[Journey] Creating Good Books With AI

So I think I’ve got my next experiment.

I previously mentioned studying counterfeit AI books, but I’ve come to the conclusion that it was a bit of a dead end.

The more I read the less I felt human.

So I’ve decided to change direction.

I am going to order half a dozen bestselling nonfiction books from Amazon. Probably on a mix of subjects but successful books like Atomic Habits,

The plan then is pretty simple.

I’ll use the table of contents from each book to generate an AI version on the same subject using the best prompting methods I can find.

Then I’ll compare them side by side and see what they stack up.

I think it’ll be an interesting experiment.

If nothing else, I should come away with a better understanding of what separates a bestselling nonfiction book from one that’s merely generated by AI.

Any recommendations on a good read?
 
Advertise on BHW
MasonBookwright said:
So I finally signed up to Blackhatworld after being a little scared of the place.

But I have gotten over myself and now I am here.

As I mentioned in my intro I have previously made money online through Adsense and affiliate marketing until the big G changed direction and tanked all my sites.

Then there’s my current business major POD mugs with AI art. It’s doing okay but even in POD there are unexpected costs and pitfalls.

I have decided to experiment with writing non fiction books with AI. I have previously done some content with it and know a little bit about the pitfalls and some tips and tricks to get better output.

My ultimate aim is not to create AI slop but actually useful material that can stand the test of time.

I have chosen to mainly use Claude for the books as I like the projects and being able to keep things together but I am not afraid to try others.

So here’s the plan:

Decide on a topic
Create a book outline
Create an author and author voice
Write the book
Redraft
Edit

My estimated costs are £20 for Claude but open to spend more as the journey goes on.

Goals:

Prompt
Publish
Profit

I am going to start with a random non fiction topic probably in self help or wellness.

When the process is complete I will look at market research for choosing the books to launch. For the moment I want to sort out the book writing process first.

The first thing I have seen being taught is to outline the book. So that’s my first job.

Here’s the prompt I will start with:

[You are a best selling author specialising in books on [niche] . You have been tasked with outlining a best selling book on [niche]

I am going to pop this into chatgpt Claude grok and Gemini and see what comes back.

Following this I am going to pop across to Amazon and do a search and see how the book chapters of actual books compare to what AI has spit out.

Anything I am missing at this stage?

Any questions please just ask.
Click to expand...
Thanks for sharing your journey and being transparent about your process. I like that you're focusing on creating genuinely useful content instead of relying on AI-generated text alone.

One suggestion would be to validate the topic before investing too much time in writing. Looking at reader reviews, common questions, and gaps in existing books can help ensure you're addressing real audience needs. I think combining that research with your AI-assisted workflow could make the final product much stronger.

Looking forward to seeing how your experiment develops.
 
michaelwilliams1 said:
Thanks for sharing your journey and being transparent about your process. I like that you're focusing on creating genuinely useful content instead of relying on AI-generated text alone.

One suggestion would be to validate the topic before investing too much time in writing. Looking at reader reviews, common questions, and gaps in existing books can help ensure you're addressing real audience needs. I think combining that research with your AI-assisted workflow could make the final product much stronger.

Looking forward to seeing how your experiment develops.
Click to expand...
Thanks, I appreciate the comments.

Validation definitely seems like a good idea. I’ve heard a few people mention using Amazon reviews to work out what’s working and what isn’t. Some recommend comparing the 5-star and 1-star reviews, while others say it is in the 3-star reviews because that’s where readers often explain what was missing.

Your point about looking for knowledge gaps really resonated with me as well. It like in SEO

Have you used that approach yourself?

It’s definitely something I want to explore once I get to the research stage. In fact I can image a couple of experiments that may be fun to run. At the moment I’m trying not to swim before I can paddle .
 
MasonBookwright said:
Thanks, I appreciate the comments.

Validation definitely seems like a good idea. I’ve heard a few people mention using Amazon reviews to work out what’s working and what isn’t. Some recommend comparing the 5-star and 1-star reviews, while others say it is in the 3-star reviews because that’s where readers often explain what was missing.

Your point about looking for knowledge gaps really resonated with me as well. It like in SEO

Have you used that approach yourself?

It’s definitely something I want to explore once I get to the research stage. In fact I can image a couple of experiments that may be fun to run. At the moment I’m trying not to swim before I can paddle .
Click to expand...
You're welcome! I agree that 3-star reviews can be especially valuable because they often highlight what's missing. I also like your approach of focusing on the process first before moving on to validation. Looking forward to seeing how your project develops.
 
the one thing i’d add is to build an evidence pass into the workflow, like a step where you replace any vague claims with real-world examples, citations, or at least verifiable references so it doesn’t feel like generic self-help.
also, when you start picking the random topic, try to choose something narrow enough that you can fill multiple chapters with distinct subproblems
 
Nefertum said:
the one thing i’d add is to build an evidence pass into the workflow, like a step where you replace any vague claims with real-world examples, citations, or at least verifiable references so it doesn’t feel like generic self-help.
also, when you start picking the random topic, try to choose something narrow enough that you can fill multiple chapters with distinct subproblems
Click to expand...
Great suggestion. An evidence pass can definitely improve credibility and make the content more useful. I also agree that choosing a narrower topic makes it easier to provide more depth and practical value throughout the book.
 
michaelwilliams1 said:
Great suggestion. An evidence pass can definitely improve credibility and make the content more useful. I also agree that choosing a narrower topic makes it easier to provide more depth and practical value throughout the book.
Click to expand...
yeah exactly, and the evidence pass is what keeps it from turning into generic “motivational” stuff. if you pick a narrow angle, each chapter can focus on a specific problem plus a real example or exercise, and that’s what makes it feel genuinely useful.
 
Nefertum said:
yeah exactly, and the evidence pass is what keeps it from turning into generic “motivational” stuff. if you pick a narrow angle, each chapter can focus on a specific problem plus a real example or exercise, and that’s what makes it feel genuinely useful.
Click to expand...
I completely agree. Focusing on specific problems and supporting them with practical examples makes the content much more valuable. It also helps readers apply the ideas instead of just reading general advice.
 
Nefertum said:
the one thing i’d add is to build an evidence pass into the workflow, like a step where you replace any vague claims with real-world examples, citations, or at least verifiable references so it doesn’t feel like generic self-help.
also, when you start picking the random topic, try to choose something narrow enough that you can fill multiple chapters with distinct subproblems
Click to expand...

Just want to check by evidence pass do you mean in the editing phase?

I agree with you both on drilling down. I really like the one person one problem approach. I think some can go too far down but as a general rule it’s a good one.
 
The problem is. Hollywood with their massive billion dollar budgets cant figure out how to make AI stay compliant enough to make a story thats actually engaging. Maybe you found a loophole? In that case that person needs to keep it to themselves and make some dough.
 
SIPSAMURAI said:
The problem is. Hollywood with their massive billion dollar budgets cant figure out how to make AI stay compliant enough to make a story thats actually engaging. Maybe you found a loophole? In that case that person needs to keep it to themselves and make some dough.
Click to expand...
That's a fair point. AI still has limitations when it comes to maintaining consistency and delivering genuinely engaging storytelling. I don't think it's about finding a loophole so much as using AI as a tool while relying on human editing and creativity to shape the final result. That combination seems to produce the best outcomes.
 
MasonBookwright said:
Just want to check by evidence pass do you mean in the editing phase?

I agree with you both on drilling down. I really like the one person one problem approach. I think some can go too far down but as a general rule it’s a good one.
Click to expand...
Yes, that's how I see it. The evidence pass fits well during the editing phase, where you can verify claims, add credible examples, and strengthen the overall quality. I also agree that focusing on one person and one specific problem usually results in more practical and engaging content.
 
SIPSAMURAI said:
The problem is. Hollywood with their massive billion dollar budgets cant figure out how to make AI stay compliant enough to make a story thats actually engaging. Maybe you found a loophole? In that case that person needs to keep it to themselves and make some dough.
Click to expand...
I can’t image trying to write long form fiction with AI. That feels like you would be really fighting against the AI. There was a study recently that showed that AI writing of fiction can be spotted in the very structure of the story not even just the words.

I am looking at non fiction and hoping that I can create something that comes from using AI strengths.
 
MasonBookwright said:
I can’t image trying to write long form fiction with AI. That feels like you would be really fighting against the AI. There was a study recently that showed that AI writing of fiction can be spotted in the very structure of the story not even just the words.

I am looking at non fiction and hoping that I can create something that comes from using AI strengths.
Click to expand...
I agree. AI seems much better suited to non-fiction, where it can help organize ideas, summarize information, and speed up drafting. With careful editing and fact-checking, it can be a useful tool without replacing the human perspective.
 
Two of the books have arrived Atomic Habits and Brainfluence. I picked two random chapters and prompted them in Claude and ChatGPT.

One looked at the 2 minute rule and the other the paradox of choice. Both chapters were prompted the same way.

The Claude output was interesting. On the 2 minute rule it pulled in extra information and made a distinction between two different two minute rules. It handled paradox of choice much better.

ChatGPT only writes in single line paragraphs so everything looks like a massive list.

I was pleasantly surprised with the paradox chapter in Claude. It read closer to the information covered in the book.

It’s still far from perfect and no where near something that could be published. It was however a simple prompt.

I wonder why they both did one well whilst struggling with the other.I suspect it’s because the paradox of choice is more concrete in the information. Also I just noticed the paradox chapter is probably half the length that may have an impact.

AI writing is still an information dump at this point. Been an interesting start to this experiment. Will continue this compare and contrast experiment this week.
 
MasonBookwright said:
Two of the books have arrived Atomic Habits and Brainfluence. I picked two random chapters and prompted them in Claude and ChatGPT.

One looked at the 2 minute rule and the other the paradox of choice. Both chapters were prompted the same way.

The Claude output was interesting. On the 2 minute rule it pulled in extra information and made a distinction between two different two minute rules. It handled paradox of choice much better.

ChatGPT only writes in single line paragraphs so everything looks like a massive list.

I was pleasantly surprised with the paradox chapter in Claude. It read closer to the information covered in the book.

It’s still far from perfect and no where near something that could be published. It was however a simple prompt.

I wonder why they both did one well whilst struggling with the other.I suspect it’s because the paradox of choice is more concrete in the information. Also I just noticed the paradox chapter is probably half the length that may have an impact.

AI writing is still an information dump at this point. Been an interesting start to this experiment. Will continue this compare and contrast experiment this week.
Click to expand...
Interesting observations. I think the topic itself can make a big difference. Concepts with a clearer structure are often easier for AI to organize, while broader ideas may lead to more generic output. It'll be interesting to see whether refining the prompts or breaking chapters into smaller sections improves the overall quality.
 
A small update after a few evenings of experimenting.

I’ve now recreated around ten random chapters from the different books, across a few different genres, using three different prompts and 2 AI’s (AIs AIses? not sure on the plural).

One pattern that’s starting to stand out is that AI seems much more comfortable with concrete, well-defined ideas than topics that are nuanced, controversial or abstract.

Another thing I’ve noticed is chapter length.

If I let the AI write as much as it wants, it has a tendency to waffle. If I force a much shorter chapter, it becomes far more focused, but often skips over important details.

As an seperate thought I also tried adding a target audience into one of the prompts. For Brainfluence I used something like “business owners wanting to improve online conversions.” Though using the one person one problem this might help

I expected that to improve the writing.

Instead it became… odd.

It reminded me of the “How do you do, fellow kids?” meme. The AI kept trying to sound like it was talking directly to business owners, but it felt forced and unnatural rather than authentic.

every experiment seems to raise another question.

I don’t feel any further forward.

I guess at the moment I’m learning at least what doesn’t work.
 
MasonBookwright said:
A small update after a few evenings of experimenting.

I’ve now recreated around ten random chapters from the different books, across a few different genres, using three different prompts and 2 AI’s (AIs AIses? not sure on the plural).

One pattern that’s starting to stand out is that AI seems much more comfortable with concrete, well-defined ideas than topics that are nuanced, controversial or abstract.

Another thing I’ve noticed is chapter length.

If I let the AI write as much as it wants, it has a tendency to waffle. If I force a much shorter chapter, it becomes far more focused, but often skips over important details.

As an seperate thought I also tried adding a target audience into one of the prompts. For Brainfluence I used something like “business owners wanting to improve online conversions.” Though using the one person one problem this might help

I expected that to improve the writing.

Instead it became… odd.

It reminded me of the “How do you do, fellow kids?” meme. The AI kept trying to sound like it was talking directly to business owners, but it felt forced and unnatural rather than authentic.

every experiment seems to raise another question.

I don’t feel any further forward.

I guess at the moment I’m learning at least what doesn’t work.
Click to expand...
That's an interesting finding. I've noticed something similar—AI often performs better with clear, structured topics than with more nuanced ones. It also seems that shorter, focused sections produce better results, especially when they're refined through editing rather than trying to generate everything in a single prompt.
 
rexant said:
I also listed many books on KDP, but no sale
Etsy is good for POD(Tshirt and digital goods)
Click to expand...
I do POD mugs on Etsy. For the book (s) I would do my own site linked to a book POD company?

Would. Love to know, how long have your books been up? How are you promoting them and did you write them or use AI?
 
Advertise on BHW
You must log in or register to reply here.
Sign up now!

Main Menu

Home Main Forum List Black Hat SEO White Hat SEO BHW Newbie Guide Blogging Black Hat Tools Social Media Downloads

Marketplace

Account Selling Content / Copywriting EBooks / Methods Hosting Misc Proxies For Sale SEO - Link building SEO - Packages Social Media Social Media - Panels Web Design More

Making Money

Affiliate Programs Hire a Freelancer IM Journeys Making Money Pay Per Click Site Flipping Want to Buy

BlackHat World

Dispute Resolution Forum Suggestions & Feedback Introductions Lounge
Back
Top