Topic overview

Understanding and using Claude right

Claude is the AI made by Anthropic: a language model and the apps that go with it, in the browser, in the apps and on desktop. My AI employees do not live inside Claude Projects; they live in working folders on my own computer. Their knowledge, rules and Skills are normal files. Claude Code can work with them, but I can also switch the same employee to Codex or an open model. Getting started with Claude is free, and the Pro plan costs 20 dollars a month.

What is Claude?

Claude is Anthropic’s AI model and, at the same time, the app you work with it in: in the browser, in the apps and on desktop, in plain language and without programming skills. For building an AI employee, three building blocks matter. Claude Projects are one possible entry point, but they are not where my own workforce lives.

Files and folders

Every employee has a dedicated working folder on my computer. The personnel file, rules, knowledge and feedback live there as normal files that I control.

Skills

A Skill is a work instruction you write once and that applies from then on. That turns ways of working into infrastructure instead of a prompt you retype every time.

Claude Code and Cowork

Two ways Claude works independently in your files and systems: Claude Code in the terminal with maximum control, Claude Cowork without a terminal for office and knowledge work. Both are included in the Pro plan. According to Anthropic, Cowork and chat have been gradually merging into one Claude since September 16, 2026, and after the switch you no longer need a separate Cowork mode.

What Claude costs: Free for 0 dollars, Pro for 20 dollars a month, Max for 100 or 200 dollars, Team from 25 dollars per person. All plans in one table and which one you really need: Claude pricing and plans explained.

Why my setup is not tied to Claude

My entire AI workforce lives in local working folders: fourteen employees, from accounting to content, each with their own job, personnel file and knowledge. That is an architecture decision. Because the question that changes your day-to-day is not which model leads the benchmarks. It is: can I turn this AI into an employee that knows my business and delivers every week?

That takes three things. First, a place for permanent knowledge: files and folders on my own computer, not a knowledge store owned by one provider. Second, definable ways of working: with Skills I write work instructions once, and after that they are infrastructure. Third, a tool that can work directly with those files. Today I often use Claude Code for that. Because the role lives in the folder, I can switch to Codex or an open model for the same employee.

I’m a developer and haven’t written a single line of code myself in 1.5 years. What I do instead: hire, onboard and manage employees, just digital ones. On this page you’ll find all my Claude content in one place, from the price comparison to Projects and Skills to making sense of Claude Cowork. If you don’t know the principle behind it yet, start with the fundamentals page Hire an AI employee.

The articles

33 matching articles

Frequently asked questions about Claude

How much does Claude cost?

There is a free entry point. The Pro plan costs 20 dollars a month and includes Claude Code and Claude Cowork, the Max tiers cost 100 and 200 dollars (as of August 2026). For building your first AI employee, Pro is enough. All details: Claude costs and plans at a glance.

Can I use Claude in German?

Yes, completely. You write in German, Claude answers in German, and instructions, Projects and Skills work in German too. I even run Claude Code entirely with German sentences, not with commands.

Do I need programming skills?

No. For your first AI employee, create a working folder with its role, rules and knowledge, then run the onboarding in plain language. You can use Claude Code, Codex or a suitable open model for that. The process is described in Hiring an AI employee.

What is the difference between Claude, Claude Code and Claude Cowork?

Claude is the chat app with Projects and Skills. Claude Code and Claude Cowork are two ways Claude works independently in your files and systems: Code in the terminal with maximum control, Cowork without a terminal for office and knowledge work. According to Anthropic, Cowork and chat have been gradually merging into one Claude since September 16, 2026: after that you simply describe your task in the conversation, without picking a mode first. Claude Code stays separate. My own employees live in local working folders, however, so they are not tied to Claude. The full picture: Claude Cowork: what it can do and who it is for.

Is Claude better than ChatGPT?

I don't answer the benchmark question, it doesn't change your day-to-day. What matters to me is the architecture: permanent knowledge in local files, work instructions as Skills, and a direct route into my systems. I currently use Claude Code often, but the same folders can also run with Codex or open models. The full reasoning is covered in Claude instead of ChatGPT. And if ChatGPT is enough for you today: don't switch because of a blog article.

Don’t operate Claude. Manage it.

In the community you hire your first AI employee: load a ready-made package, hold the onboarding conversation, first result after about an hour.

Join the community