So What? How to Write a Book with Generative AI

So What? Marketing Analytics and Insights Live

airs every Thursday at 1 pm EST.

You can watch on YouTube Live. Be sure to subscribe and follow so you never miss an episode!

In this episode of So What? The Trust Insights weekly livestream, you’ll learn how to write a book with generative AI by leveraging existing content and AI agents. Discover how to transform your raw content, like transcripts and newsletters, into a coherent book outline and then full chapters. You will learn the importance of establishing a human-originated source for copyright and how to refine your AI’s writing style to match your unique voice. You will also explore the practical steps of using AI agents for writing and developmental editing, simplifying the book creation process.

Watch the video here:

So What? How to Write a Book with Generative AI

Watch this video on YouTube

Can’t see anything? Watch it on YouTube here.

In this episode you’ll learn:

What materials you’ll need to write a book with generative AI
How to preserve your human voice and human copyright
What tools work best to write a book with generative AI that’s worth reading

Transcript:

What follows is an AI-generated transcript. The transcript may contain errors and is not a substitute for listening to the episode.

Katie Robbert – 00:40
Well, hey everyone. Happy Thursday. Welcome to “So What?”, the Marketing Analytics and Insights live show. I’m Katie, joined by Chris and John. Gang’s all here.

John Wall – 00:49
There we go. High five.

Katie Robbert – 00:50
And John is in his own home.

John Wall – 00:52
I know. Back finally out of the jerks.

Katie Robbert – 00:56
Of the jig shirs. This week, we are using generative AI to write a book. So we, in the matter of however long this live stream is, are going to write a book, apparently. Chris, where are we starting with this book that we’re writing?

Christopher Penn – 01:16
Well, we’re going to start in a couple of different places. The first place to start is, do you want the book to be copyrighted or not? Generally, most people do, but the reason I ask is because if we want any work to be copyrighted, it has to start with a human-originated work. Generative AI can make derivative works, but if you start with a prompt, say, “write a book about B2B marketing,” and it capably spits one out, you can’t copyright that because it is not a human-originated work. In all but five jurisdictions on the planet, that would not be copyrightable. So we do.

Christopher Penn – 02:03
Generally speaking, if you’re going to go to the effort of creating a book, and you’re going to go to the effort of marketing a book, you probably want it to be copyrighted so no one can just copy and paste your entire thing and you have no recourse. That’s the first part. So we need material that’s human-originated in order to write a book that will be copyrightable. It just so happens that we have this thing called the AI Ready Strategist, which Katie, do you want to take a few minutes to explain what it is that we’re looking at here?

Katie Robbert – 02:33
Absolutely. If you haven’t heard, we are in the process of launching a brand-spanking-new course, the AI Ready Strategist. If you downloaded our AI Marketing Ready strategy kit from a couple of months back, this course is based on that kit with all of the frameworks, templates, checklists, and workbooks expanded out, plus a heck of a lot more content and useful assets that have been created in addition to what lives in the downloadable kit. The kit is a good start. This course really digs into the details of how to use those assets in a way that’s going to set you up for success. We called it the AI Ready Strategist.

Katie Robbert – 03:22
It’s really the Technology Ready Strategist because AI, in the way that the course is designed, is the tech focus right now. Tomorrow it could be something else. The course is foundational, so swap in any flavor of the month shiny object technology and everything you learn in this course will still hold true. Just swap out AI for Bitcoin, or Bitcoin for NFT, or NFT for CRM. It doesn’t matter. That’s what I really love about putting this kind of a course together is that it’s going to stand the test of time and it’s going to outlast any trend that comes along in technology. To be clear, in this course, we’re not teaching you how to use generative AI. We’re getting you ready from an organizational perspective to use generative AI.

Katie Robbert – 04:16
As you’ll learn in the course, the number one failure point of these integrations and digital transformations is people. Number two is process. We’re going to go through all of that in the course. Right now, it’s August 28th. We have it on pre-sale with a $500 off code, “strategy 2025”. You can reserve your seat. That code is good through midnight tomorrow night, Eastern Standard Time, and then the course goes live September 2nd. Go ahead and get it. I would recommend pre-registering and getting that discount with “strategy 2025”, and then it will be available to use, to love, to enjoy, to rewatch. All the downloads are there. Trust Insights AI Strategy course. How did I do, Chris?

Christopher Penn – 05:06
That was a good commercial plug. Here’s where we’re going to start the book writing process. You already did all the hard work of creating the course content. In every module, there are, of course, transcripts because you should be creating transcripts. Our first step towards creating the book is to get all of the raw data. All the transcripts we download now, they’re PDFs, and PDFs are compatible with generative AI systems, but they’re not ideal because they’re bulky files. What we’d want to do is turn those PDFs into just plain text files, the smallest, lightest-weight thing. There are any number of ways to do this. I use a free utility called PDF to Text. It runs on the command line. You can set it up as a batch job and just turn all the transcripts into text files away from PDFs.

Christopher Penn – 06:00
This preserves the letters and numbers and the words part, but it gets rid of all the formatting and weird stuff inside of PDF files. So that’s ingredient number one. Ingredient number two that we need is a book outline. In this case, because you already wrote and built the entire course, we basically have the book outline. It’s the course outline that will be. Instead of lessons, there’ll be chapters. That is pretty straightforward. If you had, say, a bunch of disconnected materials, you could have generative AI create an outline. You could say, “Here’s everything I’ve written about. Help me organize this into some kind of coherent outline so that it’s not just a disconnected bunch of mad ramblings from an old person sitting on their porch.” We don’t have to do that this time, but that would be.

Christopher Penn – 06:55
Step number two is to say we need structure, we need logic, we need an order. So we’ve got that.

Katie Robbert – 07:01
If we back up a second, that’s where the AI kit started, I have all of these things. “Can you help me put them together in a logical way?” That’s how the kit came about. AI didn’t write the downloadable paper, the kit that everybody got. I did. But AI helped me put it together in a way that made sense that I couldn’t necessarily see. Then we took that. I had AI say, “Okay, this is great, but let’s turn it into a course,” and gave me the outline. It wasn’t all like, AI just did it for me. I still had to connect the pieces. I just want to make clear to people, as you’re saying, that if you let AI do it, you still need a lot of human intervention.

Katie Robbert – 07:54
The amount of time I spent working on this and rewriting it versus having AI put something together, it’s out of proportion. It was more me than AI, but it helped me connect the pieces in a logical order that I was struggling to see.

Christopher Penn – 08:10
Exactly. So that’s ingredient number two, an outline. Ingredient number three is there may be supporting information that might not be in the transcripts, but would still be relevant. One of the things that Katie does really well is she’s an extremely good storyteller. If you’re not subscribed to it, the Trust Insights newsletter available at Trust Insights AI Newsletter. Every week, Katie writes what we call the “cold open.” That first part of the newsletter, the first half of it, actually more than half, because it tends to be about two-thirds of the original content in there. What we would want to do is say, “Let’s use that as a supporting data source because there may be things that she may have written about.”

Christopher Penn – 08:54
Maybe in February of 2024, she might not remember that she wrote about it, but it’s relevant. We would want to include things like those stories. So our third ingredient would be to take the newsletters that we have, sew them all up, and put them into one great big honkin’ Markdown file. Markdown is the plain text format that generative AI is very capable of reading. It’s a really good format. We do this every December, what’s called “Letters from the Corner Office,” which is Katie’s annual book of all the newsletter entries she’s written for that year. However, it’s also a great way to reuse this for other things. So this is going to be our next data source, having all of the newsletters from the last 18 months or so since January 2024. Those are the ingredients.

Christopher Penn – 09:44
Next, if we continue the analogy of the kitchen, we need appliances. We need ways to process the stuff. The two hardest tasks when writing a book are writing and editing. Those are both things that require a lot of time, a lot of thinking. We would probably want to say, “Let’s get some help specific to that.” How would we do this? The easy way to do this would be we’ll get fancy agentic AI. Agentic AI is essentially saying, “Let’s create little AI agents, little self-contained apps or programs that can run autonomously and perform a specific task like writing a chapter of a book or maybe editing a chapter of a book.” That’s what we’re going to need as one of the appliances. We’re also going to need Katie’s writing style. Katie’s writing style is very distinctive.

Christopher Penn – 10:40
We have a prompt that we’ve used and shared before in the Analytics for Marketers Slack group. It’s this nice, really long writing style prompt that helps an AI deconstruct a writing style, quantify it, and codify it into rules. Our first step would be to take perhaps all those newsletters, because the transcripts are the spoken word, not the written word. Take all the newsletters and build a writing style for that. What I’m going to do is I’m going to get. Oh, I forgot one other thing. The actual system for today, we’re going to use Anthropic’s Claude Code. Claude Code is a coding environment. It’s meant for writing code, but you can use it for any language model task. You do not have to use this.

Christopher Penn – 11:28
You can take just the regular prompts themselves and as a human being, use the regular Cloud Desktop or ChatGPT or Gemini or Copilot. That part doesn’t matter. I have one other addition that I find super helpful. It’s one of my favorite secret sauces when it comes to using Claude Code, and it is a tool called Serena. Serena is a coding MCP. This is starting to get into the technical realm, but what this does is it’s like a librarian. When you add it to a code repository—in this case, a book repository—it’s going to read through all the files. It’s going to read through your intent on what you want to do. It’s going to try and figure out, “Oh, this is where you’re doing this.”

Christopher Penn – 12:22
You have these names, you have these variables, these are the instructions and directives I have to keep in mind all the time. Serena is super useful for keeping AI on the rails because it remembers things from conversation to conversation that if you don’t use it, it just tends to forget. So that’s the last appliance. We have Claude Code, we have Serena, and we’re going to build the writing style and then start the writing process. While I get the setup, Katie wants you and John to debate why you would even do this.

Katie Robbert – 12:57
John, I remember earlier on in the life of Trust Insights, you wrote a book, and this was before generative AI was available to general consumers. AI technology has existed for a long time, but the way that it exists that we know today has only been around for a couple of years. Your book pre-dates that. I guess asking you, as someone who has written a book the old-fashioned way, what would you do something like this as opposed to the way you did it before?

John Wall – 13:39
Absolutely. This is just so much pain for anybody that’s gone through writing a book. It’s even funny. I was talking last week with Ashley Faust, who just had a book, “Human Centered Marketing,” come out, and it was the same type of thing as my book. It was, “Hey, let’s look at everything that’s worked over the past five years and write up all the tactics.” So you get a book like, “Okay, if somebody throws you this job today, here’s how you do it.” It would be so much faster, easier, cheaper now because I had to do a full brain dump on everything.

John Wall – 14:09
Whereas, you can say, “Hey, create a chapter on what to do at a trade show,” and you will at least get 50% or 60% of all the good stuff out there, everything that’s just out in public. Then you can just go through and add and edit and redirect the copy. You don’t have to do it all from scratch. Staring at that empty page is the most painful part of getting the book off the ground. Being able to generate a whole bunch of copy that’s at least close to where you want to go is a huge time savings. Then being able to do stuff like have it change the voice a little bit without having to rewrite the book.

John Wall – 14:47
I was talking to a screenwriter who was talking about how he wrote a whole movie, and the production company came back and said, “The lead needs to be a woman.” He was like, “Alright, no problem. Let me just throw it into AI, grind the whole thing out, and 90% of the work is done.” It’s definitely a much better time to be an author than ever before because it’s a whole lot less painful.

Katie Robbert – 15:10
I’ve struggled a little bit with the—gosh, how do I say it?—the morality of it, “Did I write the book or did AI write the book?” This is something that Chris and I have debated on podcasts and in other conversations. If I were going in and saying, “Hey, generative AI, how do I improve the process operations of a business?” and took what it wrote, that would be—to me—not really writing a book. But where I’m mostly okay with this version of it is because it is all my writing. It is everything that I personally, the human, have done. I’m just asking the machine to clean up my rambling into something a little bit more coherent and usable.

Christopher Penn – 16:05
Exactly. Part of the kickoff process for this, again, using a coding tool, is this onboarding, where the onboarding tells the agent, “Hey, you have to read all the background data that we provided, learn what’s in it, learn all the pieces, learn what each file is for, and then store that in your own internal agent memory so that it remembers, ‘Oh, this is a book project. This is not a coding project that we’re not using Python. We’re using Markdown. These are the files that are available to me. This is the layout, the folders.'” In here, we have—and this is part of the process—we have a clear set of folders. We have things like writing style, we have the documents, which is in a coding project where you put things like a requirements document.

Christopher Penn – 16:51
Even in a project like this, I didn’t do it for this project because Katie already did that for the course itself. If I was doing this from scratch, I would absolutely have a requirements document that says, “Here’s what this book is for, here’s the audience it serves, here’s the things that have to be in it,” and the course transcripts and stuff like that.

Christopher Penn – 17:16
Let’s go ahead now and start our first prompt. Our first prompt is to say, “Using the instructions for how to use a writing to create a writing style, you’re going to read some of the background newsletters that we provided and extract out what Katie’s writing style is, fill out the template, because there’s a template in our writing style instructions so that we end up with a solid analysis of what Katie’s writing style is because.”

Christopher Penn – 17:38
Then put it in the writing style folder. Now, while it’s doing that, I also forgot I need to put an output folder to actually put the chapters of the book, because it wouldn’t be terribly helpful to just have it leaving files all over the place. The components of a writing style, just to review, are things like clarity, conciseness, and not saying that these are how you should write. It’s to measure how concise the author is. Some authors are very verbose, but you want to know that so you can mimic it properly. Purpose and goal, sentence structure, diction and word choices, specificity, figurative language, and so on and so forth. These are all the things that we would want to diagnose and extract from existing writing. Almost every writing style prompt in AI goes completely wrong here: the frequency.

Christopher Penn – 18:32
That says frequency one to ten. Whenever somebody’s squinting, I was like, whenever somebody says, “Analyze my writing style,” and gendered AI comes back with, “Oh, well, you’re a storyteller in the first person and you used ‘whelp’ a lot in your language or whatever.” It doesn’t quantify it. This means that when you then go use that writing style and tell it to imitate it, what you often end up with is a caricature of that person’s writing because it tries to use those writing style elements all the time and starts every other sentence with, “Well, I’m like, that’s not me.”

Katie Robbert – 19:07
It’s funny because earlier versions of my writing style that we’ve done did turn out to be a caricature. The Katie artifact in Claude feels very much like a caricature of me, but it’s a good starting place, at least when we get to the point where we have a little bit of free time, we can update all that stuff. For now, it’s good enough because I know what I would and wouldn’t say, so I can take that and edit it very easily. Whereas someone who isn’t me might be like, “Oh, yeah, that totally sounds like her. Let’s just run with that,” and it’s not quite hitting the mark.

Christopher Penn – 19:49
Exactly. So Claude has gone through and evaluated your writing and provided the descriptive part so that it knows what’s right, but it also provides the quantification. For example, narrative style, if applicable. The frequency for this particular style is an 8. Some other things in here, let’s take a look. Use of sources. Typically, in your newsletters, you don’t cite a lot of sources because you are the source. You are the authority on this stuff. So you don’t tend to cite a lot of sources. It should know that you don’t write a ton with imagery.

Katie Robbert – 20:19
I said, “That’s very narcissistic of me.”

Christopher Penn – 20:23
But that’s your style from the newsletter. There’s nothing wrong with it. Everyone’s got their own style. So we’ve got

Christopher Penn – 20:39
The writing style. Our next step is we have to actually build these two agents. The agents that I talk about now, in Claude Code in particular, you build the agents right inside the interface. I’m going to type in the word “command slash agents,” and we’re going to create a new, brand new agent. You can choose from personal or project. “Personal” means it applies to everything that you use with Claude Code, and “project” is specific to a project, which is what we want to do with Claude. You can either give it your complete prompt yourself or you can give the start of a prompt and have it edited. I have found personally that having it edit my prompt comes with a better prompt.

Christopher Penn – 21:09
So we’re going to say “Janet” with Claude, and I give it the agent description. It’s called “Chapter Writer.” Chapter Writer is given an assignment and then it consults the course transcripts to see what the source information is. It will look at the writing style to make sure that it knows how you write properly. It will retrieve background stuff from the old issues in the newsletters if it doesn’t have enough information to write with, and then it will write to the Chapters folder.

Christopher Penn – 21:36
So I’m going to say, “Go ahead and now make me this agent,” and it’s just going to create this thing and it’ll become available as essentially a little mini app inside Claude, which is super useful because what these things do is they run inside their own little context box so they don’t soak up main system memory, and you can do other things while they’re running, which is super cool. So we’re going to specify “inherit from parent” will give us the color blue. Our first agent is done now.

Katie Robbert – 22:13
Done. You’re making it look easy.

Christopher Penn – 22:16
This is a cooking show. The second agent is going to be called a developmental editor. There are two fundamental different kinds of editors. There is a copy editor, like fixing typos and stuff like that. There’s a developmental editor who goes and reads things like, “Does this make sense? Is this logical? Do we forget things? Does this serve the purpose of the audience?” Very often, a developmental editor will come back to you with your book all marked up and saying, “You need this, this, and this, and your book is terrible,” and stuff. It’s not so much like, “This should be a semicolon.” It’s like, “You completely forgot things or you lost the plot in this chapter. Try again.”

Christopher Penn – 22:56
We’re going to create a second agent called a developmental editor, and it’s going to reference that gigantic prompt because you can do that with agents. You can give them extensive programming elsewhere. This will be the follow-on agent that will go on after Claude writes a chapter. Then the developmental editor will come in behind it and fix it up and say, “Yeah, this could have been better,” and stuff like that.

Katie Robbert – 23:20
John, I saw you nodding along. I’m guessing that was part of the process of writing your book, having a developmental editor basically rip your ego to shreds.

John Wall – 23:30
It wasn’t mine. I had heard a story about Brad Meltzer, the famous author, about how his editor in one chapter wrote in the sidebar, “This chapter is so boring, I want to kill myself.” Even as a best-selling author, he was like, “That scarred me for a long time.” But yeah, that’s the role. I have the same thing. I have an editor that I work with that continually beats the crap out of me. It’s humbling, but that’s the only way to get to great writing. Another thing, if you can have some of that beating in the privacy of your home that will share some embarrassing time among your peers.

Katie Robbert – 24:09
I feel like in some ways all of my feelings are going to be spared from seeing how poorly it’s written the first time because I’ve already done the writing. It’s going to basically repurpose everything I’ve done and then it’s going to edit it. So I’m going to see is a really nice output that I can then go through as a human and edit. But I’m sort of like, “Oh man, my feelings really get spared here, don’t they?”

Christopher Penn – 24:34
Exactly. So we now have the writing style, we have the course transcripts, we have the background information in the newsletters, we have the two-agent setup, we have the Serena memory setup. Our next step is to kick off the writing process itself. We’re going to give it a great big honkin’, beefy prompt. In fact, let me put this on screen and make it larger so that we can see it because it’s really hard to read. It goes like this: “Using the chapter writer, read the outline, and then with the Serena MCP, if needed, write each subsection of the outline, starting with Section 1.1 as a chapter, with your chapters outputted to the chapters folder. For example, lesson 3.1 becomes chapter 3.1. Each subsection from the outline is a lesson, and each lesson is its own chapter.”

Christopher Penn – 25:26
Rely on the course transcripts and the appropriate lesson numbers. The primary sources for your information when you’re writing. If you need supplementary information, use the data in the background folder. Extract paragraphs with Serena MCP, and this is important because we want to pull not just a word or a phrase but the whole paragraph for the extra context. Adhere strictly to the writing style. In writing style, unless the style conflicts with this prompt, it has supremacy, and I’ll explain why that’s important in a second. Use verbatim text as much as practical. That’s really important because we want to keep Katie’s voice as intact as possible. Remember, this is a book, so only have one list per chapter because otherwise AI loves making lists at the end of the chapter. The only list is at the end of the chapter named “So what?”

Christopher Penn – 26:11
Otherwise, the rest of the chapter should be formatted as prose, appropriate for a book. You must write prose for everything except the key takeaways. Because this is a book and not a course, you will need to remove references in the transcripts to the course. You also need to remove the pleasantries that are course-specific, such as “welcome back” and “in the next lesson.” This is a self-contained non-fiction business book. You should have no references to the course. For other content documents, write each chapter from the subsections in the outline now with the chapter writer agent answering MCP, beginning with lesson 1.1, proceed through all the chapters and lessons uninterrupted. So we’re basically going to say, “You are now going to go off and you’re going to do this thing.” Let’s go ahead and plop this in the chat.

Christopher Penn – 26:53
Now it is going to begin what is approximately a two-hour process where it’s going to read, write, and go on. It’s just going to keep reading and writing throughout time. Like a good cooking show, we have the fully baked process where it has gone through. You can see, when I get down to the relevant section here, you can see, “write this chapter, write this chapter,” and it just goes through. Every chapter takes between three to seven minutes for it to process. What comes out in the end is a list of chapters. So let’s open up—actually, let me open up one of these so we can see.

Katie Robbert – 27:45
As you like to say, Chris, I feel like two hours, like three to seven minutes per chapter, is a reassuringly long time for AI to be processing because if it came back within 30 seconds, that’s really fast. But then it says to me, “Did it even really pay attention to the background material? We gave it a lot of information. Did it just skip over and say, ‘I’m just going to write whatever I feel like?'” Whereas if you’re saying it’s going to take two hours to process through everything we gave it, I’m like, “Oh, that actually makes me feel more reassured that it’s really going to take a look at what was previously created and put it together in a more thoughtful way.”

Christopher Penn – 28:30
Exactly. So here’s an example. Let me make this full screen here and make it easier to see. “Four point introduction to the six C’s of data quality.” When you read this, it’s fairly close to the course transcript. All the speech disfluencies, repeated words, and things like that, tie-downs on the end of sentences using “okay” or “right” or “you know,” and all that stuff has been extracted out. What you end up with is a pretty decent section of a chapter. This looks like what you’d want to see in a book. Here’s the “So what?” list of takeaways from this section. “More data isn’t always better?” Well, yeah, I mean that’s kind of a given. So now the first draft is done. What do we do?

Christopher Penn – 29:27
We now go back in, and we fire up the developmental editor. The developmental editor is given this prompt: “Using the developmental editor in the MCP, you’re going to evaluate each chapter in the chapter’s fullest of the following: Is the writing fully aligned with the writing style? Is the chapter aligned with the outline? Did you make things up? Is it aligned with the sources in the transcripts? If you need additional content, such as stories and personal anecdotes that are hallmarks of Katie Robbert’s writing style, are they sourced from the newsletters? Is the content truthful and factually correct based on the sources, avoiding hallucination and avoiding fabrication? Did you make things up? Does the content serve the needs of the business non-fiction reader who wants to understand AI strategy? A strategic level?”

Christopher Penn – 30:14
Is the content written appropriate for a book with references to courses, downloads, transcripts, etc., removed? Is it not part of the book? Does the content have the required “So what?” list of takeaways at the end? Is the content written well? Written as well-formatted prose with no other list besides “So what?” This agent is given these instructions, and it now goes through and says, “Okay, great. I’m now going to use the developmental there and inspect each chapter.” When it went through, it modified about half the chapters. It found things that the first draft didn’t really do as well as it could have and it fixed them up. So what we have now is—let’s close—that’s the wrong folder. Where is my—here’s the Katie book folder.

Christopher Penn – 31:01
We now have the 28 chapters in total, all nicely cleaned up and in Markdown format, ready to be used. Now this is good. This is super helpful. However, in this current format, it’s not exactly a book. We need to now go to the next step, which is to convert it. Here’s the wonderful thing about the Markdown format: besides being text, it is easily converted to other formats. So what? The most popular format for book writing is Microsoft Word. So if I issue a command that says, “For every Markdown folder in the Markdown file in this folder, convert it to a Word doc,” it has gone through and turned that ugly Markdown into a nicely formatted Word doc here. This is already looking better. Now we can take those Word docs and close this project into.

Christopher Penn – 32:16
I’m using a package called Scrivener. We’ll call this AI Ready Strategist. Scrivener is available for Mac and Windows. It’s like $50. It’s a one-time cost, which is nice. One of the things I can do with Scrivener that I just love about the software is I can take all of these Word documents, drag them right into the interface, and it makes them chapters for a book. All I need to do is clean up the chapter names, maybe apply the formatting, and then from here I can go to the export. I can choose a 6×9 paperback. I’m just going to do a test run on this because obviously we’re not going to do the full book publication right now. Let’s export to PDF. Actually, let’s do ePub. Switch to ePub. This is an ebook.

Christopher Penn – 33:19
We’re going to give it the section layout to assign it to a new page section, hit compile and go. What it’s going to do is it’s going to take all these chapters and hopefully successfully. I think it’s still working. Here we are in Apple Books. On my desktop is the new book, nicely formatted ebook, ready. We now have a lovely textbook to go with the course or as a standalone, in Katie’s words, from all the hard work that Katie did in approximately three hours.

Katie Robbert – 34:18
With 20 years of experience of writing behind it.

Christopher Penn – 34:24
Yes, 20 years of experience, a month of recording the course.

Katie Robbert – 34:31
I had a throat lozenge before this live stream because my throat is still.

Christopher Penn – 34:34
Junk from all the recording, plus two months of planning out all the slides and the content for the course stuff. What this emphasizes is that if you’ve already got existing content laying around, use it. Take the content you have. Use generative AI to essentially clean it up and reformat it and help repackage it and turn it into something that you can extend the life of your content. A real simple thing. Let’s say you have a podcast like the Marketing Over

Christopher Penn – 35:10
Coffee podcast, and you have interviewed 400 guests over the years. You could take all the transcripts from all 400 guest episodes and interviews and call it, “The Espresso Edition,” or “Marketing Lessons Learned from 400 Guests on the Marketing Over Coffee Podcast.”

Christopher Penn – 35:36
Following this exact same process of getting the transcripts, distilling it down, and turning it into a book. You could have probably—I would actually say probably five or six different books—because the guests have been in different categories: sales and marketing, biz dev, customer service, and strategy. You already did all the hard work. The hard work is done. Now it’s just having machines essentially do the paperwork.

Katie Robbert – 36:04
Just a matter of marketing over espresso. Espresso marketing.

John Wall – 36:11
We get burned. The one thing it would have to go through is the topicality of it. Nobody wants to hear all those MySpace interviews from 1996. Those are.

Katie Robbert – 36:20
I don’t know. There is something to be said for nostalgia.

John Wall – 36:25
This is true. It could be, “The 500 Marketing Lessons You No Longer Need,” or something like that.

Christopher Penn – 36:33
Remember to put your best prospects in your top eight.

Katie Robbert – 36:40
I think this is really cool. Obviously for those watching, what Chris produced today is not going to be available with the course on Tuesday. That said, there may be a version of it coming down in the future, considering I have yet to actually read any of it. Pro tip: make sure that there is always human intervention with your generative AI and that you don’t just take the first output and go, “Okay, good enough.”

Christopher Penn – 37:09
Exactly. It repurposes the hard work you already did and extends the life of it. As you said, if it’s available eventually as its own standalone book, then the book becomes, “Oh, by the way, you can take the course and get the certificate and get access to the community and get all the downloads and worksheets and things.” The book could be sold at like $29.99 or $39.99 and then use that as a business driver to drive registrations for the course. But you had to have the raw data to start with. That’s the hard part. Again, not just the months you’ve spent working on the course, but almost two years of newsletters that you’ve written too.

Katie Robbert – 37:54
Yeah, I would agree with that. There’s—and this is something that we talked about a few weeks ago—AI is going to replace a lot of the processes and summarization and the things that you just showed. It doesn’t replace the critical thinking, and it becomes even more crucial for you as the human to come up with those original ideas and do the critical thinking about them and figure out the different innovative ways to use the ideas that you have. AI is only going to take it so far. We get a lot of the sameness from generative AI. What makes it different and useful are the humans using it.

Christopher Penn – 38:39
Exactly. What you also didn’t see, because I started this process this morning at 7:00 AM, was the first two tries where the prompts themselves needed some improvement. I looked at the first couple of chapter drafts and saw, “This needs this. It needs to be told this.” Even in the prompt case itself, I had to do some tuning and some hammering behind the scenes just to make the bits and pieces work properly. I ran into an issue where one agent wasn’t talking to another agent properly. However, that did only take a few hours to work itself out. I would encourage everyone to look carefully at the inventory of content that you’ve already created.

Christopher Penn – 39:25
Not too long ago, I was hanging out with a friend at an event and she said, “I write on LinkedIn like two or three times a day. I just don’t have time to write a book.” I said, “You already wrote the book. You just need to export your LinkedIn data.” Which we did. Following a similar process, Claude was able to crank out 65,000 words of coherent text. It still needs editing, and Katie’s book will still need editing. But that initial lift of, “Oh my God, I have to write a 65,000-word book,” is now “I have to edit a book.” Okay, I can tell. I can stomach that.

Katie Robbert – 39:59
I can say with confidence, the thing that’s missing from the course that I usually include in breakout sessions at events or in the newsletter is more of the storytelling and more of the anecdotes. Pulling from my own personal experience, I didn’t want to distract students in the course by getting too far off topic. It was more of, “You came here to learn something. I’m here to teach you the thing.” In the book version, I would want to bring back more of that storytelling of, “This is why I have this experience. This is why I know this,” versus, “Here’s the thing. You came to learn the thing. Here it is. Go do the thing.” I feel like that’s going to be a big part of the editing process, at least for me, for a proper book.

Katie Robbert – 40:51
Because to your story—I’m sorry, to your point—I’m a bit of a storyteller and that’s just not part of the current course. The course is the course. It’s academic-focused, whereas a book should be more narrative.

Christopher Penn – 41:04
Exactly. The first word count, by the way, on the generated book that we just did is 65,900 words.

John Wall – 41:16
That’s huge.

Katie Robbert – 41:18
I don’t know what that means, I’ll be honest.

Christopher Penn – 41:20
So this is about 70,000. This is about 60. So it’s between these two.

Katie Robbert – 41:30
Gotcha. Once I add in more of the storytelling and the anecdotes and the examples, it will be closer to. Yeah, okay. That’s helpful because I feel like—well, this is getting too much about me—I feel like I’m going to do it. I want to do it right and have it be like a really good, not just throw away like, “Oh, hey, here’s a compilation of everything I did.” Which isn’t to say that’s how it comes out, but I want to put my personal stamp on it. I don’t want it to just be, “I put these things together. Enjoy.”

Christopher Penn – 42:05
Exactly. That’s the process I would recommend to folks. Give it a try, keeping in mind all the requirements. You’re going to need source data. That doesn’t have to be an entire course. I have written almost timeless. My new book was written principally from voice memos from me “Foaming at the Mouth” for five hours on a drive to Albany. If you bought the deluxe edition, you got a copy of the “Foaming at the Mouth” audio. It’s in the deluxe edition. You can hear me swearing at people in traffic and stuff. It’s fantastic. But I do that for two reasons: one, because it’s entertaining. Two, it also provides lineage. It provides proof that it was human-originated. So you need your source data.

Christopher Penn – 42:53
You need ideally a generative AI system that has agents built into it that allow you to process the stuff. If you don’t,

Christopher Penn – 43:24
That’s fine. You can do it just with prompts. It’s just a lot more copy and pasting you want to use. Generally speaking, you want to use a reasoning model. We use for this book, Claude Opus 4.1, but Gemini 2.5, ChatGPT5, all those would be perfectly suitable. You want to have a good writing style prompt, and you want to have good prompts to actually do the writing. Make sure that you do a test run on a chapter or two before you kick it all the way off so that you can spot issues early and fix them. It’s actually just like compiling software.

Katie Robbert – 43:38
It really is. Because the stuff that I’ve already written, that’s the requirements. So now it’s just a matter of putting it all together with the technology, as you stated at the beginning of the live stream.

Christopher Penn – 43:49
Exactly. Any final thoughts?

John Wall – 43:53
Just need to cover.

Christopher Penn – 43:55
Yeah.

Katie Robbert – 43:56
Stay tuned for the book coming soon.

Christopher Penn – 44:00
That’s going to do it for this week’s show, folks. Thanks for tuning in, and we will see you all on the next one. Thanks for watching today. Be sure to subscribe to our show wherever you’re watching it. For more resources and to learn more, check out the Trust Insights podcast at TrustInsights.ai Podcast and a weekly email newsletter at TrustInsights.ai Newsletter. Got questions about what you saw in today’s episode? Join our free Analytics for Marketers Slack Group at TrustInsights.ai Analytics for Marketers. See you next time.

Need help with your marketing AI and analytics?

So What? Marketing Analytics and Insights Live

airs every Thursday at 1 pm EST.

In this episode you’ll learn:

Transcript:

Leave a Reply Cancel reply

Pin It on Pinterest