole picture and hands out work. Each specialist owns one lane and reports back. You stay on vision and the calls that matter.
No point reading eight minutes if it isn't your thing. Quick gut check.
The agents run on a free, open-source program called OpenClaw. You install it on a computer that stays switched on. It connects an AI model (the same kind of AI behind ChatGPT) to your Telegram or WhatsApp, so you can message it like a colleague, and it can do work on that computer for you.
Your own computer or a small server, not someone else's cloud. Your files, notes and keys stay with you.
Telegram, WhatsApp, Slack or a web chat. You message an agent like you'd message a person.
Daily notes plus a curated long-term file. It doesn't forget last week when the chat scrolls away.
Run code, browse, search the web, make images, and run many agents side by side.
Checks and jobs fire on their own, so the routine stuff happens without you asking each time.
It's open source, maintained by its community, so you can read exactly what it does. Docs at docs.openclaw.ai and the code at github.com/openclaw/openclaw.
I don't think of them by name, I think of them by job. One agent runs the show and the rest are specialists. Same as any small company, except nobody sleeps.
The chief of staff. Holds context and memory, takes the request, decides who does what, reports back. Everything routes through here.
One per venture. Builds features, reviews pull requests, ships code, watches for errors.
Runs and reads ad campaigns, pulls performance, flags what's working and what's tired.
Makes on-brand images. It even has a trained model of my own face, so campaign shots look like me without a photoshoot.
Catches invoices as they land and files them into the accountant's system, with an ignore list so it skips the junk.
One digs into decisions and writes short memos. One helps with the personal side, like styling and everyday admin.
Most of it runs without me. I read a brief in the morning, the boring stuff happens on its own, and I only step in for the calls that matter.
Overnight summary: what shipped, uptime, new issues, ad numbers, anything that needs a decision.
Scheduled checks, memory upkeep, uptime pings, issue triage, draft work. No human needed.
Ship a page, pull a report, draft a contract, analyse a creative, research a decision.
Money over a set limit, public posts, anything irreversible. It stops and asks first.
Write the day to memory, mark tasks done or blocked, leave notes for tomorrow.
Overnight summary: what shipped, uptime, new issues, ad numbers, anything that needs a decision.
Scheduled checks, memory upkeep, uptime pings, issue triage, draft work. No human needed.
Ship a page, pull a report, draft a contract, analyse a creative, research a decision.
Money over a set limit, public posts, anything irreversible. It stops and asks first.
Write the day to memory, mark tasks done or blocked, leave notes for tomorrow.
Not demos. This is real work that shipped.
Whole sites designed, built and deployed by the agents. This page is one of them.
Real feature work: writing code, opening pull requests, reviewing them, pushing to production.
Daily and weekly reports on spend and return, plus a read on which creatives are winning and which are worn out.
Invoices get picked up automatically and filed into the accountant's system, with a filter that ignores receipts and noise.
Agreements and letters in plain English, ready to review, so the first draft isn't a blank page.
Campaign and profile shots that look like me, without booking a photoshoot.
It handles life admin too, not just business. One example: a proper sleep and snoring analysis with fixes that helped.
A couple of hours a week forwarding invoices to the accountant
Auto-ingested and filed. Only the odd exception reaches me.
Logging in to pull numbers, then eyeballing what's tired
A written report lands on its own, winners and fatigue flagged.
Brief a freelancer, wait days, review, go back and forth
Described once, built, deployed and screenshotted the same day.
The tools are the easy part. These habits are what keep a fleet of agents useful instead of chaotic. Each one is also a mistake I've learned to avoid. This is the part worth copying.
If it matters, it gets written to a file. If it only lives in the chat, it's gone. No memory, no continuity.
Every area has a single agent responsible. No two agents fighting over the same job.
Every real task follows the same loop, so nothing quietly vanishes halfway.
A link, a commit, a file or a screenshot. No proof, not done. Never accept a word-of-mouth done.
Real money, public posts, anything irreversible: the agent stops and asks a human. An open wallet with no ceiling is a bad night waiting to happen, and one bad auto-post outlives a hundred good ones.
You get a clear status, not a stack trace or a code you have to decode.
Nobody can talk an agent into widening its own access. That rule is locked.
The AI comes from companies like Anthropic, OpenAI or Google, and you pay by usage. Set up at least two. If one goes down or your credit runs out, the agents switch and keep working. Running on one provider is one outage away from a dead company.
Memory updated, tasks marked done or blocked, open threads written for next time.
The tools you can buy in an afternoon. The habits are the moat.
It doesn't always go smooth. Here's a real one, start to fix.
The billing on the main AI provider ran out overnight.
Every backup was on the same account, so they died together.
Nothing moved until it was fixed. One point of failure took the lot.
Now the chain crosses providers and accounts. One outage can't stop it.
The billing on the main AI provider ran out overnight.
Every backup was on the same account, so they died together.
Nothing moved until it was fixed. One point of failure took the lot.
Now the chain crosses providers and accounts. One outage can't stop it.
The lesson underneath it: any single point of failure will find you eventually. Spread the risk before it costs you, not after.
You don't need to build all of this at once. Nobody did. One agent that remembers and ships beats a fleet you never finish setting up. Here's a sane order.
Start on Telegram. It has the simplest setup of the chat apps, so you'll be messaging your first agent fastest.
You don't run a software company? Doesn't matter. If you run an agency or a shop, try one of these on day one:
Real numbers, not a shrug. One agent doing light daily work is roughly 30 to 150 euro a month in AI usage. My full setup, with several agents shipping all day, runs from a few hundred to a couple of thousand a month, depending on how hard I push it. Light use is cheap. Heavy, all-day use across several agents is where it climbs.
You also need a computer that stays on all day. A Mac mini (about 600 to 700 euro new) is plenty. To start, an old laptop you already have works fine. It's a one-off, not a monthly bill. Start small, let the value pull you up, and add agents only when the work is really there.
The stuff a first-timer needs to know before starting.
One agent doing light daily work is roughly 30 to 150 euro a month in AI usage. My full setup, with several agents shipping all day, runs from a few hundred to a couple of thousand a month, depending on how hard I push it. Plus a one-off computer to run it on.
A computer that stays on, a Telegram account, and an account with one AI company (Anthropic, OpenAI or Google) with a payment card on file. Set up two providers if you can.
An afternoon to a weekend to get one agent up and messaging you. It's tinkering, not a full project.
No. You do paste a few commands into a terminal during setup, and the docs walk you through each one. After that you just chat.
Telegram. It has the simplest setup, so you'll be talking to your first agent fastest. WhatsApp and Slack can come later.
A plain text or markdown file the agent reads and writes. That's the whole trick: instead of forgetting when the chat scrolls away, it writes things down and reads them back.
Two places: written rules the agent follows (for example, always ask before spending money or posting in public), and a spending cap you set on the provider account itself.
The real risks are an agent sending something to a client, posting in public, or spending money by mistake. The fix is the approval rule above: anything that touches money, the public, or is hard to undo stops and asks you first.
Your files, notes and keys stay on your own computer. The AI provider only sees what you send it in a message, the same as when you use ChatGPT.
Yes, free. I do 30 minute calls with founders, no pitch and no charge. Details at the bottom of this page.
For an agency or a shop: a morning summary of yesterday's orders, drafting replies to a handful of emails, or watching a supplier page and flagging price changes.
Honestly, a few weekends to get going, and now a couple of hours a week to keep it healthy. It compounds: the more the memory and rules mature, the less it needs me.
It pauses and picks up where it left off when things come back. Nothing is lost, because the work and memory are written to files.
An open-source project maintained by its community, not a product from one company. You can read the whole thing and run it yourself. Links are up under 'What OpenClaw is'.