AI Coding for Makers
and Solopreneurs
If you can describe it, you can build it.
A tool-agnostic companion to the course. Built to remain useful for years, not just for the current version of any model or agent.
About the book
A companion, not an extract
This book exists in parallel to the video course, but it is not a direct extract of it. The two cover the same territory — how to use AI coding assistants to go from idea to working software — but they emphasise different things.
The course shows you the work in motion: every prompt, every response, every dead end and correction, recorded against a specific set of tools at a specific moment in time. The book steps back. It puts the emphasis on the concepts and work practices that are tool- and model-agnostic: how to frame a problem, how to choose the right level of delegation, how to catch the ways AI output goes wrong, and how to keep your own judgment sharp as the tools get more capable.
That emphasis is deliberate. Model names, tool versions, and API prices change every few months. The book quarantines all of that into dated sidebars and appendices, so the main chapters are written to be read years from now. If you are reading this a year after it was printed, the chapters still hold; you only need to check the resources page for the current tool set.
Where the course explains each build and walks you through the key steps, the book captures the method behind them. If you learn better by reading before you build, or want a reference you can return to long after the videos are done, that is what the book is for.
What you will build
Four projects. Each one bigger than the last.
This is a book you build along with, not just read. Each part ends with a real tool, something you could use — not a tutorial exercise with the interesting parts removed.
A calculator in a browser
An interactive analyser for a first-order RC filter. Enter resistance and capacitance, and it plots the frequency response and marks the cut-off. A single self-contained HTML file, built with nothing more than a chat-based AI assistant in your browser — no editor, no terminal, no installation.
A serial data plotter
Point it at an Arduino or any microcontroller sending values over a serial connection, and it plots several variables live. This is where you experience the full development workflow end to end: brainstorm, specify, build, test, refine, document, and ship.
A datasheet question-and-answer tool
Give it a PDF datasheet and ask it questions in plain English. You get cited answers back. The first build where a language model runs inside the finished tool at run time — a practical introduction to retrieval-augmented generation (RAG).
A resource booking system
The capstone: a complete multi-user application that lets a group share and book equipment or facilities. You meet every concern that separates a personal script from an application other people rely on — multiple users, a database, external services, background work, and multi-tenancy.
What you will need
A short list
- A computer. Windows, Mac, or Linux. If it runs a browser and a code editor, it is enough.
- A code editor. Free, cross-platform, and used throughout the hands-on chapters.
- An AI coding assistant. The tool that sits between you and the model, reading your files and applying changes.
- Access to a large language model. Through a cloud service or running locally. Every build can be completed with affordable model access.
- An internet connection for cloud models. Local models do not even need that.
No specialised hardware. No paid licences before you have decided this is for you.
What you will not need
Just as clear
- You do not need to be a programmer. Some background helps you judge what the AI produces, but it is not a gate.
- You do not need fluency in any particular language. The builds use Python and JavaScript because they are practical. You develop the ability to read and guide code as you go.
- You do not need prior experience with AI tools. This book starts at the beginning.
- You do not need expensive hardware or subscriptions. Every build can be completed with affordable model access.
What you do need is a tolerance for ambiguity. AI-assisted development is not a deterministic process. The workflow this book teaches is built around that reality.
Table of contents
Five parts, four builds, one workflow
The book is in five parts. Part I covers how AI-assisted coding works. Part II is the development workflow, stage by stage. Part III is about applications that use a language model at run time. Part IV is the capstone. Part V is the durable skills.
Introduction
- 00 Introduction — Why I wrote this bookclick to see sample chapter
Part I — How AI-Assisted Coding Works
- 01 What AI-assisted coding is
- 02 The five levels of delegation
- 03 Knowing your level
- 04 Framing the problem
- 05 Failure modes
- 06 Build: a browser calculator
Part II — The Development Workflow
- 07 Brainstorming
- 08 Specification
- 09 Implementation
- 10 Testing
- 11 Iteration
- 12 Documentation
- 13 Deploying
- 14 The business layer
- 16 Build: a serial data plotter
Part III — A Language Model Inside the Tool
- 17 When to put an LLM at runtime
- 18 API basics
- 19 Retrieval-augmented generation
- 20 Preparing documents
- 21 Cost, latency, and failure
- 22 Build: a datasheet Q&A tool
Part IV — A Multi-User Application
- 23 Multi-user design
- 24 Database and ORM
- 25 Multi-file with an agent
- 26 External APIs and background jobs
- 27 Finishing and shipping
- 28 Designing for multiple users
- 29 Build: a resource booking system
Part V — Durable Skills
- — The parts of this craft that outlast any tool
Appendices
- I1 Toolscape — current editors, assistants, and models
- A1 RAG alternatives
- A2 Being a centaurclick to see sample chapter
Availability
Not yet on sale
Ebook — pending
The book is finished and in its final production stages. Publication is pending. When it ships, the ebook will be available directly from Tech Explorations.
Expected: July/August 2026
Print — coming later
A print edition will be available from Elektor at a later date. Details will be announced here when the print run is scheduled.
Via Elektor — date TBA
Want to know the moment it is available? Join the email list — you will get a notification when the book ships, and nothing else in between.
Join the email list