In Part 1 of this series, I described how I accidentally gave myself five weeks to write, edit, and publish my first book — and why I turned that constraint into an experiment using AI as scaffolding rather than a shortcut. In Part 2, I walked through how editing became the most demanding phase of the project, and how using different AI tools for structure, clarity, and line editing made judgment sustainable without replacing it. This phase picks up where that work ended — when the words were done, but the book wasn’t.

Introduction

After writing and editing, I assumed publishing would be the easy part.

The thinking was done. The words were there. How hard could it be to turn a finished manuscript into a book?

That assumption was wrong — in a very different way than the others.

Writing and editing are creative problems. Publishing is an operational one. And that distinction mattered more than I expected.

If you want to catch up on how the writing and editing came together, the first two parts of this series are a good place to start.

Two paths to the same book

Publishing The Doodle Principle meant producing two different artifacts from the same manuscript:

• A Kindle ebook, created using Kindle Create

• A print-ready PDF, built in Microsoft Word for the physical book

On paper, this sounded straightforward.

In practice, they exposed two different kinds of friction — and two different limits of AI assistance.

Kindle Create: when control becomes the problem

Kindle Create was the most frustrating part of the entire project.

Not because it’s a bad tool — but because I kept trying to use it the wrong way.

Coming from a program management and documentation background, I’m used to controlling layout precisely. Fonts. Spacing. Line breaks. Page flow.

That instinct worked against me here.

Kindle ebooks are reflowable. The reader’s device, font size, and preferences determine how text appears. The author gives up a lot of control by design.

AI tried to help me troubleshoot formatting issues — but it kept answering the questions I asked, not the problem I actually had.

An experienced human would have said this immediately:

You’re trying to control something you’re not supposed to control.

Once I stopped fighting the tool and understood its constraints, things improved. But getting there took far longer than it should have — and AI never quite surfaced that big-picture insight on its own.

Publishing as an operational problem

Writing and editing are creative problems. Publishing is an operational one.

Creative problems tolerate ambiguity. You can experiment, revise intent, and change direction. Voice matters. Judgment matters. There’s room to be “mostly right” while you discover what you’re actually trying to say.

Publishing doesn’t work that way.

Publishing is about fitting content into an established system of rules and constraints — many of which exist for reasons that aren’t obvious until you violate them. Kindle ebooks are reflowable. Physical books are fixed. Margins, headers, footers, page numbers, and section breaks all have to conform to both printing requirements and reader expectations.

There’s very little room for interpretation.

Page numbers need to appear where readers expect them. Front matter (title page, credits, table of contents) follows conventions most readers never consciously notice — until something feels off. Chapters need to start cleanly. Margins aren’t aesthetic choices so much as physical necessities.

In other words, publishing isn’t about expression. It’s about compliance.

That shift mattered. The instincts that helped me while writing — experimenting freely, refining ideas as I went — often worked against me during publishing. I didn’t yet understand the system I was working inside.

AI was good at explaining how to do specific things within that system. It was much less reliable at helping me understand the system as a whole.

PDF creation in Word: precision by accumulation

Building the print-ready PDF in Microsoft Word was more successful — but also more iterative.

AI gave me accurate, step-by-step guidance for specific tasks:

• Creating section breaks

• Using lowercase Roman numerals for front matter

• Switching to Arabic numerals for the main text

• Starting chapters on new pages

• Managing headers, footers, and page numbering

The issue wasn’t correctness.

The issue was orientation.

Each answer was right — but narrow. I often discovered the next requirement only after fixing the previous one. In several cases, I realized something was off only after pulling other nonfiction books off my shelf and checking how they handled the same detail.

A human editor would have explained the entire structure up front: how front matter works as a system, why section breaks matter, and what conventions readers subconsciously expect.

AI got me there — but through iteration, not overview.

Where AI helped — and where it didn’t

AI did shine in a few important ways.

It clearly explained the differences between fiction and nonfiction formatting. It helped me understand which layout details mattered to readers and which ones didn’t. That guidance saved time and prevented some avoidable mistakes.

But publishing exposed a clear boundary.

AI can tell you how to do something.
It’s less effective at telling you why the system works the way it does — or when you’re solving the wrong problem entirely.

The cover: prompts, patience, and taste

The cover process was the most collaborative part of publishing.

ChatGPT helped refine the language of my image prompts. Producing the images took a lot of trial and error. Grok produced images that came closest to what I had in my head — after significant experimentation. DALL·E, Gemini, and other generators missed badly.

Claude was especially helpful in critique mode. It pointed out moments where the title and subtitle were competing for attention and where spacing and hierarchy could be improved. Those weren’t technical issues — they were judgment calls — and that’s where AI worked best as a second set of eyes.

The cover image for this post comes from the AI-assisted process I used to create the book’s cover.

The pattern I didn’t expect

Looking back, a clear pattern emerged.

AI was strongest when:

• The task could be decomposed

• The rules were explicit

• Iteration was cheap

It struggled when:

• The problem required a holistic understanding of the process

• The “right” answer depended on convention or taste

• The fastest solution was the simplest—telling me not to try to control something

That pattern repeated itself several times during publishing.

The lesson from publishing

If editing taught me that judgment is the real work, publishing taught me something else:

Context matters more than instructions.

AI didn’t teach me how publishing works. It helped me survive learning it.

As scaffolding, it did its job — temporary, imperfect, but enough to get the structure standing.

What comes next

The final article in this series will be practical rather than reflective.

I’ll share the actual prompts I used across writing, editing, publishing, and cover design — not as a recipe or a guarantee, but as scaffolding.

The same kind that helped me finish.

The ideas and concepts in this article are the author’s own. AI assisted with ideation and editing.

In Part 1 of this series, Using AI as scaffolding, not a shortcut, I described how I gave myself five weeks to write, edit, and publish my first book — and why I turned that constraint into an experiment.

If you’re curious how the writing itself came together, I’d start there.

What follows is where the real work began: editing.

The part I underestimated

Before I started The Doodle Principle — How AI Becomes Your Partner in Curiosity and Creativity, I assumed editing would be a linear cleanup step. Fix grammar. Tighten sentences. Maybe catch a few mistakes I missed.

That assumption was wrong.

Editing isn’t one task. It’s several fundamentally different kinds of thinking — structural coherence, factual accuracy, voice, rhythm, tone, consistency.

Trying to do all of that at once is exhausting, and it’s one of the reasons I believe first-time authors trying to do all the steps themselves stall, burn out, or never publish at all.

Without AI, my options were limited:

• Spend months rereading, revising, second-guessing, losing momentum, and getting frustrated

• Or hire a professional editor I didn’t have the budget for

Instead, I asked AI to help me answer a simple question:

What’s the right way to edit this without losing my voice or my sanity?

The answer surprised me.

Editing in passes, not all at once

Rather than one monolithic edit, AI recommended three distinct passes, each with a different purpose — and, critically, a different AI partner based on how each one tended to think.

At first, this felt excessive. Why not upload the manuscript once and be done?

Because editing isn’t a single skill.

It’s a sequence.

And mixing those skills together creates drift, overcorrection, and tone loss.

Editing, I came to realize, is a writer’s scaffolding — the temporary structure that helps ensure the author’s best work is actually visible. AI became my editing scaffolding.

Pass 1: Structural editing with ChatGPT

The first pass wasn’t about sentences at all. It was about thinking.

I used ChatGPT as a structural or developmental editor, working chapter by chapter rather than on the full manuscript at once. That decision mattered. Uploading everything at once increases the risk of stylistic drift and overgeneralization.

This pass focused on questions like:

• Does this chapter deliver on its intent?

• Are ideas introduced in the right order?

• Where does the argument wander or repeat itself?

• What assumptions am I making that aren’t explicit?

In traditional publishing, this would be called a developmental edit. With AI, it felt more like a thinking partner that never got tired of asking, “Does this actually work?”

ChatGPT consistently behaved like a generalist. It wanted to zoom out, reorganize ideas, surface assumptions, and test whether a chapter actually delivered on what it claimed. That tendency made it well suited for structural work, where breadth of reasoning mattered more than sentence-level polish.

What it didn’t do was rewrite the book. I rejected plenty of suggestions. Others I accepted not because they were perfect, but because they clarified something I was already trying to say.

This pass set the foundation. Without it, everything that followed would have been cosmetic.

Pass 2: Content and clarity checking with Gemini

Once the structure held together, I moved to clarity and accuracy.

This is where Gemini came in.

I used it as a content and clarity editor, focusing on:

• Explanations that felt muddy or overly compressed

• Places where I assumed too much reader knowledge

• Factual consistency and light fact-checking

• Sentences that made sense to me but might not land for others

This wasn’t about style. It was about comprehension.

Gemini had a tendency to pause on ambiguity. It regularly flagged places where something was technically correct but open to misinterpretation, or where a reader could reasonably challenge a claim based on wording alone. That made it particularly effective for clarity checks and factual accuracy, even when it suggested very few changes.

In practice, many chapters came back nearly clean. But when Gemini did raise a concern, it was usually worth addressing. In a few cases, those flags sent me back to my structural editor to rework tone or framing before moving forward.

Again, this was done chapter by chapter, not all at once.

The goal wasn’t perfection. It was clarity and confidence.

Pass 3: Line editing with Claude

Only after the structure and clarity were solid did I move to line editing.

This is where Claude excelled.

Claude became my sentence-level editor, focused on:

• Rhythm and cadence

• Word choice

• Reducing unintentional repetition

• Making sentences read cleanly and naturally

Claude seemed especially attuned to cohesion across longer passages. It noticed when clauses piled up, when rhythm flattened, or when a paragraph subtly drifted out of sync with the surrounding text. That made it particularly effective for line editing, where consistency of voice and flow mattered most.

This is the pass most people think of when they hear “editing,” but doing it earlier would have been a mistake. Polishing sentences before you know they belong is wasted effort.

Claude didn’t change my voice. It sharpened it.

Reading the edited chapters back was the first time I felt real confidence in the manuscript — not because it was perfect, but because it finally sounded like me on a good day.

The tedious part (and why it was still worth it)

This process wasn’t magical or instant.

It meant:

• Breaking the manuscript into individual chapter files

• Copying text between tools

• Reviewing edits carefully

• Accepting some changes and rejecting others

• Revisiting sections I thought I was done with

It was slow. At times, tedious. I still felt frustrated along the way.

But compared to months of solo editing — or never publishing at all — it was a trade I’d make again without hesitation.

What surprised me most

The biggest surprise wasn’t speed. It took nearly as long to edit the book as it did to write the first draft and begin the formal editing process.

It was confidence.

By the time I finished these passes, I enjoyed reading my own work. I trusted it. I could see its flaws clearly — and that made them less intimidating, not more.

AI didn’t eliminate judgment. It required more of it.

But it made judgment sustainable.

A quick clarification

I didn’t use one AI for everything on purpose.

Each model leaned naturally toward a different kind of thinking — generalist reasoning, detail sensitivity, and long-form cohesion. Treating them as interchangeable would have flattened the result. Treating them as specialists preserved both quality and voice.

Editing didn’t save me the most time because it was faster.

It saved me the most time because it made finishing possible.

What comes next

I assumed publishing would be the easy part.

I was wrong again.

In Part 3, I’ll describe why formatting, tooling, and distribution turned out to be the most frustrating phase — and the one where AI helped the least.

That’s where this experiment took its sharpest turn.

The ideas and concepts in this article are the author’s own. AI assisted with ideation and editing.

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:

1. Creation (this article)

2. Editing

3. Publishing

4. 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.

Get the book Online: https://books2read.com/DoodlePrinciple

The Doodle Principle is the belief that AI becomes most powerful when paired with human curiosity, creativity, and judgment. You supply the spark; AI supplies the scaffolding. Together, they turn imagination into action—creating what neither could create alone.

The Doodle Principle is built on five simple ideas: Fallacy, Anatomy, Doodles, Evolution, and Scaffolding — FADES. These concepts explain what AI really is, how it thinks, and how you can work with it. Once these pieces click, something shifts. You RISE. You become Ready, Inspired, Seeking, and Exploring — using AI the way it was meant to be used: as a partner in your curiosity and creativity.

The Doodle Principle centers on individuals, but the same ideas scale beautifully to teams and organizations. Think of this as the starting point for expanding these concepts into a practical approach for adopting AI across teams and businesses.

Curiosity is all you need to begin. Open the book, take the first step, and discover how far you can go when AI becomes your partner in creativity, clarity, and exploration. The spark is yours — let’s build something extraordinary together.

Real-world illustrations of The Doodle Principle will be told using Doodle Loops. Doodle Loops are simple rhythms for making sense of the world with AI: Observe → Wonder → Explore → Understand. You notice something, get curious about it, explore it with AI, and end up understanding it in a new way. It’s the bridge between everyday moments and the creative possibilities of AI.