Before any step in this book makes sense, you need two things: a place to write, and something to build with. You will not type code by hand, so that something is an AI agent. This chapter sets both up on the computer you already own, and leaves you a folder ready for the spec you write next.
Your own computer is enough1.1.1
Your computer already runs Windows, macOS, or Linux. That is its operating system, the ground floor everything else installs onto, and any of the three builds everything in this book.
Any laptop from the last few years is enough: 8 GB of memory works, 16 GB is comfortable. Buy nothing and switch nothing, you start from what you have.
The agent matters more than the editor1.1.2
The one thing you cannot skip is an AI coding agent: the program that actually writes and changes your code. Since you never type code by hand, the agent is the engine this whole book runs on.
Two things decide how good it is: the agent itself, and the model powering it, the AI brain it thinks with. Keep an eye on both. A sharp agent on a weak model, or the reverse, will let you down.
Pick where you work1.1.3
Where you and the agent work together is your choice, and it matters far less than the agent itself.
- More technical, or want full control? Install VS Code, a free editor from Microsoft, and run your agent inside it.
- Want the simplest path? Use an agent-first tool like Claude Code, Codex, Cursor, or OpenCode, where the agent is the whole interface.
New options appear all the time. Ask your agent or search for the current best, then pick the one you feel comfortable in. What matters is the agent and its model, not the shell around them.
Never lock into one model1.1.4
Your agent runs on a model, and most agents let you swap that model out. Two camps are worth knowing:
- Frontier models, like Claude, GPT, Gemini, and Grok, are the most capable. They are closed, run by the big labs, and best for hard reasoning and tricky code.
- Open-source models, like Llama, DeepSeek, Qwen, and GLM, you can run cheaply or host yourself, and they are closing the gap fast.
Which model leads changes every few weeks, so no ranking you read today stays true for long. Do not trust last year's winner: check a live leaderboard like LMArena or Artificial Analysis when the choice matters.
The move is to stay loose. Pick an agent that lets you switch models, and re-check every few months. That way you are never stuck with one vendor, and you always ride the current best.
Hint: OpenRouter gives you most models through one account, one bill, and one interface, so you switch between them without signing up with each vendor. Open-source models you can also run on your own machine, but that takes serious hardware to run a capable one well.
Make a folder, and a home for your spec1.1.5
Create one new folder on your computer for this project; it will hold everything you build. Inside it, add a folder named specs for your planning notes. That is your whole workspace today.
The full project layout waits until you know your app's pieces. A specs folder is all you need to start writing, which is the very next thing you do.
Set it all up in one pass1.1.6
This prompt has your agent recommend the right tools for you and walk you through the whole setup:
Act as a patient senior engineer setting someone up to
build software with AI for the first time. Based on my
computer and how technical I am, recommend an AI coding
agent and where to run it: a plain editor like VS Code, or
an agent-first tool. Then walk me, step by step, through
installing it, creating a project folder with a folder
named specs inside, and checking it all works.
My computer and experience:
Do this now: set up your agent and editor, create your project folder with a specs folder inside, and open it once so you have seen your workspace.
