Ask a model for an example to illustrate a point and it will give you one. A mid-sized company, a plausible problem, a sensible resolution.
It reads fine. It is also a composite of every case study ever written, and a reader who has read three business books recognizes the shape within two sentences.
The reason is simple and it does not go away with better prompting. Nothing that happened to you is in the training data unless somebody wrote it down, and almost nothing that happened to you was written down.
What is missing from a generated example?
The detail nobody would have chosen.
Real stories carry things that do not serve the argument. The chair was uncomfortable. It was a microwave. The brick was propping the door for smoke breaks specifically. None of those are the point, and their presence is what makes a reader believe the rest.
A generated example contains only load-bearing detail, because it was assembled to make a point. Everything in it is relevant, which in a real account never happens, and the uniform relevance is the tell.
This is why a composite feels thin even when the reader cannot say why. They are missing the noise, and the noise is the evidence.
The book on this: Family Cybersecurity is 231 pages of things that happened to specific households, which is the part no model can supply.
Why does specificity matter this much?
Because it is the only thing a reader can use to judge whether you have been there.
Claims are cheap and every book in the category makes similar ones. What separates them is whether the author can produce the particular. A number, a name, a specific afternoon. Those cannot be reasoned to. Either you were present or you were not.
I can tell you that most home networks are poorly secured. So can anybody. What I can also tell you, and what went into Family Cybersecurity, is that I drove through a suburban neighbourhood with a laptop and found 127 networks on default passwords and 43 with none in about twenty minutes.
The second version is not a better argument. It is the same argument with proof of presence attached.
The book on this: Behind the Wire could not have been generated by anything, because it came out of a journal a man wrote after he got home.
Can you prompt your way around it?
Only by supplying the story yourself, at which point the model is formatting, not generating.
That is a legitimate and useful thing to do. Give it the raw account, badly written, with the details in the wrong order, and ask it to tighten the structure. The result can be genuinely better than your draft.
What you cannot do is ask it to supply the account. Any story it produces will be a synthesis, and a synthesis presented as personal experience is a fabrication with your name on it, which is a considerably larger problem than a flat chapter.
The line is clean. Your story, its formatting: fine. Its story, your byline: never.
What about composite examples in business books?
They have a place, and it has to be declared.
Plenty of legitimate books use composites for confidentiality. A consultant who cannot name a client builds an illustrative case from several, says so, and the reader adjusts their expectations accordingly.
What fails is an undeclared composite presented with the texture of a real event. The reader assumes it happened, then finds out it did not, and every other claim in the book becomes suspect.
If you cannot use the real case, say the case is constructed. The cost of admitting it is small and the cost of being caught is the whole book.
The book on this: The Ghostwriting Advantage describes the interview process that gets these stories out, which is a conversation and not a prompt.
How do you get your own stories out?
By being asked, which is why interviews work and blank pages do not.
Memory does not work by retrieval on demand. A question about a subject produces the general version. A question about a specific occasion produces the details, and a follow-up question produces the ones you had forgotten you knew.
That is a conversational process and a model cannot start it, because it does not know what to ask you about. It has no idea that something happened at a housewarming party in 2011, so it cannot ask about the ice.
The practical version for somebody writing alone: record yourself telling the story to a person. Not writing it, telling it. The details that arrive when somebody is listening are not the ones that arrive at a keyboard.
What should the tool be doing instead?
Working on the material after you have supplied it.
Tightening a rambling account. Suggesting where in a chapter a story would land best. Finding the three places you told the same anecdote in slightly different words. Producing a first structural pass so you can see the shape and rearrange it.
All of that is real work and it saves real time. None of it requires the tool to have been anywhere.
The neighbouring pieces cover the other gaps: AI never writes in your voice and the labour split that works on a book. The AI and Writing Hub has the rest, and my ghostwriting service is mostly six interview sessions and a lot of follow-up questions, for exactly this reason.
The Guides That Get Your Book Written, Published, and Sold
Four short, practical guides on writing, publishing, and selling your book, plus the occasional note when there's something worth your time. No fluff, no daily inbox clutter. Drop your email and they're yours.
We use MailerLite to manage our list and send these emails. Your address is used only to send you what you signed up for. We will not sell it, share it, or use it for anything else, and you can unsubscribe anytime.
Frequently Asked Questions