So What? Whisper and Claude for generative AI content repurposing

Well, hey there. Happy Thursday, everyone. Welcome to So What the Marketing Analytics and Insights Live Show. Today I am joined by both Chris and John. It's been a while since the three of us were all in one place.

And of course, next week that will change again. But at least for this week, we're back together. The band is back together. How is everyone? Good.

We have to put together a sophomore album, right? We have to get back on the charts. Everybody's giving up their grudges and come back together because we need the money. That's right. And then Chris will go take it on tour next week.

Exactly. Going on tour. That's right, getting on the bus. Um, but this week we are talking about using artificial intelligence for content repurposing. Specifically, we'll be looking at Whisper and Claude, which are two different artificial intelligence tools.

I'm sure Chris, you'll tell me that there's hundreds of tools out there that do similar things or you know, do pieces of things. But today, specifically, we're focusing on whisper and claude. So where do we want to start? Let's start with the purpose. Let's go to the first of the five P's.

Uh Katie, what is the purpose of content repurposing? The purpose of content repurposing is basically to get more bang for your buck to scale. So you create something once and then you reuse it in multiple different ways to reach different audiences on different platforms. So it's the purpose is efficiency, the purpose is scaling, and the purpose is broader reach. Okay.

Um but does that really that that doesn't really fit into a user story very well like that, does it? Uh it could fit into a few different user stories. So as a CMO, I want to repurpose my content so that I can keep costs down. Or as a CMO, I want to repurpose existing content so that I can find efficiencies in my process, or so that I can have my uh team focus on other more meaningful tasks. Got it.

Okay. I like that first one because that segues nicely into the process that we're going to talk about today and the platform. Um, because there's two different avenues you can take. There's an easier avenue that costs money, and then there is a more technical avenue that costs no money. And so the question that folks will need to entertain is okay, which which road do I want to take?

Well, and this goes to something we were talking about in our free Slack group, Analytics for Marketers yesterday, uh, which you can join at trustinsights.ai slash analytics for marketers. I was asking the question of how do you decide which AI tool uh solves your problem? And it was in some ways it was almost a trick question because you never want to start with the tool. You want to be very clear about the problem you're solving. And so with the user story that I gave you, Chris, as a CMO, I want to repurpose content to keep costs down.

Adding an additional tool might not solve that problem for me. Exactly. And we haven't talked about the the second P yet, which is uh in this in this journey, if you will, the people, it depends on their skills, right? There the easier way costs money, but does not require people to be technical. The the lower cost way from a a dollar's perspective requires your people to be a lot more technical than the easy way.

But it sounds like then there's a trade-off because then you are asking for technical skills which could cost more even though the tool itself could cost less. And so those you need to factor in if your if the purpose is to keep costs down it's not just looking at the cost of the tool it's looking at the cost of the people who have to operate the tool as well. So you may be trading low cost software for higher cost talent. Exactly exactly so let's talk about the process because that makes logical sense before we dive into the the platform what we want to think about is the content that that is the richest is typically stuff like this right like a an episode of So What or an episode of Marketing over coffee or an episode of Iner Insights where we as people are saying a whole bunch right we talk anywhere from 150 to 200 words per minute you know depending on how much caffeine we've had that day. And when you have a 30 minute podcast or a 45 minute live stream you're talking about thousands and thousands of words.

That's a lot of content. Now, not all of those words valuable, right? There sometimes they're you're discussing, you know, for example, like how do you improve the quality of chickens you can get? Um, but those words are still content that you can repurpose that you can be part of the repurposing engine. So the first part of the process is identify what content you want to repurpose.

And I would suggest for marketers who have content laying around, particularly podcasts, videos, webinars, you know, if our B2B friends, uh, live streams, and especially uh if you've done a good job with your public relations, guest interviews where you've been the guest in other places. Those are all the I would say the starting points of the process. John, do you know how many words per minute you speak? Yeah, we are in the over-caffeinated category and get up to 150, 160, and 180. And one thing, you know, from podcast research, your brain can take like up to 2x.

You can you can handle much faster. Um, but on the flip side, I have more than one one-star review on my audio book because people say it was way too fast and they couldn't take it. So you have to play to the lowest common denominator on that, and and that's the way to go. But it's really interesting. I hadn't thought too much.

I like that idea of other interviews on other channels, being able to summarize those and bring them back as content on your side. That's a cool angle. I had never thought of that. Exactly. Um, so in fact, one of the interviews we're going to be working with today um is an interview with Katie uh when she was on the the B Squared uh TV show, the B Square TV.

And so we're going to use that as our example, but they'll you know we there you could do this with anything. So let's talk about the materials that you're gonna need, sort of the the the mise on plus if you were cooking. Um for today's for today's cook, you're gonna need um some kind of large language model can process a lot of text. So the two that are are uh capable of this right now is GPT 4 from OpenAI, which is having some issues right now. Um, and one called Claude 2 from Anthropic, which is for today is my choice for doing this kind of work.

Claude is not a good as good a coder and doesn't do as well as with reasoning and and it doesn't do as much well with like mathematical logic, but it is really good at language, and it has uh a larger context window, has a 100,000 token context window. So for folks who are unaware of what that means, a context window is essentially uh a large language model's working memory. How much can it remember for starts to forget stuff? If you remember in the old days when chat GPT first came out, you could be typing and having a conversation with it, and then like 10 minutes in, it just starts forgetting like things you've talked about. Like what happened?

Like you I told you already, this is a blog post about this, and it's like huh. What happened was the text kind of scroll away and after a certain point it forgets what happened because it can only hold a certain number of words in memory. Claude uh can hold 100,000 tokens, and a token is about a four-letter segment of a word. So the word of would be a complete word. The word example, the first token would be exam, and the second token would be PLE.

So Claude can hold on to about 60-ish thousand words at a time, which makes it ideal for dealing with long transcripts and things. If I were to put on my tinfoil hat, uh, which I do like to do from time to time, because I do love a good conspiracy. My tinfoil hat side would say that perhaps the makers of these tools purposely made these tools forget what you talked about because that's what it's like to talk to an actual human, and this is their step towards making these tools more human-like and sentient. Because I mean, how many times have you talked to someone and they're like, wait, we talked about this already? Wait, huh?

Wait, what wait, what were we talking about? I got distracted. And so, of course, obviously, I know logically that's not what's happening, but tinfoil hat version of me uh was like, Oh, maybe that's how they're trying to make it seem more human. There is a whole rat hole, it's a very deep rat hole uh around things like memory and and memory chains and and you know the lang chain system, which we'll do another time. Um yeah, there that is a thing.

So you're gonna need some core kind of large language models for access. The second thing you're gonna need is the media itself, right? So have your YouTube channel, have uh somebody else's YouTube channel where you are a guest on it. Please don't do any of these techniques with content that isn't yours, right? That's unethical.

Um, so you know, if you're if you are the guest on someone else's show, that's fair game because you're there to provide value, and you're and and presumably, yeah, at least I don't know about you guys, but I don't get paid to be a guest on other people's shows. So uh my fee is I get to use the media how I want. Um, but yeah, don't you you technically can use these techniques with content that is not yours. You you ethically cannot, and legally it probably not. I think that's solid advice.

And now comes the the third and messiest part. Um, how you turn video into text? And there's a couple of different ways to do this. The first thing you need is some way to grab the video itself. Um, and there is an there are paid desktop tools that you can do this, like uh there's what's called YouTube downloader.

Um, there are also open source tools. There's one called YTDLP, YouTube Download Program. That if you are technically savvy, you can download this code and run it on your computer. And this will allow you to give it uh at the command line a very short command that would be goes like this do go ITD YT DLP, and then the the URL of whatever uh content you want to download. And that will grab that content from the internet, assuming it's publicly available, and put it locally on your hard drive.

But I would assume if you're you know, and this is you know, every every situation is going to be different. If you are looking at your own content, you likely have the source file that had to get uploaded to YouTube in the first place. Um, you know, things don't just magically appear on YouTube, they have to come from something. And so for you know, for us, this live stream, you know, it gets you know brought into YouTube after the show, but I have all the source files. So if I have that, I don't need to go through this process, right?

That's correct. This would be if you were guesting on someone else's show, for example. Got it. I just want to make sure I was clear on the use case. Yes, exactly.

Or you know, maybe uh you're like me and you were you're you had you published a whole bunch of stuff 10 years ago and you've lost all those files because they're they're in like five five MacBooks previously, you know. You know, either way, you can do that way, or if you do have the source files yourself, that that's a great way of doing it. The second thing you need to do is convert the video to audio. Uh, and again, there's a number of different ways to do this. If you are familiar with and capable with Adobe Premiere or iMovie or Camtasia, you can do it in those tools.

You can load the video up and you can say export to MP3 or WAV file or whatever. Um there is an open source tool, uh very, very powerful one called FFmpeg. That again, it's uh it's an amazing tool that will convert pretty much any media into almost any other media. So that's the tool that I typically use. But again, you have you almost certainly have a piece of software on your computer that will convert a piece of uh video into an audio format.

So why do I why is that step necessary? That step is necessary because a lot of the transcription tools need uh audio in order to work. They can't ingest video natively because they're not equipped to handle the you know multi-gigabyte files that that a lot of uh these videos are. Got it. You know, we are we're recording this in in HD, uh full 1080p HD.

So this file, this you know, the the 35 45 minutes we're gonna spend together today is gonna weigh in at about three gigabytes, and no one wants that crossing the network if they can get a 45 megabyte MP3 file instead. I mean, I'm always saying that. Aren't I always saying that, John? It's all about the gigabytes. All right, so we have our video file.

We have an audio file. Now what do we do? Okay. Fork in the road time. If you want a the easy but costs money um approach.

There is a fantastic piece of software uh called Otter. Otter.ai, which is one that we've used actually at Trust Insights for actually since it came out. And all it does is you drop your audio files in, you pay your uh, I believe it's I want to say it's like 60 bucks a month now to do this, and it will take your file and transcribe it. And then from there, you would export it as a text file. You know, that's that that's probably the easy solution.

And by the way, there's some really cool new features in Otter that have just been added relatively recently, one of which is Otter Chat, which is their um integration of a language model. So you can do something as you know simple with this, like um, what are the major talking points from this episode? So this is our last week's uh so what episode, and it will go through and attempt to uh distill out those talking points, which is is nice and handy. This is really good, by the way, if you are um recording with permission, uh client calls, and then you want to like get action items from your your meetings. This is a phenomenal way to do that.

Well, and as we're in the spirit of uh content repurposing, um, having something like otter chat summarize the main talking points, uh gives you an opportunity to repurpose these small snippets on social media where you might have uh a character limit or you just want to have a very short summary of here's what this thing is about, rather than having to rewrite it over and over again. Exactly. Now, if you want to go the the free route, um there's a package called Whisper from OpenAI. So this is the same OpenAI that makes chat GPT, but they open sourced their their Whisper software a couple of years ago, actually. I believe it was a couple of years ago, it might have been a year ago.

And this software, again, when you download it and compile it, runs locally on your computer. You it will feed the audio files you're making to Wisper. And what it does is, and it does some things that that Otter and other tools just are not capable of. Um, it will go through and it will do a transcript, make your subtitles for for YouTube. One thing that it does that I've not seen any other software do even closely well is it will automatically translate.

So if you have uh audio in another language, you can feed it the way and it'll automatically translate into a target language, which is super super cool and very helpful if you're consuming any kind of international media. Um but this is this does what Otter just did too, which is just does the transcript and makes you a sell you a nice text file. Okay, so we started with a video of us talking. We started with some kind of an interview. We got the source file.

We basically converted the video into an audio file, transcribed it. So now we have the written content from the original video. What do we do now? Okay, so the next step is you find that video file, that um text file that it made. Uh, let's go ahead and go to our text files, and we load, we just attach it as an attachment into um into Claude.

And now the question is what do we want to do with this, right? What kind of thing would we want to do? So I'm gonna use a uh a prompt that's uh I use for this sort of thing, and I'm gonna say we're gonna summarize the transcript. This is a conversation between Brooke Cellus of eSquared Media and Katie Robert of Trust Insights. The transcript is not diorized.

The speakers from the words. Katie and Brooke talk about equal amounts of time. So what we're gonna have to do is we'll say first you are going to draft a blog post in a professional tone of voice that summarizes the transcript. Use active voice avoid adverbs avoid business jargon. These last three commands are really important because otherwise you tend to get sort of a very bland sort of uninteresting summary whereas if you tell it like hey you can't use adverbs and you're not allowed to use passive voice it it tends to create better results.

Oh we'll fix that um actually it fixed it on its own um oh okay so now what it's got doing is it's taking this this multi-page document here and it is spitting out essentially what um what we what you and Brooke talked about so you talked about predictive analytics empowering marketers the two main types of predictive analytics for social media marketers um you gave the example of using time series um so this is essentially what the the the the discussion was about now we would say now write out the top five bullet points from the transcript time driver analysis times use analysis. Predictive analysis, clean customized analytics data is crucial for accurate predictive and predictive analytics, allows markets to be proactive rather than reactive. This looks good. Okay. Next, create five different tweets of 140 characters each that could be used to promote the viewing of the original episode.

Be sure to use what is the B squared handle. Is it hello b squared? I believe so, yes. Hello, B squared, and at trust insights as the Twitter handles. And use at least one hashtag in each tweet.

The URL should always be present. Use trust insights as the URL. Let's see how it does. So you're going through this in like a stepwise. Do you have to go through this exact set of steps to get to like the five tweets, for example?

Do you have to first you know clean it up and say, you know, provide the summary, you know, we don't know who was talking when, then the fullet points, and then I'm wondering: is there a process to getting to this set of content, or can you put in the transcript and say give me five tweets? You can put in the transcript and get and say give me five tweets. You can absolutely skip to that step. Um it there is a slightly higher chance of hallucination if you go straight to the the end. Because one of the quirks of language models is that they need runway to think.

They need time to think. And the more processing and input and output you have them doing, the better their thinking tends to be. So hallucination is basically that unfocused uh output that you get back. Yes, or just outright lying. Well, it's a machine, it's not lying, it's just not giving you the right information.

Right. Um, exactly. I love what you said about focus. It is definitely about right, because it's like the tenth query is always going to be more accurate than the first because it doesn't, you know, it's still hunting around to try and figure out where it's going. Exactly.

So now we have five lovely tweets. And these are actually pretty decent. Like I would be okay with with putting these up on our social channels. Okay. Yeah.

So now we've gone through and the last thing we can do uh is I'm gonna say, let's take that transcript. I'm gonna say, do not summarize refray rephrase the input text, only fix grammar spelling and formatting. Right. And we're gonna have it try to process the actual transcript itself because it comes in as a you know just a big pile of words. Um and by having it go through and start to uh process this down, it will try to clean it up.

Now I can guarantee you it's going to get the diarization wrong, which is the assignment of speakers because I'm using the whisper version. Whisper can't in its current version do speaker differentiation. So if you're doing speaker, if it's important to delay who's speaking, you either have to give it those explicit instructions or you use the the version that comes out of the paid product, Otter, which has the speakers already delineated, and then you can uh then it will clean that up. But this is just an example of how you would now use this to make the maybe a longer form transcript for your website. So if you think back, for example, to um maybe earlier podcasts that we did, or maybe you know, in John, in your case, it would be you know, episodes 100 through 600 of marketing over coffee from you know 10 years ago.

This would be a great way for us to be able to take that those old audio files, get them transcribed through Whisper at no cost, and then have massive amounts of content for the marketing over coffee uh website. Yeah, it's funny because it is some of the we've used tools over the years that are so horrible. It would you could even just run a cleanup on some of the existing ones. I'm sure they would actually come up better. Exactly.

Now, what we've done, we've done a lot of this this step by step piece by piece. One of the things that um if you again, if you have technical access to technical talent on on team, a good portion of this process can also be automated, a good portion of it can be um glued together to the point where all you're really doing is copying and pasting into a system like uh anthropic. Actually, Anthropic itself has an API. So if you are technically skilled, you could do the entire process from beginning to end. So I have a piece of code that I wrote that essentially takes in the video URL and it processes all the steps up to Anthropics Clause.

So it will download the video, transform the audio, it will clean it up, it will run through Whisper, it'll create the transcript, and then all I have to do is go take that and to put it in a clause, and eventually I will take um I will have a piece in here that will talk to Anthropic's API directly. But that's the most advanced version for scaling your content production. If you've got 200 episodes of any of your insights, you probably want to have at least a good chunk of it automated so that you know the amount of time you spend on is is minimal for the processing side. So let's talk for a second about marketers who aren't Chris Penn, uh marketers who are more like myself. Uh John sort of straddles the two worlds between me and Chris.

Uh so you know, we'll see what side of the fence you land on, John. But you know, the process you just described is not something that feels attainable for me. I can't code. Um, you know, so I would be doing it in a clunkier way. I've also gotten a lot of sales pitches from companies who've stated that, like, oh, I listened to your podcast and I want to repurpose this content for you.

At what point do marketers or companies rather start to think about investing in doing it themselves versus bringing on a company or an agency to set up a system for them, you know, to either fully do it and hand them back different kinds of content or to bring them, you know, as you were just saying, like up into the point of just dropping the file into a system like uh like Chat GPT or Whisper or Claude. This is gonna be the answer that we give all the time. It depends. Um, and it depends on really on the purpose. Uh, you know, this that first P is really important.

If this is something that you're doing just for maybe SEO purposes and you don't have a ton of content, then you might want to look at one of those all-in-one tools. Just um because their costs are not egregious for the most part, you know, 100, a couple hundred bucks a month. And if you're doing a piece of video content a week, this process, this process that I do, like for example, Katie, you could do most of it with otter and and and Claude, right? The only part where I think would be a sticking point. Actually, no, because you have all the video and audio files.

So you could do pretty much all of this. If you're doing one file a week, I would just do it yourself, right? There's the um if you're if you have to do hundreds of files a week, uh, maybe you're a media company, uh, then yeah, you probably want to look at some kind of system that it really was souped nuts and that critically had someone you could call for help when you know when the plumbing got jammed. Uh so John, is after seeing all of this, are you now sort of considering going back to those older episodes of marketing over coffee and repurposing them as fresh new content? Yeah, I mean, that's always been on the list is to try and get more of that stuff on the library.

Um, you know, unfortunately, the website traffic is not primary income generation, you know. It's really more about getting the content in the advertiser square. So it, you know, keeping the blog up to date is pretty low on the priorities for getting stuff done. But you know, I do know there's podcast networks where this is it's become insane. Like they have millions of hits a month because they've you've got now five, 10 years of transcripts up there or whatever.

So it can definitely be a path if you just want to get raw tonnage for advertising, especially if you have a ton of content. It's a great way to go. Yep. The go ahead. There's extra value to for marketers where you don't control the source content, right?

Um, so real good a simple example here. This is one on my blog. I was on Mike Stelner's uh social media examiner show, and you know, it was a it was a fun chat. You know, he put the video up on YouTube. And so what I did was I did exactly the process we just uh went through.

I said, okay, summarize the show, right? There's a big old warning up there saying it was in from May, so it's already out of date. Um, but here's the major bullet points. Here's the video itself, and then here is the machine transcript. Now again, I feel comfortable doing this because I was the one providing you know 95% of the content for the show.

Uh I have another one I did with Evan Christel. So for me, this is a good way for me to reuse the time I spent on somebody else's show that I don't necessarily get a lot of direct value out of. We get exposure to their audience and things like that. But um, from search purposes, this might be a way to take advantage of this. I would even say this is probably something that from a process perspective, I would also eventually want to be able to do on the Trust Insights website, put it right on our blog too, because hey, why not?

It you know, we'll get it get as much mileage out of this content as we possibly can. Uh any kind of guest appearance where you've been on shows, Katie. You know, you've been on you know marketing props, you've been on B Squared, uh, you've been on uh Martech, you've been on a whole bunch of these uh shows talking about things. That you gave up your time um essentially in exchange for exposure. But we could then take the words that you had to say and put them to put them to work again.

Ironically, uh I've done quite a few podcast interviews recently that will launch uh soon. And the question is always, you know, what can I do with generative AI? And hey, look, it's a it's it's like very meta of itself, where we're using generative AI to repurpose the content as we're talking about generative AI. It's it's like conception, except with blog posts. Yeah, not nearly as interesting.

Not nearly as interesting. Um so that's the that's the structure that I would recommend. You can use, for example, you can use uh Claude too for just repurposing other stuff too, uh, and for doing advanced editing. So you could take old blog posts, perhaps, um, and have it refresh them, have the update them. Uh so for example, you could take a blog post that was about universal analytics.

And as long as you had your own text file, like we did with the transcript, you had a text file. Here's everything that's changed since blog post came out. You could tell Claude, here's the original blog post, here's everything that's changed, rewrite this blog post using Google Analytics 4 as your knowledge base instead of universal analytics. Sometimes it will work, sometimes it won't, but it is is capable of at least that substitution logic to go ahead and do those rewrites. Um we were talking in Analytics for Marketers earlier today, uh, which again, as Katie mentioned, if you haven't already been there over there, go to TrustInsights.ai slash analytics for marketers about developing a prompt to do sensitivity reading.

So in another community we're in uh the Spin Sucks community, someone shared this really nice uh piece of background information about uh decolonizing language, uh nonviolent language, demilitarized language from the American Psychological Association. And I said, okay, Claude, here's your knowledge, here's a prompt. I want you to read through this blog post I've written and identify any problematic language and tell me how to fix it. I put what I put our so what transcript from last weekend, and it said, This is a great post, no changes needed. I'm like, thank goodness.

And then I put in an episode of All in the Family, the 1970s TV show. And it's like, hey, here's a long list of problems. Well, I mean, that one we knew. If anyone under if anyone knows the TV show, they know that would be problematic. But I understand that for the sake of example, uh, it's probably a good one to use.

But yeah, no, I think, you know, it's interesting as you're describing sort of the uh the use case of converting Google Analytics content to Google Analytics 4, but you have to first list out everything that's different. You know, in those cases, I can see pushback from writers saying, wouldn't it just be as easy for me to rewrite the content myself? And so this is where you have to take it on a case-by-case basis of how much needs to be written, how many versions need to be rewritten, for what different audiences, the different tones, uh, the scale of it all, versus using uh a system like Claude to do sensitivity reading, that seems to me like a really good use case for all of your content, you know, versus bringing on a person. Now, I would highly recommend, you know, consulting with an expert to create those sensitivity prompts to make sure you are not inadvertently introducing new problems into your content and that you're getting the language correct. But once you have that initial consult done, then it's just a matter of rerunning the prompt on all of your content over and over again, and that's where a lot of that automation comes in.

Exactly. And here's the thing. As we saw with Claude's interface, there it's got that little paperclip icon where you can attach files. If you are a smart marketer and a clever marketer, you will start building libraries of knowledge that you can drop into language models, right? Maybe you have a uh you know just a running set of notes.

We in fact, I remember back in the day when we worked at the agency, we had one of our our team members wrote like a 22-page document on everything she learned when she was taking the Google Ads course, right? And she just summarized it, boiled it all down for the team. And we were like, wow, this is really impressive. Um, today, I would tell that same team member, this is awesome. We're now going to use this as training data for when we use a system like Claude to say, okay, I'm gonna write a blog post about Google Ads.

Here's all the background information that Claude's gonna need to write an intelligent post or chat GPT or the system of your choice. But if you uh if you're a marketer, just like we talked about you know plenty of times on on any year insights, which if you're not subscribed, go to trustinsights.ai/slash ti podcast. Not only should you have a prompt library of the prompts that you've written that work well for you, but you should also have a training data library of a valuable background information that can really help um make models do better. It occurs to me, so you know, John, off the top of your head, how many podcast episodes are there of marketing over coffee? Uh 730-ish.

So it strikes me that if you wanted to build a marketing over coffee, sort of branded toned model, you certainly have enough cut you have more than enough content to work with because it's always you consistently hosting it and you know talking about it, like you could build a John Wall large learning model very easily because you have enough volume of content to do so. Yes, and I see a file pile here. I think there's something we have so much content. Yeah. I think that you know it's it's interesting because John, you had said that you know, updating the blog is such a low priority with the advances in this technology.

Do you think that it's an opportunity to use some of the automated processes that Chris has outlined and bump that up higher on the list because it's not as much of a burden to you as the individual? Yeah, and then there's the whole value of using that as training data, like you said, to have something that could answer questions or come up with new topics. That's really where you know there's also some upgrade to that besides just SEO, which you know, in itself does bring in money if it's done right. So yeah, it's all good. Think about this.

John has had some of the the biggest names in marketing, the most successful people in marketing on marketing over coffee. John has a training library to make a blog post that sound exactly like Seth Godin or David Muirman Scott, or you know, the name of person of your choice because you have their language, you have the the uniqueness of the patterns of the way that they speak, and you can distill that out. As long as you have a good enough prompt, you can distill that out with these tools and then uh reuse that. So you may you might not want to write exactly like you know another person, but you could certainly coach the tool to say produce content in this style. And if you know that you're gonna be you have an opportunity to present that content to that person's audience, maybe as a guest blog post or something, what better way to do that than to give the audience the information you want to share in a tone and in a style and in a voice they are accustomed to.

Yeah, match it as it goes. Now coming soon, our virtual conference with all the biggest names. It's it's funny, Chris, that you went that route because my first thought was, you know, John, you get pitched for guests all the time. And sometimes you're not quite sure if the topic would be a fit. And so I could almost imagine you training using the content as a training library and then spinning up some kind of a chat bot to help vet potential guests where they put in their topic and say, This is who I am, this is the topic.

And then the chat box will come back with additional questions and help you screen in or screen out potential guests, sort of taking that off of your plate to have to do the dirty work to say, why would you pitch me this topic? It's definitely not a fit. Like let the chatbot do it. Oh man, yeah, I'm totally on board with that. Because I can't do flag words, you know, it can't be that basic.

I can't just be like, oh, if you're a branding guru, you know, that goes in the trash bin because that still gets used for some great people. But yeah, to be able to have AI be like, oh yeah, this is a branding guru and you know, formerly franchised chicken shacks, you know, this is obviously not somebody that is gonna have a story we want to keep. So yeah, I that's a really interesting idea of being able to kind of filter out the the other automated generated stuff that's gonna clog up your box if you don't come up with a better way to handle it. Just let the bots fight it out and then they'll come back to you with an answer. Yeah, I just want the three good ones.

I could care less about the rest of the fighting. Yep. Yeah, these tools are capable of repurposing content in all sorts of different ways, including ways that probably no one has ever given any actual thought to. One thing I was playing around with earlier today, which I meant to tell you two about, but I forgot. The people that we love working with, our our clients, and extracting the LinkedIn profiles, putting them in a text document and feeding that to Claude and saying, You are a sales consultant.

Your first task is to review all these different LinkedIn profiles. Here's the who we think our typical buyer is. Help me understand the buying profile. Like what do all these LinkedIn profiles have in common? Because I don't know.

I mean, I can make some guesses, but by having all that knowledge, their backgrounds, their education, the you know what they've posted about, that's super valuable for finding connections in text that we can't because we just can't hold that much information in our brains all at once. When you have a 100,000 token context window, 66,000 words, you could put uh 500 LinkedIn profiles in there and develop a buying profile from it. You don't have to give away the answer live, but did it give you an answer? Just a yes or no? It did give me an answer, and it did not the answer did not surprise me.

Fair. Um if you look at our client roster, it you know, it says, hey, this is so your client roster. It probably is. Um, but then you would use that to um do alignment checks. And this is something that I use.

Uh, if you are not subscribed to our newsletter, go to trustinsights.ai slash newsletter. Today, um we sent out a promo a promotion for Google Search Console for our Google Search Console course. I wrote the first draft of that copy, and I was like, okay, cool. And then I wrote out the the information, the prompt from this LinkedIn exercise, and I said, I want you to review this sales pitch email against our buyer profile and make suggestions about what you think I could have done better in the copy for the sales pitch. And it it changed the text.

What you saw, Katie, when before we sent it, was after AI, and it was so much better than what I had written because I was going from my perspective, like, hey, this is a cool thing. This is this all this, and and the AI is like, no, you're your prospects won't care about this. Well, you know, it's interesting that you say that exact phrase that it was from your perspective. I think that's the trouble that marketers in general have not writing it from the user's perspective. We write it from our perspective naturally, and maybe don't realize that we we think we're speaking to the audience.

We think we're telling them what they need to know, but we're still introducing our own set of biases into the content. So I think that is a really interesting use case. Mm-hmm. Um, yeah, we can I can show you just a little bit from chat GPT. I said here this was the original pitch, right?

Um, and then it went through and it said, Hey, um, you've got some address some pain points, replace this with this, replace this with this, you know. And so this is this the copy that eventually made it into the final. It's a um it said instead of just saying, hey, it's got 12 lessons, it said no comprehensive insights and 12 lessons, two hours of focused instruction, a certificate to validate your newfound knowledge instead of just hey, get a certificate. Like it it changed the language. Um, I didn't even think about you know writing, for example, the closed captions.

It says it's it's we we foster inclusive learning with uh with accommodations. Um and in this of the and more, which is you know typical sales languages analysis and the confidence to make strategic decisions at the age of AI, right? So the because I gave it a good buyer profile um this is content repurposing too yeah i i gave it a that good content that we had from linkedin profiles turned it to a buyer profile turned that into a sales pitch alignment tool and now I have a better pitch that went out now of course the test will be if anyone actually buys it but sure at least at least we used the tools to repurpose content and refocus content to the way that the audience hopefully is more receptive than than what's coming out of my brain makes sense totally makes sense so to summarize if you want to use artificial intelligence to repurpose your content for content repurposing uh purposes uh it's absolutely possible to repurpose uh with purpose um so basically there's a few different ways to approach it you can build your own process using code and open source tools that's a lower cost version but it increases the amount of dollars spent doing the thing versus other tools they can sort of do it start to finish for you the tools themselves will cost more money but the labor involved aside from a sort of a learning curve and training will be less overall or the third option is to bring on uh a company like trust insights to help you set up that process to help you evaluate what you have what content you can repurpose and build out the process help you select tools or even get you 90 or 100% of the way there, and then all you have to do is just do something with the content. Um, so if you want to reach out to us for one of those options, you can uh find us at trustinsights.ai slash contact, and you will be uh paired up immediately with our chief statistician, uh, Mr. John Wall.

Right here. Just follow the line. And I think on that note. On that note, thanks for tuning in, folks, and we will talk to you next time. 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 slash TI podcast and a weekly email newsletter at trustinsights.ai slash newsletter. Got questions about what you saw in today's episode? Join our free analytics for marketers Slack group at TrustInsights.ai slash analytics for marketers. See you next time.