Thoughts • AI and engineering • • 4 min read

AGENTSPEK Is Live on Amazon

I wrote a book about coding with AI using AI to write it. Now it is on Amazon. What building it was actually like, and why I think this is only the beginning.

AGENTSPEK Is Live on Amazon

The book is out.

AGENTSPEK: A Beginner's Companion to the AI Frontier is now available on Amazon, on Kindle and in paperback. You can also start reading here for free, beginning with Chapter 1. Some chapters are posted in full and the rest as excerpts, and the whole book is on Amazon.

I want to tell you what this was actually like to build.


How It Started

I had been writing the AI Development Revolution series here since July 2025. Seven long essays tracking what it felt like to work at machine speed, with agent mode as a daily development partner, watching the shape of software creation change in real time.

At some point I realized this was a book, more than the posts stacked up. Something with a spine and a cover and a through-line that takes a person from wherever they are now to somewhere new.

So I started writing one.


The Recursion

I wrote a book about coding with AI using AI to write it, and that still makes me smile. Claude in agent mode, mostly. I would talk through a chapter's structure out loud, then write. I would get stuck and talk to the AI about where it was stuck. The AI would surface things I had not quite articulated yet.

It felt like having a very fast, very patient editor who had read everything and could keep all the threads in the air while I found the next sentence.

The voice in AGENTSPEK is mine. Every idea in it came from living this work. But getting those ideas onto the page, staying unstuck and moving forward, is exactly what the book is about, so I was doing the thing while I wrote about it.

I do not think I could have understood agent-mode development from the outside. You can feel the gear shift once you are in it, and the book is my best attempt at a translation.


What Is in It

Eighteen chapters. About 57,000 words. It starts at the very beginning, what is an LLM, what is a token, why does any of this matter, and ends somewhere near the edge of what is coming next.

The middle is where I spent the most time. The chapters on agent mode, on prompting as a skill, on building a working mental model of how these systems think, and on what changes in your development practice once you start treating the AI as a collaborator.

It is a beginner's companion. I wrote it for my past self, the version of me who showed up to this in 2025 with no map. I tried to hand him the map I eventually found.


Why Amazon Too

I published it here first. A good part of it is free to read on the book page, some chapters in full and the rest as excerpts.

But people asked about a physical copy. And there is something about holding a book in your hands that changes how you read it. The paperback is real. I held the proof copy and felt something I did not expect: this is a finished thing.

The Kindle version is the cheapest entry point if you just want to read it outside the browser. The paperback is for the kind of person who annotates margins and goes back.


What Comes Next

The world this book describes is already moving. Agent mode in 2026 does not look like it did in 2025, the models are faster and the context windows are vast, and the things that felt like edge cases are now standard workflows.

I am watching this carefully. At some point there will be a second edition, or a sequel, or both. I am not sure what shape it takes yet.

What I do know is that this is the most complete thing I have made, a full arc, start to finish, published and in the world, and that is not nothing.


If you have been reading this site for a while and the book sounds like something you want to read properly, the Kindle edition is the easy way in. If you want something to hold, the paperback is there. Either way, thank you for being here.

Joshua