TL;DR: The hard part of a book comes before the writing: getting the raw material out of your head and onto a page in a form a writer can work with in my ghostwriting process. AI handles that stage surprisingly well when you use it right. You talk the book into existence, and the machine organizes the talk into usable material.
I like this use of AI more than any other, because it gets people’s own material out of their heads and leaves the thinking to them. I use AI every day as a digital assistant for transcripts, session summaries and first-pass outlines, and I still do the writing. The same approach works for an author on their own, as long as you keep the average prose AI produces by default away from your raw material.
The bottleneck nobody names
Authors who hire a ghostwriter or who try to write a book themselves both hit the same wall, and it’s not the writing.
The wall is that the book exists in your head in pieces. Scattered memories. Half-formed ideas. Lessons learned the hard way. Opinions you’ve never put into clear words, and stories you’ve told dozens of times but never written down. Until that material gets out of your head and onto a page, nobody can do anything with it.
Not your writer, not you, not the editor, not the publisher. The material has to exist outside your head before the book can be built from it. For more, see using AI for research without getting burned and isn’t using a ghostwriter cheating?
Most authors underestimate this stage and assume the writing is the work. The writing is twenty percent of the work. Sixty percent is getting the raw material out of your head. The remaining twenty is editorial shaping. The bottleneck on most book projects is the first stage. Used the right way, that’s the stage AI handles better than any tool ever available to authors.
Can you talk your book into existence with AI?
From the podcast
Martin Ricketts argues that the friction of typing is itself the obstacle, and that removing it is worth deliberate practice, on Leaders and Their Stories:
One of the best ways to lower friction in your technology is using voice typing. Now, voice typing you use for lots of different things.He went as far as studying acting exercises to enunciate better, on the grounds that the return on it was worth the effort.
The right way is to talk. Most people are far better at talking through their thoughts than at writing them down. A speaker can hold a complex idea in mind while a sentence runs. Interrupt himself with the better version of the point. Pause and circle back. Use the tones and gestures that carry meaning before sentences do. On paper, all of that gets stripped out and you’re forced to produce final-form sentences, and that’s why writers stall.
Speech sidesteps the stall because you don’t have to produce final-form anything when you talk. You just say what you think. An hour of a client rambling tells me more than a polished paragraph they sweated over for a week, because the ramble has their voice in it.
Talk into a voice recorder, your phone, or any of the dictation tools that exist. Talk for thirty minutes about one piece of the book. Then transcribe what you said using one of the cheap or free transcription services available, or paste the recording into an AI tool that handles transcription. What comes out is a messy, rambling, redundant version of what you know about the topic. That mess is gold, because it contains your material in your own voice that no other process can produce.
Where is AI worth using in drafting?
The mess that comes out of a transcription is unusable as it stands. Sentences are incomplete. Topics overlap. Ideas double back on themselves. Tangents go nowhere. This is exactly the kind of mechanical organizational work AI handles well. Drop the raw transcript into the model with a clear prompt. Organize this into topics. Preserve the speaker’s specific words and phrases. Don’t paraphrase. Flag anything that seems unclear or contradictory. The machine returns a structured version of the mess that’s now usable as source material for the actual writing.
Don’t let the machine paraphrase. Most authors who use AI for this go wrong right here: they let it clean up the transcript, and the cleanup smooths away the phrasings that carry the voice. The machine turns “I always tell people this is the trap” into “this represents a common pitfall,” and the voice is gone before the writing starts. That drives me nuts, because the author rarely notices what they’ve lost.
The instruction has to be explicit: preserve the speaker’s words, don’t improve the prose, flag confusion but don’t solve it.
Run that prompt and the output is a structured raw material file that contains your actual voice waiting to be shaped into chapters. I’ve written elsewhere about why AI prose is structurally shallow, and the shallowness comes from exactly the paraphrasing instinct the machine defaults to. The first move is to turn it off.
Prompt yourself, then prompt the machine
You also need to know what to talk about. The fix is to prompt yourself. Sit down with a list of questions, generated by you or by AI from your topic, and answer them out loud one by one. Talk about the worst project you ever ran, the lesson that changed your career, the client who taught you something, the moment you knew you were wrong about something important. Each prompt produces five to thirty minutes of voice material, and the prompts draw out the stories and arguments the book needs.
AI can generate the question list well, once you’ve given it the topic and the audience.
A useful prompt is something like “generate twenty interview questions for a memoir about [topic], focused on specific moments, decisions, and turning points instead of general reflections.” The list comes back as a working interview script. You answer them out loud over the course of a week, an hour a day. By the end, you have ten hours of transcribed voice material covering the territory of the book in your own words.
Answering out loud feels awkward for the first few sessions, so push through it. The stories you’d never bother to type are the ones that make a book sound like a person wrote it, and no machine can invent them for you.
The writer or you, depending on the engagement, now has source material that’s usable. The Book Discovery Intensive runs a version of this process formally, where the interviews and material extraction happen in a structured engagement before any larger writing commitment.
What to do with the material once it exists
Once the raw material is in a structured file in your own voice, several paths open.
A ghostwriter on a full or AI-assisted engagement now has source material that lets them write quickly because the substance is already there in your words. Book coaches can work with you to shape the material into a manuscript while you keep doing the writing. DIY authors have the raw foundation to build chapters from directly, and the chapters will sound like the author because they’re built on material that already sounds like the author.
The savings in time and money are real on every path, because the bottleneck has been cleared. The author who has talked their book into existence and organized the transcripts can move through the writing process at perhaps three times the speed of the author who’s still figuring out what the book is about. I think that’s the single biggest practical benefit of AI on a book project, and the hype crowd never mentions it, because it doesn’t involve the machine writing anything.
What rules keep AI-assisted drafting from going wrong?
Three rules keep this process honest. First, preserve your actual words at every step. The transcription captures what you said. Organization preserves the phrasings. Each writing step builds on the phrasings instead of replacing them. Any step that smooths your voice out of the material has just damaged the source. Second, verify the AI’s organization against your recordings. Did the machine drop something? Did it group two unrelated things together? Could it have introduced a claim you didn’t make?
The verification is fast and catches the errors before they propagate. Third, never let the machine generate raw material from nothing. The output of “write about [topic]” is the average. The output of “organize what I said about [topic]” is your material, and only that second prompt gives you anything worth using.
Get those three rules right and AI becomes the most useful tool ever invented for the front end of a book project. Get them wrong and you’ll spend a month building a source file that smells like AI and drags the book down. It frustrates me to watch authors do that, because they had the real material in their own words the whole time and let a machine sand it off. Use the machine to organize your work, and keep the writing for yourself or for the person you hired.
