Five digital colleagues: the analyst, the project lead, the office manager, sales and the bookkeeper. For each colleague, what they do on their own, day and night, and how they help when I need them. Below: one shared memory, and the rule that they ask me when in doubt.
My AI colleagues at a glance. Orange happens on its own, blue is what they do when I need them.

It is a team you will never see sitting in the office: five AI colleagues, each with their own tasks. Part of their work happens on its own, while I sleep, sit in a meeting or am busy with something else. With the rest, they help as soon as I need them.

Some people call a setup like this an AI OS or a Claude OS: an operating system for your business. Just as Windows is the layer between you and your computer, this sits between you and your business. You ask for something in plain language, and underneath, the system searches, connects and processes the rest. It is not a package you buy, and not off-the-shelf software you have to bend your way of working to. You build it around AI the way your business works and the way your customers want it: what it knows about your business, which systems it can use, what it can do and what happens on its own.

I am building mine step by step. Today it counts 35 skills, a shared memory and a handful of tasks that run every night, every morning or every minute. A technical diagram of that means little to most people. So I would rather introduce you to the team.

What does a team like this need?

An AI team is only as good as what you give it. There are four building blocks, and they build on each other, in this order:

  • Context: what it already knows. Who we are, how we write, which customers and projects we have, which agreements we follow. Without context, Claude answers like a stranger you just met.
  • Connections: which systems it can use. Email, calendar, projects, time tracking, accounting. Without connections, you keep copying and pasting.
  • Skills: what it can do. Fixed ways of working that you write down once, so Claude carries them out the same way every time. Drafting a quote, scheduling a meeting, preparing the monthly invoices.
  • Rhythm: what happens on its own. Tasks that run at a set moment, even when your laptop is closed.

For a business, I add two more: a memory the whole team shares, and rules that are enforced, so nothing goes wrong. More on that below.

Meet the team

My 35 skills naturally fall into a few roles. Each colleague does part of the work on their own, and helps with the rest when I need them. The examples come from our own systems, but the principle works just as well with other software.

The analyst

Every week they keep an eye on our competitors: which articles they publish and how the message on their website changes.
When I need them they build our reports: what sales activity there was over a chosen period, which hours have not been invoiced yet, and the job costing per project. How many hours went into it compared to the budget in the quote?

The project lead

24/7 they process everything that comes in. Every email, every meeting report and every phone call is linked to the right customer and the right project, split into topics and turned into a proposed task. Three times a day, they update the whole team on the status of each project, me included.
When I need them they tell me where a project stands or what was agreed with a customer. They look it up in emails, meeting reports and phone calls at once, so I don't need to remember where it was. They also set up new projects, from planning to time tracking, and ask customers for feedback on open items in one clear email.

The office manager

When I need them they plan my day from my calendar and task list, tell me which customer I still need to update, and prepare meetings with the right title, location and travel time. They write customer emails in our tone, as a draft that I send myself.

The office manager only works on request. Not every colleague needs to be working all the time. That is exactly the point: for each task, you decide what may happen on its own and where you give the go-ahead yourself.

Sales

Every morning they follow up the open sales opportunities: does every opportunity have a next step, and is nothing missing anywhere? They suggest what needs to happen, but change nothing themselves.
When I need them they set up a new opportunity in one go after a first conversation, from company and contact to the first follow-up task. They also write our quotes. And for a campaign, they research every prospect: what the company does, what was in the news recently, and based on that they write a personal first email and a LinkedIn message, in that customer's language.

The bookkeeper

Every afternoon they forward the purchase invoices that don't come in via Peppol to our accounting software.
When I need them they draw up invoices from the tracked hours, and check for fixed-price projects that no instalment invoice was forgotten. For the VAT return, they check every quarter that each payment has an invoice, that sales invoices and credit notes add up, and that salaries, social security and payroll tax have been paid. Anything missing, they look up across all our mailboxes. Only when everything adds up does the return go to our flesh-and-blood accountant. And every month they prepare the payroll overview for our payroll provider, with leave, sickness and remote work per colleague.

Behind these five, there are two more colleagues. A marketer writes our blog articles and website copy in our tone, in Dutch and English, and publishes them with everything that goes with it. This article is one of them: they wrote the first draft, I polished it. You can read how that works in managing your website with AI. And a networker prepares our weekly networking meeting.

One memory for the whole team

What turns separate helpers into a team is that they work from the same source. Every email, every meeting report, every phone call, every task and every project document ends up in one shared memory. Searchable, and linked to the right customer and the right project.

That changes more than you would think. A colleague who wants to know what was agreed with a customer no longer has to ask me. They ask the system, and it often knows better than I do, because it forgets nothing and tells you where it was said. How we get conversations like that into the memory automatically, you can read in the report that never came.

In doubt? Then it asks me

A team that works independently needs clear rules. In my system, there are a few we never deviate from:

Personal, or for your whole business?

Many examples you find online are personal. Someone builds an AI assistant for themselves, gives it every permission and lets it run. That is a good start, but a business needs more:

Which data an AI colleague may see and which not, you can read in not everyone needs to see everything.

That is also why I talk about colleagues, and not about an assistant. They don't just work for me, but for everyone at Sevendays. Whoever follows up a customer, starts a project or writes a quote, relies on the same AI colleagues and the same memory.

The Sevendays team together at a table during lunch on a sunny terrace.
The human team at Sevendays. The AI colleagues don't work in their place, they strengthen each of them.

I wrote earlier about the difference between AI for yourself and AI for your business in Claude for yourself, or for your whole company. This article is that idea in practice.

Are you then locked into Claude?

No. Our AI colleagues run on Claude today, but most of what they know and can do doesn't belong to Claude. It belongs to you.

That is not theory. Our system already runs models from five different providers side by side, each for what it does best: writing text, doing research or transcribing conversations.

Not everything moves over one to one, but what matters stays yours: your ways of working, your rules and your data. The model underneath is replaceable, and that is how it should be.

How do you get started?

Not with 35 skills. My system grew one task at a time. Start with one question: what did you do three times this week, what felt like copying and pasting, or which task made you think "I really don't want to do this this way ever again"? That is your first skill.

Then stick to the order: context first, then connections, then skills, and only at the end what may run on its own. A task that runs every night without Claude knowing your business mostly creates work to fix.

And expect a small dip. The first weeks you are slower, because you are explaining things you used to just do yourself. After that it turns around: what you explain well once, you never have to explain again.

Want to know which colleagues your team needs first? At Sevendays we build this for other businesses too, connected to the systems you already use. Feel free to ask your question below.