How I Accidentally Wrote My First Book with AI
Part 1: Using AI as scaffolding, not a shortcut
Introduction
I didn’t intentionally plan to write my first book in five weeks.
I thought I was starting early, then I realized Christmas was only five weeks away.
It wasn’t until I began outlining what I was actually trying to do — writing, editing, formatting, and publishing a first book as a Christmas present — that the scale of the effort hit me. Hard. What I had casually penciled in as a “nice side project” quickly revealed itself as something much bigger.
That’s when I realized I needed help.
At the time, I was between clients. I had time, but not the kind of open-ended time where you can disappear into a creative project indefinitely. I also didn’t want my wife to worry that I was about to turn into a starving author chasing an uncertain outcome.
So I reframed the work.
Instead of “writing a book,” I turned it into an experiment — one with a concrete deliverable. Even if the book wasn’t perfect, I wanted to come out the other side with something tangible: a real product, warts and all, that demonstrated how AI could actually help a human create.
Once I set that goal, the constraints became very real.
A fixed deadline.
A limited budget.
And a requirement that the result be useful, not just expressive.
This series shares how that experiment played out. I’m especially curious how it compares to your own creative process — whether you write with no AI at all, minimal support, or treat AI as an active collaborator. If you’ve experimented, or deliberately avoided it, I’d love to hear why. The comment section is part of the experiment.
This series covers four phases:
Creation (this article)
Editing
Publishing
The prompts I actually used (appendix-style)
The AI fallacy
Like a lot of people, I carried a quiet fantasy about how this might work.
Best case, I’d write a few clever prompts, AI would somehow read my mind, and out would come a guaranteed bestseller — something insightful, beautifully written, and world-changing, with minimal effort on my part.
This book exists largely because I learned why that belief is wrong.
Writing The Doodle Principle — How AI Becomes Your Partner in Curiosity and Creativity still took easily 200 hours over five weeks. AI didn’t remove the work. It didn’t eliminate judgment. And it certainly didn’t replace thinking.
What it did was subtler — and far more valuable.
It reduced friction.
It absorbed frustration.
It helped me keep moving when I would normally stall.
AI didn’t make the book easy.
It made it possible.
Creation as collaboration
The ideas, metaphors, structure, and point of view behind The Doodle Principle were mine. But I didn’t develop them in isolation.
I started by sharing a rough concept, an early chapter outline, and a working title with ChatGPT. We went back and forth. I challenged suggestions. I rejected many. I accepted others — not because they were perfect, but because they helped move the thinking forward.
The title itself evolved through several iterations:
AI — Why Doodles Are Not God, David Muir Is Not the Devil, and Squirrels
The Doodle Fallacy — How AI Liberates the World’s Knowledge and Inspires Creativity
The Doodle Principle — How AI Becomes Your Partner in Curiosity and Creativity
Each version reflected a shift in emphasis — from provocation, to scope, to clarity.
To avoid turning any one tool into an echo chamber, I occasionally used Grok as an independent sounding board. Not because I trusted it more, but because I wanted friction in the process. That tension — between assistance and over-reliance — became a recurring theme throughout the project.
Writing through blocks
For most chapters, I wrote the first draft myself. When I hit a mental block — when I knew what I wanted to say but couldn’t quite land it — I’d do a full brain dump. Fragments, half-formed thoughts, raw ideas.
Then I’d ask AI to help integrate them into something coherent.
Sometimes I kept what it produced. Other times I threw it out entirely but kept the structure it revealed.
That pattern surprised me. AI wasn’t most useful as a writer. It was most useful as a mirror — reflecting back what I was trying to say, even when I hadn’t said it well yet.
The unexpected speed
The full draft came together in less than two weeks.
At the time, I felt a rush of excitement. The book felt almost finished. I was already thinking about covers, layout, and publishing platforms.
That’s when reality set in.
Writing was the easy part.
Editing would be something else entirely.
Using AI as scaffolding, not a shortcut
This series isn’t just about the process — it uses it. Not as a shortcut, but as scaffolding. If AI-assisted collaboration could help me produce a book I was proud of, it should also hold up under something smaller, more immediate, and more conversational. What you’re reading is an example of what that produces in practice.
The first draft of this article was written like a program manager wrote it—a style that’s very effective for a governance meeting. It covered all the points I wanted to make, but not in the way people like my parents would enjoy. AI helped me express myself in a more relatable style. It helped me to turn an incident report into a story with meaning.
In some ways it feels like learning to ride a bike. The balance isn’t natural yet, but I’m getting from point A to point B faster—and with fewer crashes.
AI didn’t make the book—or this article—easy. It made them possible.
What comes next
Creation was only the first phase.
I’ll publish the next part, on editing, in a few days.
Editing turned out to be the most time-consuming, mentally demanding, and revealing part of the entire project — and where AI’s strengths and limitations became impossible to ignore.
That’s where the experiment really began.
The ideas and concepts in this article are the author’s own. AI assisted with ideation and editing.