I Told the AI to Edit My Book

7-40 Challenge | Round 4, Day 22


Earlier this year, I finished my first novel — 105,000 words of a YA superhero story set in the 1990s. It needed editing. I had Claude. I figured this would be straightforward.

I said, essentially: let’s edit this.

The AI started rewriting my story. Not editing — recreating. It changed plot points. It rearranged material. It put scenes out of order and stopped tracking what had happened in previous chapters. It was hallucinating its way through my manuscript, and the output was getting further from my story with every pass.

So I stopped and changed how I talked to it.


Instead of “edit this,” I said: read this chapter. Read the chapters before it. Tell me what works and what doesn’t. Point out the parts that are heavy, the parts that don’t explain enough, the parts that slow down. Do not make any edits. Just show me the problems.

And it worked.

The AI became a sharp, tireless reader who could point out structural issues I was too close to see. I made the decisions about what to change. I did the rewriting. But I had a partner who could read my 105,000 words without fatigue and tell me where the story was dragging, where a character’s arc was inconsistent, where I was telling the reader something the scene had already shown.

That manuscript lost nearly half its weight through editing. Every cut made it better. And the AI didn’t make a single one of those cuts — I did.


The difference between the first attempt and the second was entirely in how I defined the problem. “Edit this” is not a problem statement. It’s a wish. “Read this and tell me what’s wrong without touching it” is a problem statement with boundaries, criteria, and a clear role for each party.

The AI didn’t get smarter between attempt one and attempt two. I got clearer.

Away

7-40 Challenge | Round 4, Day 22


The Light Bearer went up on KDP today.

That’s two novels published in 2026. The first one took five months from manuscript to launch. This one took longer than I wanted — I missed my own deadline, pushed through more revisions than I planned for, and learned that editorial work doesn’t care about your timeline. It takes what it takes.

But it’s away. The story is out of my hands and into the world’s.


I wrote about Parkinson’s Law four days ago and made a public commitment to ship this book by Saturday. I missed it by a day. Not because the work wasn’t done — because I wasn’t honest about how much work was left. The two-hour edit I promised myself turned into weeks of revision that made the book significantly better than what I would have shipped if I’d rushed it.

Some deadlines deserve to be missed if the work gets better for it. This was one of them.

Start Writing Something Different

7-40 Challenge | Round 4, Day 21


Years ago, I wrote a blog post about the difference between facts and story. I used an example of two people answering the same question — “how was your day?” One gave a list: did some spreadsheets, took some calls, met a new coworker, came home. The other told a story — the spreadsheets took forever because Mark kept stopping by, but Mark’s having trouble at home and it felt right to help. A new woman started today. They hit it off.

Same day. Same details. Completely different experience for the listener.

I ended that post with a line I didn’t know I was writing for myself: “If you are living a story you wouldn’t want to read, then it may be time to start writing something different.”


It took me years to take my own advice.

I kept living in bullet points. Went to work. Came home. Had ideas I didn’t act on. Wrote a few pages of stories I never finished. Knew what I was capable of but treated it like trivia instead of plot.

Then I started writing something different.


Not a blog post. Not a metaphor. I sat down and wrote a novel. Then I wrote another one. I started a daily blog and haven’t missed a day in 157 of them. I picked up a Bible illustration project that’s reached almost 9,000 people. I built a structure around seven daily habits and rode it through four rounds of forty days.

I stopped narrating a life I wasn’t living and started living one worth narrating.


The old post asked the reader a question: “How would thinking of your life in terms of story benefit you?” I don’t need to ask that anymore. I know the answer. It made me the main character instead of a bystander in my own plot.

The story I’m telling now has problems I haven’t solved, deadlines I’ve missed, fears I’m still fighting. It’s not clean. But I’d want to read it. And that’s the difference.

Deep Breath

7-40 Challenge | Round 4, Day 19


Every once in a while, you need to take a deep breath.

We had friends over tonight that we’ve known for over twenty-five years. Good people. The kind you don’t have to perform for. The kind where you sit down, the conversation starts, and three hours disappear.

Whatever I was working on today fell by the wayside. And that was exactly right.

Some nights the most productive thing you can do is stop producing and be present with people who restore you in a way that nothing else can.

My Fault

7-40 Challenge | Round 4, Day 19


I was in a business conversation today. I thought I was being clear. I gave what I believed were straightforward directives — here’s the problem, here’s what I need done, here are the actions to take.

One person on the call almost point-blank refused to accept the message.

After a lot of going around, I realized it wasn’t that my words were wrong. It was that their understanding of the problem was different from mine. The solution I was prescribing didn’t make sense because they were stopped by their own mental model of the issue — and I had never checked whether we were looking at the same thing.

That wasn’t their fault. It was mine.


Here’s what I should have done. Before I prescribed a solution, I should have started with the problem statement. Here’s the issue. Here’s what I understand about it. Here’s how I see the pieces fitting together. Does everyone in this room see it the same way?

If they did, we move forward. If they didn’t, I’d have the chance to adjust my framework before I tried to build on top of it.

Instead, I assumed everyone was already crystal clear on the problem. I skipped the foundation and went straight to the fix. And the fix made no sense to someone who was standing on different ground.


Once I walked it back — restated the problem, rebuilt the understanding, asked “is this correct?” — everyone agreed and we moved on. The solution was the same one I’d proposed at the start. It just needed the foundation underneath it.

That ten minutes of conflict resolution could have been two minutes of consensus building at the top.