Chapter 1bBeginner10 min read

Your First Hour in the Windows Terminal (and Claude Code)

By Pascal van Steen, Founder — Ryzo

Last updated: March 2026

You have probably never opened a terminal. That is completely fine. Most people haven't. It sits somewhere on your computer, quietly waiting, and nobody ever told you what it was for or why you would want to use it.

That is about to change. The most powerful AI tools available right now — the ones that can read your files, write code, and build things for you — live inside the terminal. Not behind a login screen in a browser. Not in an app with a drag-and-drop interface. In the terminal.

This guide will walk you through your first hour. By the end, you will have navigated your computer using text commands, installed real software, and had a conversation with an AI that can see and edit files on your machine. No prior experience required.

What is a terminal?

A terminal is a text-based way to talk to your computer. Instead of clicking icons and dragging windows, you type short commands and your computer responds with text.

Think of it like texting your computer. You type a message, press Enter, and it replies. That is genuinely all it is.

Here is the most important thing to know before we start: you cannot break your computer by typing the wrong thing. The worst that will happen is you see an error message. The computer will tell you it did not understand, and you try again. There is no command you can accidentally type that will cause damage. Error messages are just the computer saying "I didn't get that."

So why does this matter now? Because the most capable AI tools — the ones that go beyond chatting and can actually do work on your behalf — run in the terminal. Learning to use a terminal is not about becoming a programmer. It is about opening a door to tools that are genuinely useful for anyone, regardless of their technical background.

Let's open that door.

Opening the terminal on Windows

Windows gives you a few options for terminals: Command Prompt (the old one), PowerShell (the modern one), and Windows Terminal (the app that makes PowerShell look good). We are going to use Windows Terminal because it is clean, modern, and supports tabs — like a browser but for terminal sessions.

If you are on Windows 11, Windows Terminal is already installed. You have two ways to open it:

  • Click the Start menu and type "Terminal", then click the result
  • Press Win + X on your keyboard (hold the Windows key, press X) and select "Terminal" from the menu that appears

If you are on Windows 10, you need to install it first. Open the Microsoft Store (search for it in the Start menu), search for "Windows Terminal", and install it. Alternatively, you can skip the installation and just use PowerShell directly — search "PowerShell" in the Start menu and open it. Everything in this guide works the same way.

Once you open the terminal, you will see a dark window with a line of text that looks something like this:

PS C:\Users\YourName>

That PS means PowerShell. C:\Users\YourName is where you currently are on your computer — your user folder. And the blinking cursor after the > is waiting for you to type something.

We will use PowerShell for everything in this guide. It is the default tab when you open Windows Terminal, so you are already in the right place.

Let's type something.

Your first commands

You are staring at a blinking cursor. Let's find out where you are.

Type this and press Enter:

pwd

You will see something like:

Path
----
C:\Users\YourName

That is your home folder. pwd stands for "print working directory" — it tells you which folder you are currently standing in. Think of the terminal like a file explorer, but instead of seeing folders as icons, you ask the computer to tell you where you are and what is around you.

Now let's see what is in this folder. Type:

ls

You will see a list that looks something like this:

    Directory: C:\Users\YourName

Mode                 LastWriteTime         Length Name
----                 -------------         ------ ----
d----          28/03/2026    09:15                Desktop
d----          27/03/2026    14:22                Documents
d----          28/03/2026    11:30                Downloads
d----          15/01/2026    08:45                Music
d----          20/02/2026    16:10                Pictures
d----          10/12/2025    12:00                Videos

Those are the same folders you see in File Explorer. The d in the Mode column means "directory" (which is just the technical word for folder). You are looking at your files — just in text form instead of icons.

Let's move into your Desktop folder. Type:

cd Desktop

Nothing dramatic happens. The prompt changes to show your new location:

PS C:\Users\YourName\Desktop>

You just moved. Let's confirm by checking where we are again:

pwd
Path
----
C:\Users\YourName\Desktop

Now let's create a folder for our project:

mkdir my-first-project
    Directory: C:\Users\YourName\Desktop

Mode                 LastWriteTime         Length Name
----                 -------------         ------ ----
d----          31/03/2026    10:00                my-first-project

A new folder just appeared on your Desktop. You can actually see it if you look — there will be a new folder icon called "my-first-project" sitting right there. You created it with five words.

Let's go inside:

cd my-first-project

And check what is in here:

ls

Nothing. An empty folder. That is expected — we just created it.

Before we move on, here is something reassuring: if you have heard that Windows terminal commands are completely different from Mac, PowerShell has you covered. The basic commands we just used — pwd, ls, cd, mkdir — work the same way on both systems. You are learning skills that transfer everywhere.

The mental model

Here is how to think about what you are doing. You are always "standing" in a folder. Every command you type happens in that folder. When you type ls, it lists what is in the folder where you are standing. When you type mkdir, it creates a new folder inside the one where you are standing.

Commands are like short sentences. They have a verb (the action) and sometimes a target (what the action applies to). cd Desktop means "change directory to Desktop." mkdir my-project means "make a directory called my-project."

Here are the commands you know so far:

CommandWhat it doesExample
pwdShows where you areC:\Users\You\Desktop
lsLists what's in the folderShows files and folders
cdMoves to a foldercd Desktop
cd ..Goes back one levelGoes up to parent folder
mkdirCreates a new foldermkdir my-project

Two more things that will make your life easier:

Tab completion. Start typing a folder name and press the Tab key. The terminal will try to finish the name for you. If you are in your home folder and type cd Desk then press Tab, it will complete to cd Desktop. This saves typing and avoids spelling mistakes.

Up arrow. Press the up arrow key to bring back the last command you typed. Press it again to go further back in your history. This is incredibly useful when you want to repeat or slightly modify something you already ran.

One more note about paths: Windows uses backslashes (\) in paths, like C:\Users\YourName\Desktop. If you are reading guides written for other systems, you might see forward slashes (/) instead. PowerShell accepts both, so do not worry about it. cd Desktop\my-project and cd Desktop/my-project both work.

Installing Node.js

Before we can install Claude Code, we need to install Node.js. Think of it like this: Claude Code is an application, and Node.js is the platform it runs on. The way a mobile app needs iOS or Android to run, Claude Code needs Node.js.

Here is what to do:

  1. Open your web browser and go to nodejs.org
  2. You will see a big green button that says "LTS" (Long Term Support) with a version number — something like 22.14.0. Click it to download the Windows Installer (.msi file)
  3. Open the downloaded file and click through the installation wizard. The default settings are fine — just keep clicking "Next" until it finishes, then click "Finish"

Now here is the most important step, and the one most people miss:

Close your terminal window completely and open a new one.

This is not optional. When you installed Node.js, it made itself available to the terminal — but only to new terminal windows. Your current window does not know Node.js exists yet. Close it, open a fresh Windows Terminal, and navigate back to your project folder:

cd ~\Desktop\my-first-project

That ~ is a shortcut that means "my home folder." So ~\Desktop\my-first-project means "from my home folder, go to Desktop, then into my-first-project."

Now let's verify Node.js is installed:

node --version

You should see something like:

v22.14.0

The exact number might be slightly different. As long as you see a version number, you are good.

If you see an error that says something like node: The term 'node' is not recognized as the name of a cmdlet, it means the terminal has not picked up the installation. The fix is almost always the same: close the terminal window, open a brand new one, and try again. Make sure you are opening a new window, not a new tab in the existing window.

Installing Claude Code

Node.js came with a tool called npm — think of it as an app store for the terminal. Instead of browsing a store and clicking "Install", you type one command and the software gets downloaded and set up for you.

Let's install Claude Code:

npm install -g @anthropic-ai/claude-code

This will take a moment. You will see some progress text scroll by. The -g flag means "install globally" — making Claude Code available from any folder on your computer, not just this one.

When it finishes, verify the installation:

claude --version

You should see a version number. That means Claude Code is installed and ready to use.

If npm is not recognized as a command, it means the terminal still hasn't picked up the Node.js installation. Close the terminal, open a new one, and try the install command again.

One more thing: you will need an Anthropic account to use Claude Code. If you do not have one, go to claude.ai and sign up. It is free to create an account. When you first run Claude Code, it will walk you through connecting your account.

Your first conversation with Claude Code

Make sure you are in the project folder. If you are not sure, run:

cd ~\Desktop\my-first-project

PowerShell also accepts forward slashes, so cd ~/Desktop/my-first-project works too. Use whichever feels natural.

Now type:

claude

Press Enter. Claude Code starts up. You will see a welcome message, some information about the version, and then a prompt waiting for your input. It looks different from the normal terminal prompt — you are now inside Claude Code's interface.

Let's start simple. Type:

What files are in this folder?

Claude will look at your project folder and tell you it is empty (because it is — we just created it). Nothing magical yet, but notice what just happened: you asked a question in plain English and the AI looked at your actual files to answer it.

Now let's do something more interesting. Type:

Create a simple HTML page that says Hello World

Claude will think for a moment, then show you the code it wants to write and ask for permission to create the file. This is the permission system — Claude Code never changes anything on your computer without asking first. You will see something like:

Create file: index.html

Press y and Enter to approve. Claude creates the file.

Now exit Claude Code for a moment — type /exit or press Ctrl+C — and check what happened:

ls
    Directory: C:\Users\YourName\Desktop\my-first-project

Mode                 LastWriteTime         Length Name
----                 -------------         ------ ----
-a---          31/03/2026    10:15            150 index.html

There it is. A real file, sitting in your project folder, created by an AI that you gave instructions to in plain English. If you go to your Desktop and open the "my-first-project" folder, you will see the file there. Double-click it and it will open in your browser showing "Hello World."

You just went from an empty folder to a working web page using a terminal and an AI.

Understanding the basics

Now that you have seen Claude Code in action, here are a few things that will help as you continue exploring.

How Claude sees your files. When you start Claude Code in a folder, it can read everything in that folder and all its subfolders. This is what makes it so useful — it is not just a chatbot you send messages to. It has context. It can see your project, understand the structure, and make informed suggestions. Start Claude Code in the folder that contains what you are working on, and it will have the full picture.

The permission system. Claude always asks before creating, modifying, or deleting files. Every time it wants to make a change, you see what the change is and press y to approve or n to reject. You are always in control.

Getting help. If you want to see what Claude Code can do, type /help inside a Claude Code session. This shows you the available commands and options. You do not need to memorize anything — the help is always there.

A practical exercise. Start Claude Code again (type claude in your terminal) and try this:

Create a simple Python script that prints the current date and time

After Claude creates the file, ask:

Explain what each line does

Claude will walk you through the code line by line, in plain English. This is one of the most powerful aspects of working with AI in the terminal — you can create something and immediately understand it. You do not need to learn a programming language to benefit from what it produces.

Exiting Claude Code. When you are done, type /exit or press Ctrl+C. You will be back in your normal terminal, and any files Claude created will still be there in your folder.

What you just learned

Take a moment to appreciate what you did in the last hour.

You opened a terminal — something most people have never done. You navigated your computer's file system using text commands. You created folders. You installed real software from the command line. You started an AI assistant that can see your files, write code, and explain what it wrote.

You went from someone who had never touched a terminal to someone who uses one. That is not a small thing.

The commands you learned — pwd, ls, cd, mkdir — are the same commands that professional developers use every single day. There is no separate "beginner" set and "real" set. You learned the real ones.

And Claude Code is just the beginning. Now that you know how to open a terminal, navigate to a folder, and run commands, you have access to an enormous ecosystem of tools that were previously invisible to you. The terminal is a doorway, and you just walked through it.

Next in the series, we will explore working with Claude Code on real projects — from organizing files to building things you actually need.