Today, my special guest is not only an expert in using generative AI in business, but he's also a community fellow at ChiefAIOfficer.com. Chris Lannon is a seasoned software engineer with a rich career and big names like General Instrument, Motorola, and Hewlett Packard. Now, Chris has made a complete plunge into the world of generative AI. In this episode, we talk about his powerful AI-powered bookwriting tool, ghostwriter.ai. From automating blog posts to publishing full-fledged books, Chris is here to share his journey and insights. Now, let's get started. Welcome to Using AI at Word. I'm your host, Chris Stable. Each week we'll be learning how today's business owners, entrepreneurs, and ambitious professionals are getting more done with smart use of tomorrow's tech. Let's get started. Hey everybody, this is going to be a lot of fun. I think you'll know why pretty quickly, but I want to introduce our guest. Chris, why don't you tell everybody a little bit about yourself and what you're up to in the AI
space?
SPEAKER_01Yes, so uh I spent my career as a software engineer. Um worked at you know places like General Instrument, Motorola in the C-band satellite industry, uh Hewlett-Packard with uh their printer projects, Sharp Healthcare, which is a large healthcare organization here in San Diego, uh Mitchell International and Transcorps. Um and now I'm in the the casino gaming industry uh as an IT manager. And uh about a year ago when all this I this AI stuff started happening, I um put my nose to the grindstone and started basically just spending time in the morning every day learning this stuff. And so it's gotten me excited about getting involved in technology again. I was considering retiring pretty soon, but I think I'm gonna stay in the game a little while longer.
SPEAKER_00Yeah, for sure. So, Chris, let me let me pull on that thread a little bit. You know, Gary, I don't know if you you know, but Gary V's whole thing was stay up late to do the business, hustle, hustle, hustle, right? Would you say that those that getting up early and that extra time that you spent, was that was it the hustle for you? Like was it that kind of grind, or what was that experience, the learning curve like?
SPEAKER_01Well, I was so excited that basically I couldn't sleep, and I'm more of a morning person. So it made it a lot easier. Plus, I have a 10-year-old son, and uh, he's not up that early. So that's my alone time in the morning, and that's basically how it worked out. Um, so I've got a good, you know, four hours before he's even up to play with this stuff, and it's uninterrupted time. It's kind of like, you know, I guess the miracle morning, but yeah, I don't really didn't really follow that. I just kind of have my own routine in the morning, and I'm more of a morning person.
SPEAKER_00Yeah, nice. So for anybody listening, it's as simple as that. And I'll say that the same thing happens over here at AIHQ. Um, just get up early and hit it real quick before the rest of the chaos of the day gets in, and that's all it takes. So let's talk about that learning curve for you. You you got a computer science background, you've been involved in in technology for your entire career. There may be people listening that would be of say, of course it was, you know, of course you're the person on the other end of this. Of course this was easy for you. But were what did your computer science background come into compressing that learning curve at all when it came to generative AI?
SPEAKER_01Um, not initially. I, you know, I was hiring ghostwriters to write blog posts, and uh, I'm an I'm an Amazon seller on the side, so I basically was hiring people to write content for me. And when the generative AI stuff, I started with Jasper. Um, and when the generative AI stuff came along, I started using it for that and realized that I could basically do that instead of hiring people. Um I was paying quite a bit of money, like $75 per blog post just to get traffic to my e-comm site. And uh that's basically how I started using it. And then once I discovered automations and the the powerful combination with uh the generative AI and automations, I started playing with some of the no-code solutions to to do some prompt chaining and some uh automatic report generation with those solutions.
SPEAKER_00Yeah, that was one of the things that I was very excited about talking about. Here is what initially got me really interested was most people who will be using generative AI on a day-to-day basis don't have a technology background. So most of the time when we're doing these interviews, we're not really exploring what happens if you get really sophisticated with generative AI, with APIs and the assistance and stuff like that that we talked about on our other call that wasn't recorded. Uh so I definitely want to pull on those threads, but the reason that uh Chris and I got connected, just so everybody knows, the context was at uh my the parent company of this uh podcast is chiefaiofficer.com, and we have had a manuscript that was 95% done on a book about the role of the chief AI officer. It's been done for almost six months, and it was just one of those things that we couldn't get over the finish line. There was always something in the way. And um Chris and I got connected through uh the AI space, and he was sharing um the project that he's about to tell us about. And uh, needless to say, I was very intrigued. And as a result of uh Chris coming on the scene, the chief AI officer book is a masterpiece and was actually published on Amazon as of last night, thanks to Chris. So, Chris, why don't you tell us a little bit about what that conversation was that you and I had?
Um, yeah, so basically uh you told me about your chief AI officer program, and I was really interested in the program and uh enrolled in the program and started going through it and and uh kind of wanted to reciprocate for the work that you were doing with that, and uh offered to write your book with my my product, ghostwriter.ai. That's ghostwriter without the e. Um, and asked you about that and and uh basically got some information from you from your uh about your courses and about your background. And with that night, pretty much I was able to write the book with my automation um system. And basically we ended up with a book. We yeah, we had the first draft the next day, and then your people went through it and and fixed it, and you you guys made it your own, and we were able to publish it last night.
SPEAKER_00Yeah, the only uh I'll tell you, the only feedback that they had were more nuanced about uh the way some more preference than anything, not anything about the content. That's what blew me away because I know a lot of this isn't a new service. There's other individuals out there who were doing, you know, creating uh books with AI. However, the reason that we didn't use any of those tools to get us over the finish line was because uh the output wasn't terribly impressive. And it's important for me because look, we had put a lot of energy into creating the course, which was the source material for your book. It's not like it was made up from scratch, everybody. This is um like all of the blood, sweat, and tears we put into the chief AI officer training, that was authentic. That was uh human-generated content. And all Chris did was take that and repurpose that into uh uh the format of a book. So that was one of the things, that was the only reason that I said yes. Once I saw that output, I was like, my gosh, this is like let me sign off on this. This is good to go. Um why of all the skills and techniques and and tactics that that you've learned in the computer science career, but also in your four hours of miracle morning with AI every day, why this? Why why books?
So I I had seen a couple other um of these products where people were generating books with AI, and I wasn't impressed with not only the the quant the quality, but the quantity. Um, I think that was the hardest part in the beginning was actually getting uh you know a book that was something like 35,000 plus words, 10 chapters with quality writing. And I had was looking at hiring a ghostwriter to write my own book for my uh e-commerce brand, and kind of decided to put this together on my own. And when I saw some of these people playing with the automation platforms, particular, particularly make, um, I became really intrigued, and it just kind of became my first big project. And I'm there were times when I thought this is way too big of a project for me to tackle as like a first project. Yeah. So I've been working on it for eight months, and the quality is really important to me. Um, and I'm finding that the um the generative AI models are getting a lot better at writing. And I think, I mean, they're gonna get better from here. Um I'm even looking at possibly trying to disrupt the publishing, the self-publishing industry, because I think there's a lot of people that are charging a lot of money for things that AI agents will eventually be able to do. So that's just the old paradigm and it's still holding on. Yeah, and I don't think these people see it coming.
SPEAKER_00Um interesting.
SPEAKER_01It you know, they're just like everybody else. They they're intimidated by AI, they don't know what it's about. Um, just like you know, a lot of a lot of the people in your audience, they're they're just getting started, I think. Um the people, a lot of people in the publishing industry, I think they probab some of them see it, but a lot of them don't realize what's coming, I think.
SPEAKER_00Wow, and you know, of all the industries, I'm sitting here and I'm going, uh, yep. Output being text or word, if that's your business or your industry, um, there's there's some competition now, especially if you can calibrate the environment of output so that it is high quality, it is authentic, it does, it is trained on that individual's voice or style or that sort of thing. So, you know, it's it's interesting because just today I was listening to uh another podcast, Isar Matis has a podcast called Leveraging AI. I don't know if you know the podcast, but I listen to it, I've been listening to it for a long time. And the episode that I listened to was a content uh business, right? Like they were generating content. And we do that internally. We've got some pretty robust stuff, but they got they got a little geeky, right? And they got into um, he was Australian, so he said, Python, not Python, like we say in the states, but um he was, but he was, he also said, Listen, I'm not a coder. I just go to the models and I say, here's what I want to have happen. And I would iterate, it would give me something, I'd try it, it wouldn't work. I'd go back and say, hey, that didn't work. This was the error I got. And the models were doing the heavy lifting when it came to this guy learning Python, that is, you know, uh certainly a more sophisticated application of or involvement of technology of generative AI than the average bear. So in your situation, it was kind of like that. And without giving away the secret sauce, kind of walk people through what that Goldberg machine looks like, right? Like all these pieces that you've got.
SPEAKER_01So I a lot of developers use Python, and I think it's because that that's what the data scientists use when they're dealing with AI. Um, and I I wasn't trained to use Python, but I did realize that I could get the the generative AI models to write in Python, and I have you know gone through those iterations to create front ends where you basically exactly what you described, you basically tell it what you want. You can even upload a a picture of what you want the web page to look like if you're building a front end, and it'll actually write the code for that, and it'll also write any kind of SQL code or back-end code in whatever language you want. And I was just telling someone the other day, if I had the the choice, if if I had the choice of whether or not I was gonna get a computer science degree again, and I was going through that planning today, I think I would just skip the skip the computer science part because these agents are gonna be do be able to do everything.
SPEAKER_00So like natural language input will result in sophisticated coding occurring.
SPEAKER_01Oh yeah. And you know, you've seen, I don't know if you've seen some of these agent platforms where they act like a team. So you have you have one that does the coding, one that does the quality assurance and the testing, and then they they go into a feedback loop where you know one agent's telling the other, well, this is broken, basically what you know, what my buddy was doing. But but there are teams of AI agents that would do that. And I can see people I can see the same kind of process happening in the publishing industry where you have a proofreader and an editor, researcher. To me, that's a that's a less sophisticated problem than the programming one.
SPEAKER_00So I'm pondering that because on the coding side, I'm very familiar with that paradigm you just described. Like it's happening, and you're right. Uh it's much more precise. The tolerance for error is so much low it's smaller in that environment than it is in the written word. So if it's happening in coding, of course it's gonna happen in the the publishing, the self-publishing space. So, what do you see the future of that looking like?
I think we're all gonna end up being creators. I mean, I think that's happening to a certain extent, and we we're not gonna have to really worry about the cost of and the sophistication of having to uh hire people to um get our product to market. So there's gonna be a lot of ways that we can basically skip the the intermediate steps. And I I think with the publishing industry, um I think there's still some things that need to be worked out on the publishing side. Um, you know, like the process that we went through to publish your book to Amazon, um, automating that's a little bit tricky. Um and I haven't even looked at the API side of the Amazon publishing piece, but um that was a manual process. But I think the middlemen are gonna be cut out quite a bit and everyone's gonna be a creator, um, including for you know, if you want to create your own apps, if you're if you can prompt and you can you're good at describing or you know, illustrating what you want as an ed product, these these agents will be able to create them for you.
SPEAKER_00You know, that's a a topic that comes up a lot. How do you get good at prompting? And let me ask you when you first started messing around with the models, would would you say because of your computer science background and thinking and kind of like that type of architecture or whatever, that it was easy and and being, I would imagine, having a career full of defining requirements clearly for others to execute, it did that translate into better prompting?
SPEAKER_01Yeah, I think specifically with the with the context, you know, and the the context length. Um early on with Jasper, I think you had a context length of like 300 characters or something.
SPEAKER_00Yeah.
SPEAKER_01Um, and then you know, the LLM models now their context lengths are getting bigger, but you kind of take a programming approach to setting the context early on um as you're prompting. So instead of just using one prompt, you would at the very first prompt, you would kind of set the stage for the context, and then you can walk the the the large language model through um a process where it's doing some critical thinking and it's got it's got the memory of the process that it's going through to get to the to the end result. So instead of just a single prompt telling it what you want, you kind of want to set the stage and go through the the critical thinking stages to get better output. So in that in that regard, the programming background background comes into play because you're you're doing you're breaking down problems step by step and then turning those into prompts, basically.
SPEAKER_00So in in this scenario you just described, is that a series of prompts or is it a series of instructions within a megap prompt?
SPEAKER_01It's a series of prompts. So if you could think of like a chat session and while you're in chat GPT, you basically your first prompt would would give it a little bit of background and then you would walk it through a chain of thought process, and then the your output is like 10 times better by the end, as long as you have long enough context, then you know the the LLM has the memory to to refer back to those things that you prompted early on to get better output. Nice. I hope that makes sense.
SPEAKER_00Yeah, but none of this does. It's all how where did this come from? How did it happen, right? Like it's here. Um, all of a sudden, and it's only going to get better. So I want to get back to the book thing because for me, as I mentioned, uh we had built this course and we put a lot of blood, sweat, and tears into the course over nine months, and to not be able to convert that into a book was very frustrating. However, we already had the bulk of the material, so when it was time to convert it into a book, it was very easy. What about for an individual who like I mean, you you you didn't have uh foundational material when you were creating that first book, right?
SPEAKER_01My initial goal was just to use the universal knowledge that the LLMs had um been trained on. Um and then as they introduced uh like OpenAIs introduced the the um file uploads, like in your G in a GPT, you can upload files and then chat with those files. Um I started uploading uh documents that were related to background um and and taking advantage of that file retrieval for Ghost Rider. So that's basically the version that I ran for your book. Um the the version that I'm I'm about ready to release doesn't have that built in yet because I'm still doing some more testing on the more advanced version, but I can still I still have enough context area to paste in some background information um in the the beta version that I'm about ready to release. So you basically have a a text window that you can dump your notes into and it will consider that it builds those into the prompts to write the book.
SPEAKER_00So the process for somebody, because it's a self-serve, right? Like I could go in there and if I wanted to do book number two, I wouldn't you wouldn't need to be involved, right,
for the creation part. So that somebody can kind of understand, because if I'm driving right now and I'm listening to this and somebody's talking about writing a book with AI, here's what I'm thinking. I'm thinking that I'm giving it maybe a little prompt, but what I'm getting out the back end is synthetic. It's inauthentic, it's just like some uh computer generated, algo generated series of words that happen to make sense. But that's not the output that's happening if you do it the way that you're doing it. So I want people to understand that it's not it's not just, hey AI, write me a book. That there's the human is involved in this process. The human is directing the the output. So for the human who's interested in doing this, who's listening to this, what does that experience like? What is it, what is quote unquote writing a book with AI using Ghostwriter? What does that look like?
SPEAKER_01Basically, for in ghostwriter.ai, basically, you um you come up with a book title. So you you're filling out a form. It's a pretty simple five-point uh five-part form um where you describe the book. So you have the book title, the book type, and right now I'm doing just authority nonfiction. So it's monetize your expertise by writing a book, um, and then 10 chapters max, so you can choose the number of chapters up to 10. Um, and then you fill in the book description. Um, and then there's a little uh AI chatbot that's that's on the form that what if you don't know how to you can't come up with a book description, you basically do some ideation with that little chat bot. So it'll write the description for you, and you just cut and paste that into the book description field. Um, and then you want to supply it with a book outline, and that little chat bot will help you write that as well. And then additional context, which is your notes. Um, so if you have a personal story or you have a specialized background, you you put that in there.
SPEAKER_00How how much context can I put in for that? Because if I don't know, let's say I was I already had I've been doing public speaking and had transcripts and stuff like that. How much could I feed it? So it's right now it's 50,000 characters. Okay.
SPEAKER_01Um and that. That's kind of the max amount that I can put in without breaking it. Um, without get making the prompts too long. Yeah. Um, and then you can upload the next step is you you can choose your tone and style. So you can upload a text file that has your uh your writing sample in there, and it's your author background. So you'd have an author bio, and that again the chat, the little chat bot will help you create an author bio. Um so it can either analyze your tone and style from your writing, um, you can you can specify a tone and style. So you select from um option boxes basically what your tone and style is, or you can emulate an author. So like if I want to write like Tony Robbins, I just basically punch in Tony Robbins in there. And then the next step, the final step, is defining your audience. So and the chat bot will help you identify your audience. Um so it's like if you're in your your instance, it would be like uh you know, professional or business, right? For the for the the ni the niche. Um and then the final step it would be uh reading level. So you can specify you know if you want it. Yeah. If you don't want it to get too technical, you can you can say write at a fifth grade reading level, which is a pretty safe reading level to make it conversational. Um and that's pretty much it. And then once you have all those things filled out, you basically hit hit the go button and it launches my automation. And the automation will it will generate an outline from the outline that you've provided, and it'll walk through that outline and write each chapter um sequentially. So it's keeping track of the context of the book as it's writing it.
SPEAKER_00So it's got memory a bit. Yeah. Right. Um, so this idea about the tone and style, right? I I did I had never really considered that very much until I
started creating content and especially creating content with a tool like AI, because you want to make sure that the machine, the robot, doesn't sound like a robot. If somebody uh doesn't have that seed material for their um their their style and tone, how would you suggest they go about creating that to use in this situation?
SPEAKER_01So if they have a writing sample, um, if they've done any writing at all, or they could even record their own voice and transcribe it and then create a text file out of that. So you could use that text file to upload um in the tone and style section, and it'll it'll actually analyze that and create a tone and style, come up with a tone and style that matches yours.
SPEAKER_00So I could take perhaps. I mean, I I got a lot of stuff because I'm busting my tail over here creating it. However, if I I know that I this is new for me. So a year ago, I would have had maybe some clips of me speaking on stage from a few years ago. Like there would have been just a snippets here and there, and that's enough of like I could use those to to, like you said, transcribe and create the text doc. And that would be enough seating to get a book's worth of consistent style and tone.
SPEAKER_01Yeah, the longer, the longer the transcript is, the better, the better definition you would get. But I think, you know, 500 words is enough probably to get something decent.
SPEAKER_00That's not very hard at all. And then this bot that would be uh accompanying my my preparatory journey. I have a lot of friends, not a lot, I've got a number of friends who their career for decades was helping a thought leader go from I I haven't have an intention of you know getting building my reputation, they would take them, they'd do the interview, they'd ghostwrite the book, they'd, you know, uh set everything up so that it was gonna hit New York Times and all those types of things. And that was a process, like I know a few guys at $100,000, right? Uh Tucker Max's company scribed, if they were to do something like that. I mean, I don't know what it was, but it was it was five figures to now that included all you know the affiliate relationships and the promo stuff, but even the book alone was uh thousands, ten thousand bucks to get somebody to do this. Yeah, but the process that you just described with that bot walking me through it doesn't sound any different actually than what it looked like a year and a half ago or two years ago before people were even using Jasper to create these books. So that is I you know I hadn't considered that. I I this idea of disruption of the industry was a not something on my radar. What was on my radar was like, oh, this is awesome. This we've got a book now, and it's good and it's out there and it's done. I didn't consider the the entire industry that we bypassed in the process of getting that thing launched.
SPEAKER_01I don't think this could have been a product even six months ago, um, just based on how good it's gotten. Um basically what I did with your book too is I added a layer on top of it. I added Claude, um, Claude 3, Opus, which uh uh so it took the output as it was writing it, it took the output of of Chat GPT 4.5, I think it's the 4.5 preview, and it as it was writing it section by section, it ran it, it told Claude to rewrite it. And so that's how we ended up with your book.
SPEAKER_00Well, I would recommend that.
SPEAKER_01So I yeah, I basically ran the premium model on your on your book, and that was that's a model that I basically have to run manually because I have to babysit it a little bit to make sure it's it's assembling things properly. But I think at some point um in the next couple of months I'll be ready to make that a public beta as well. Interesting.
SPEAKER_00So, you know, with a model constantly improving and and you know, the chatter about GPT-5 and things like that, how is your build going to be impacted by something like that? It's only going to improve it, I would imagine.
SPEAKER_01Yeah, the only thing I'm concerned about is they're you know, they change the they change the API on the back end so often that I want to take advantage of
the latest changes. So there's lots of changes happening. And they they're deprecating a lot of the stuff, but they're keeping it up. So they're not they're not breaking people's stuff, basically. So you can still you can still run the old stuff, but I want the newest stuff because I'm constantly trying to get it to improve. Um, and quality is you know, it's important to me, obviously. So I'm constantly on top of it. So basically I have a version that that I leave running and then I make a copy of that and and make the improvements to it and then swap them out.
SPEAKER_00You know, you said that you've been working on this for eight months, and just for I guess perspective, what has how much has this output improved? And is the improvement you've gotten better at working with the models, or the models have gotten better, or it's both? It's both.
SPEAKER_01Um, because some of the models have gotten worse. So, like Claude between Claude One and Two, Claude One was really good, it was really impressive, but then Claude Two started refusing to give me the output that I wanted. So, like if I wanted to create um persuasive copy, it would refuse to do that and say it was unethical or whatever. So I gave up on Claude Two and pulled that out of my the book writing process. But when and when Claude 3 came out, I tried that out and I was really impressed with the writing. So I've added it back in now. Um, so there's a lot of that playing with all the models, um, playing with the prompting. Um, and then you know, sometimes a prompt will work for a while and it'll break when they change when they change the model. So it's just it's it's constantly I have to constantly stay on top of it and test it and make sure that there's quality output there.
SPEAKER_00How much time do you think you spend like with the models on a weekly basis or a daily basis, even?
SPEAKER_01Well, I've gotten into the habit of I'll go to a model before I go to Google. Um, it took me a while to train train myself to do that.
Um, I've even used the the phone version of ChatGPT, the ChatGPT app to to uh fix my car. You know, like I had a a misfi a cylinder that was misfiring, and I told it the kind of car I have and what what are the trouble what are the the steps that I should take in the troubleshooting process. It knew exactly what kind of engine was in the car, gave me the steps to find which what find out which cylinder was misfiring, told me what codes to look at when I was pulling the codes off the the the engine computer, right? And methodically told me how to go through the steps to the point where I was able to fix the car by myself.
SPEAKER_00This is like coding, right? Like you don't have to be a coder anymore. You don't have to be a mechanic.
SPEAKER_01Right. And I don't even work on my own car anymore. Luckily, this this is an old car, so it it it was familiar with the engine and how it worked and everything, which was impressive.
SPEAKER_00Were you able to use the the did you need to use the vision for that at any point in that process?
SPEAKER_01Uh no, I'm still training myself to use the vision. So like I saw a bird in the backyard and used the app to take a picture of it. And I do that with plants now too, but I'm still kind of trying to train myself to realize that I can use vision for that stuff.
SPEAKER_00No, it's the the limitation, it's it's interesting. I'm seeing the parallel, Hill, because programming, coding, okay, yeah. I don't need to be a coder, but I can get the models to give me output for code. Now I don't need to be a writer, I can get the models to give me output for the book. I don't need to be the mechanic. Now I can, if I'm if I'm trained, if I'm trained to not go to Google first, because Google's gonna say, oh, I got to read an article, and I have to figure this out, right? And what you did was you skip the like Google's kind of like do-it-yourself, DIY, right? And by using the the models to help you with that, it's like DW, certainly DWI. And if it had hands, I would imagine say, dude, hold my beer, let me go fix this for you, whatever.
SPEAKER_01And perplexity, have you used Google? It's the it's the new Google, yeah, as far as I'm concerned.
SPEAKER_00You know, and on that topic, um somebody uh uh it might have been Isar again, but somebody said that they the news story they broke was that ChatGPT had registered a subdomain for search.openai.com, indicating that or at least teasing that they might be entering the search game. If they do, perplexity is gonna be uh shaken for sure. But I mean, it's a it's an obvious next step, right?
SPEAKER_01Well, you remember they used they had a plugin, yeah. They well, and then um Chat GPT or OpenAI had their own, I thought they enabled uh internet access for a while, and then they got sued and they took it away, right? That's probably what happened. Yeah, because of the it was the whole scraping issue. People were complaining about them scraping websites and they they pulled the plug on that. I think it was probably only live for a couple months before they pulled the plug.
SPEAKER_00You know, the the trend that I'm seeing here, the pattern that I'm seeing here is the if I can train myself to consider the models first before I encounter what kind of bird is that, what am I having for dinner? How do I negotiate this deal? Give me some ideas for marketing. If I can train myself there, then truly you're thinking an AI at that point. You're right, and like you're an uber human at that point.
SPEAKER_01The the legal stuff. I had a an attorney that I was working with that was helping me with a case, and um she was telling me, oh, she was using legal speak for something, and I was like, What the hell is she talking about? You know? And I'm like, I wonder if ChatGPT can tell me. So I basically explained the whole situation of my case, and this is what the attorney said. And Chat GPT explained to me what my attorney was talking about, and then where we were in the process of this whole legal proceeding that we were doing. And the next steps are gonna be she's gonna do this, and you know, you're gonna, she's gonna ask you to do this, and then um that's that's basically how the process works. I was like, this is awesome. This is awesome.
SPEAKER_00You know, um, I was seeing uh uh use case in medical, and it was basically the equivalent, it was the patient and the doctor, right? And I'm not an attorney, I've signed plenty of contracts in my life and could probably wing it if I had to with Chat GPT, but now I have that advocate, that that intermediary that's going to make sure that um, like I was in some negotiations with some pretty big stuff with the company and uh was able to certainly save literally thousands of dollars in perspective. Now I wouldn't say, Your honor, you know, speak into the mic so that Chat GPT can give you a response. However, in the in this phase where it was a lot of discovery, like understanding the situation, working out the nuance of the deal, it was what I brought to the attorney when it was time to bring the human in the loop, um required minimal uh modification, at least to that point. There was now, obviously, the attorney took it from there and did their thing. However, what I brought to them was save them hours of research that would have been at you know 350 to 500 bucks an hour. And I learned in the process. Now I understand what's happening. I'm not just putting my uh my agency in the hands of uh somebody who there's an implied like difference in strata. I'm the attorney, I'm the doctor, I'm the expert, you're the whatever. You know, now you've got an advocate in your pocket.
SPEAKER_01Yeah, just preparing them, just preparing the mater the material when you have a legal situation like that. Um, you know, journaling all the events that happen leading up to this legal matter, um, and summarizing that for your attorney. It's just perfect for that, you know, because then you can basically journal what's happening as it's happening, and you're like, you don't have to remember it. And and ChatGPT can basically summarize it for the attorney and break it down into bullet points and give them give them the whole layout of everything that happened. It's perfect for that.
SPEAKER_00Yeah. You know, we've covered a lot of topics, but I'm seeing that the theme is emerging of a thinking in AI, of all of these different applications. And again, you said it yourself, you're training yourself to use the models first and not go to Google, which I mean, it's like everybody in the world, except for I don't know, 3%, whatever search volume Google doesn't have. Everybody for the past 20 years has trained themselves to if I need something, I go to the search bar and Google, right? This is gonna be interesting to see what happens.
SPEAKER_01Let me AI that for you. Yeah. Yeah, exactly. Instead of let me Google that. Yeah.
SPEAKER_00They're gonna be in trouble. So as we're wrapping up, Chris, I want people to understand a little bit more about um if they were interested in exploring writing a book for the purpose of building up their credibility in the marketplace, for being identified as somebody who is, oh, they're professional enough to have a book. I mean, I know that I know the credibility that a book brings to the table. And a lot of the people that are listening to us are career people or business owners. What's the next steps for them?
SPEAKER_01Decide who your audience is um and you know, who your ideal client is. And you can use AI for that as well. Um AI is very good at telling you at building avatars. So you want to you want to decide who you're speaking to, and that would be in the form of um figuring out who your ideal client is. So you basically could use Chat GBT to describe your ideal client. If you can imagine what kind of business you would have if it was a perfect business that, you know, the type of business that would make you happy, the happiest. Um, and you could plug once you have that, you you could use that in my tool, or you know, if you wanted to write a book manually, you could do that too. Um, you you can go through ChatGPT and write. Might as well write it yourself at that point, though. You know, yeah, there's a lot of cutting and pasting. Um, but that's where it all starts, is basically your ideal client.
SPEAKER_00Let's say I've got my ideal client. Where do I go from there?
SPEAKER_01So uh basically you'd plug that into my tool. Um and which is at ghostwriter.ai, rider without the e. Right. Ghostrider.ai, ghostwriter without the the e. And then um for your audience, I'm willing to offer a 25% discount with uh discount code Chris25. Very generous, thank you. Yeah, discount code Chris25. Um, and then just go to ghostwriter.ai and and click on the the buy now button and you can enter your coupon code into okay, and I'll have that in the the show notes for those of you who might be driving or walking the dog right now.
SPEAKER_00And then what is that? So they they sign up and then like how soon before they could have a book? If they've got if they know who their ideal customer is, and then they're gonna go through um the steps that you mentioned and kind of partner with your bot to help them get that input. Once they get that stuff done, and that process might take them what?
SPEAKER_01To fill out the form, it could take a half an hour, and then um, and then within an hour, they'll have their first draft. So a total of an hour and a half, and it's you know, 30,000 plus words, 10 chapters.
SPEAKER_00Yeah. So, guys, to see if you're curious about the output, go to Amazon and go check out uh go search for chief AI officer, Chris Daigle, my name. Um, and the Kindle version is gonna be free. Just get it. And I think that now keep in mind, I I had a lot of contacts. We had an entire course, an entire training program that was used, and it extracted information from there. So um, and then Chris was kind enough to run it through uh simultaneously Google and I mean uh GPT and Claude. However, that was generated by AI. And when you read that book, like I said, get it, it's for free. When you read, pick a random chapter, and if you didn't know, you would assume of course Chris wrote, like Chris wrote every single word in that. It's very impressive output, Chris. You've done a good job. Um, so Ghostwriter without the E, Ghostwriter.ai, and then when they get there, Chris 25. Awesome. And then you guys can join the club of the published, like I have. Uh it's very, it's actually, even though it was AI assisted, I'm still extremely excited that I now have that's under my belt. I have a book on this, and thank you so much for that, Chris. Congratulations. Yeah, you were a big part of that. Thank you, man. All right, everybody. Thank you so much, and we'll see you on the next episode. Thanks for tuning in to using AI at work. Don't forget to subscribe for more conversations about how to use AI at work. And a special thank you to our sponsor, Chief AI Officer, for empowering businesses with AI education and training. Visit their website for free AI readiness assessment and AI strategy guide to help you get started using AI at work. That's www.chiefaiofficer.com. Well, thanks to our producer, Evan Desponier, for making this episode possible. Follow us on Twitter at the handle usingai at work and visit www.usingai at work.com for free resources to help you harness AI in your role.