Leveraging AI

136 | Scaling AI: Build your own custom GenAI Engine in three easy steps with Pam Boiros

• Isar Meitis, Pam Boiros • Season 1 • Episode 136

Share episode

AI is everywhere, but is your marketing team ready? With AI tools becoming essential to modern business, developing AI literacy across your team is no longer optional—it’s an urgent priority. In this webinar, you’ll learn how to build a custom GenAI engine that boosts your team's efficiency, creativity, and competitiveness, without compromising your brand’s identity.

GenAI is a game changer for marketers. Whether you need help with drafting, editing, ideation, or personalization, GenAI can do it all. But the risks of generic content and AI hallucinations loom large. So, how can you harness the benefits while safeguarding your brand?

In this episode of Leveraging AI, Pam Boiros joins us, a thought leader in AI and marketing, as she guides you through a live demo of CustomGPT.ai, a tool that lets you train AI on your own brand content. Pam will walk you through the simple setup process and show you how to apply this to key use cases like competitor monitoring—giving your team all the advantages of AI, minus the risks.

In just three steps, you’ll build an AI engine that’s tailored to your marketing needs. Don’t miss this chance to see Pam in action and learn how to future-proof your marketing team!

About Leveraging AI

If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!

Isar Meitis:

Hello and welcome to another live episode of the Leveraging AI podcast, a podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business and advance your career. This is Isar Maitis, your host, and we have a guest. A spectacular episode for you today. And the reason it is spectacular is because when I talk to businesses about AI, and I talk to a lot of businesses, either through my workshops or the courses that I run, or when I speak on stages and so on, I get to talk to a lot of companies. Most of them, the place they start with AI implementation is Marketing. And there are goods and bads to that. The first thing is there are a lot of AI use cases in marketing that are already good enough. So that's one aspect, which is great. The flips out of that is that a lot of people are really frustrated with trying to implement AI in marketing. And the reason for that for most of them is that it's very hard to go from a demo or a prototype to an actual operational working solution that's actually providing consistent business value. And that obviously is involved with the fact that your leadership team is putting a lot of pressure, start using AI, get to do this faster. We need to cut budgets. We need to get this there. And that combination of on one hand, you feel that you can do this, but on the other hand, it's very hard to make it consistently good and to work in the scenarios that you needed is creating a lot of pressure and a lot of stress on a lot of marketing people. The good news is that our guest today. Pam Boros is, has been in marketing for a few good years. I want to see a few good years. She held CMO and executive VP of marketing in several different large companies. So what she brings to the table is A really in depth knowledge of how marketing in general should be done right, a very holistic approach with real life knowledge of running large marketing, departments. And she learned herself and her team how to bring AI into that in order to infuse the actual processes that are happening. In the department with AI to get them to be done faster. And she has developed a methodology that she's going to work with us, including the tools that she's using. So this episode is going to be very hands on. Here's the tools that I'm using. Here's the process that I'm using. Here are the prompts that I'm using in order to get actual marketing business outcomes using AI. I find this to be really exciting. I know a lot of people are going to find value in this and hence I'm really excited to welcome Pam to the show. Pam, welcome to Leveraging AI. Hey,

Pam:

Isar. So good to see you and be with you today.

Isar:

Same here. You know, you and I spoke several times before I was very impressed with everything you're doing. And as I mentioned, you and I think from that perspective are very similar, where we can. Came to the AI world, not Oh, I want to become an AI expert, but rather I'm a business professional who run really large marketing in your case. And in my case, just business organizations. And we're just looking for ways on how to implement this new capability into all the stuff that we already know. and that's why I think you're so good at what you're doing because of that. It's not. The AI is just a means to an end that you already know how to achieve. And so I'm very curious and I'll give you the stage and we'll take it from there.

Pam:

Awesome. That's so great. I'm looking forward to jumping into the demo in just a second. I just thought I would set it up a little bit. Thank you so much again for the great introduction. I'm gonna be demoing a tool that's called Custom gpt.ai. Not to be confused with the custom GPTs in chat, GPT. This is a standalone solution and I think what it does, what I hear when I talk to marketing leaders and what I experienced myself as a marketing leader is there are three areas of concern for most marketers. One is hallucinations. Quality of the content. The other is the content voice and tone, which when it comes out of one of the standard models can be very flat and very kind of plain vanilla. And then data protection and the file security of any of the files you upload to a system. So I was specifically looking for a platform. I'm not a technologist. I was certainly not going to build this thing. So that's why I was so thrilled to meet the folks from CustomGPT. ai, including some of my friends who are on the phone on the call with us today. So the dirty little secret is that team members and marketing teams, if you're a marketing leader, they are using these tools, no matter what they say or not. They're just too enticing. They're just too compelling. And that might mean they're using free tools. They might mean they're actually paying for the tools out of their own pocket. But you as a marketing leader have absolutely no visibility of what's going on. So there's a lot of what I'm seeing, random acts of AI. That's what I affectionately call it. Random acts of AI where a marketing team member comes to you as a marketing leader and is Hey, can I buy this book? And you say, sure, that's no problem. Hey, can I take this course? Sure. No problem. Hey, can I get a free or a paid license to this tool? Sure. No problem. So there's that kind of whack a mole of is what's happening. But none of that is going to let you build it for scale or build this capability within your team. So that was the vision for the training program that you alluded to, Isar, that I built, which is called the Marketing AI Jumpstart. We're not going to talk about that, but we are going to, the fundamental core, when I deliver the Marketing AI Jumpstart for a B2B marketing team, Is this custom gpt. ai and the ability to very quickly, very easily build your own custom AI engine. So that's actually what we're going to do. So I'm going to go ahead and screen share with you.

Isar:

So while you're doing this, I'll share a few things. One, first of all, if you're joining us live on LinkedIn or if with us on zoom. So first of all, thank you for being here. I see a bunch of people already there and I appreciate you spending the time with us. first of all, go ahead and introduce yourself in the chat. So people know who you are, where you're from, what the size of the company you're in. Where are you in the world? It's always really interesting for us to know that. And it also helps us answer the questions with relevance to the size of companies you work for and the type of business you're in. So please do that. Whether you're on the zoom or on LinkedIn with us, if you're not. What the hell are you doing? We do this every Thursday. Come join us. It's always at noon Eastern, always on Thursday. You can ask questions, you can network, and you can be a part of the conversation. you can do that with us. Like I said, go to my LinkedIn. There's a link on how to sign up for these and you can get reminders every time you do this. So that's one aspect. The other aspect is I want to relate to what you said, Pam, as far as the biggest gaps that people have. And I agree with you a hundred percent, right? So people are terrified about their own data, but they're is ample statistics from the biggest kind of like consulting companies in the world, the McKinsey's and Accenture's of the world, that about 75 percent of employees calling, they call it, you had another, kind of like a nice name to this, but they bring your own AI. So people bring their own AI to work. And even if you're going to block all your systems and you're going to block all access on the IT and you're not able to install, they have a phone. They can have ChatGPT on their phone, they can have Claude on their phone, they can have Perplexity on their phone, and they can copy and stuff, paste from their emails on their phones into ChatGPT, or into any other tool. And so, by putting your hand in the sand and saying, I'm going to just block anything until this thing, until we figure this out, is not a good approach. And having a more structured process with each tool, Great training and education for your employees is the right way forward. But with that, let's dive into your process.

Pam:

Yeah, I couldn't agree with you more, Esau. And that's exactly what we're going to show today. So we're in the custom gpt. ai environment. Everything in the custom gpt. ai world is pro is called a project. So a project is a way for you to create a collection of training materials. And, basically a different use case. So I'm showing two that I use on a regular basis. Again, I'm a fractional CMO and a marketing consultant. So I have a built a B2B marketing wizard, which has trained on all the latest and greatest thinking in B2B marketing. I also have what I call a report synthesizer. I try to read everything that there is about marketing, HR tech, which is the area that I'm in. And AI, that is a heck of a lot of stuff to read. So the first thing I do is I upload, and I'm sure you've faces too. He's sorry. I report, I upload all the reports and first I query, give me a summary. Cause I want to know which ones are worth my time. So those are just a couple of the projects, but we're going to build a project from scratch today, cause I'm going to show you how easy it is to do it. And then we're going to, we're going to actually play with it. So just go ahead and click to create a project. And the first thing you do is you just need to give it some kind of a starting point. So what we're going to start with is we're going to start with a website. You could start with a Zapier integration to data files you already have. You could link to Google Drive. We're just going to make it super easy. We're going to start with a website. So the company that we're going to build this for is a company that's called Beamery. So I'm a fractional CMO and I work with solution providers, which are basically vendors in the HR tech space. Now, just full disclosure, I have no official affiliation of any kind with Beamery, but it's a company that I know. And that is always on the list of hot companies in HR tech. And I happen to know that they have a lot of great content that we could get even not being part of their ecosystem. To build this demo, so that's why I picked them. So they are a talent platform that helps you hire candidates faster and develop the skills of the workforce. So they're really focused on employee retention. And again, they've won a bunch of awards. we're going to go ahead and we're going to build, we're going to start with. Their website, it's going to validate the website. That just takes a quick second to do. And, let me just say one other thing about custom GPT while this website is being validated. So what custom GPT dot AI, I think of it like a Lego block, right? So it's a Lego block that snaps on top of one of the foundation models. And one of the foundation models, the primary foundation model that these guys use today is they use chat. You P. T. four. Oh, now you can choose a different model. They also have Claude use Claude as well as an option. But what I like about these guys is that they have built it in a model agnostic way. we know that all the big companies have their model wars. I don't want a piece of that. I don't want to, let the billionaires spend their billions continuing to raise the bar on the foundation models, but custom GPT snaps on top of anyone, their model agnostic, which again is what I really like about it. So it accepted our, Our just going to get a, I've got a demo folder handy here, and I am going to just upload something that makes my background and my avatar look better, just so it doesn't look quite so general. So it's on brand easily set those settings. Very intuitive. So the first thing we're going to do a couple of the things about custom GPT while we're talking about it. This is a reg system. So this is retrieval augmented generation. So the first thing you need to know about that. You've not read about reg is it really helps with the solution. The hallucination minimization. This system will literally tell you, sorry, I can't help you with that. Which as a marketer, I would much rather hear than a typical, chat GPT response, which gives you a very confident and very wrong answer. So I think that's really a key thing. The second thing, we're going to upload some data in a second. All the data is protected. It stays within the custom GPT environment and its data is fully encrypted. These guys are socked too. Compliant and, when you, if you upload any files to a foundation model, you don't always know if that file is going to be used to train the model further train. We know all the foundation models are desperate for data. They're doing synthetic data. So any data they get, they're going to very happily used to train the model with custom GPT. Anything you upload here. if you upload. Okay. A customer list or any kind of proprietary information. It stays secure. and then very importantly for marketers, the style and tone your voice and tone. We're going to do that in just a second. So we've created our new project. I entered the U. R. L. We've got a couple of things that set our avatar. Now, technically, you could start using this today with that 1 data point, which is just the website for beamery. Now, I want to give it a lot more data, but basically you're honestly ready to go with the ask me anything as soon as they upload everything. But we're going to upload a lot more data. So what kind of stuff would you upload? So if you're a marketer, you might want to upload your company case studies. You might want to upload your ideal customer profile. You might want to upload your sales decks. You can upload anything in a variety of formats, PDF, Word, Excel. MP3 audio, MP4 video. So I'm going to go ahead and just upload some items here. Sorry, let me just upload some data. I've got a, pile of data over here that I downloaded, that all publicly available stuff from Beamery, from their website, and from other sources. I'm just gonna

Isar:

grab those things and carry them over. Give me one second. Yeah. So again, to iterate on that, it's, consider your business or a segment of your business. This could be just for HR or just for marketing or just for sales or just for B2B sales or just for B2B sales in North America, like each and every one of these projects could be very specific to whatever needs you are going to use it for. So think about this tool and similar tools, right? and again, just to be clear. Pam or myself are not affiliated in any way with GPT. ai. It's just a tool that Pam is using regularly with actual clients and seeing a lot of success. That's why she's chosen to demo this. They're not paying her anything to do that. But the cool thing here is that you need to understand that once you have a tool like this, you can use it, not once it's not, okay. This is now the repository for my company. No, you build these custom projects for each client. Use case, because the data set might be different and the instructions might be different and the look and feel might be different because it's serving a different purpose. And that's the cool thing about this tool is that you can do that and do as many of these as you need.

Pam:

Yeah, that's a great point. So as I said, you start, all of my clients have adopted this tool because they see the value. You when they go through a demo like this, so in a couple of seconds, to talk through that these files have been uploaded and now they are part of the training set. Now, again, I could do a really fancy integration through Zapier or some of my other things or Zendesk, like if you have a customer service, repository. The only other thing I'm just going to add here is I'm just going to add their YouTube channel. So give me one second. I'm just going to copy that over as well. Now, obviously, a robust company, or a company that has a robust YouTube channel, think about all the amazing value that you're going to get from that. So we have now added that channel. and that's going to proceed. Now, where I think the, what makes I think custom GPT super interesting to me as a marketer is this idea of giving the agent a persona. This is really cool. So basically we know what we want to do. We want to create a, something that's useful for marketing. So I've got a something I'm just going to copy and paste in here. So you can just type in here, or what I love about what these guys do is they have a persona generator. So basically you tell it in plain language, what you are, and it's going to generate a persona. In the kind of style and approach that makes the most sense for the custom GPT environment So it's going to clarify things. It's going to give it guidelines. It's going to give it Special instructions, and all we need to do is just copy and paste. It looks like code, but believe me, it's not as scary as code. I'm going to close that out. And I'm going to type it right in. And by the way, code is not

Isar:

scary if you don't have to generate it, right? If the machine generated it for you after you gave it a few words in simple English, then I don't care.

Pam:

It's a great point, and Isa, it reminds me of something else, if we think about all the years that we've all been learning, not me, but other people have been learning programming languages, human beings were taught to learn the language of computers. With generative AI computers now speak human language. So that I think is the real differentiator. And if you treat it like that, treat it as a tool, somebody is really smart intern that understands language. You are going to, do, be very successful with it. So

Isar:

we have one of those here again, just not to jump to a different subject, but I started writing and creating little pieces of software that do small little things for me. I've never written a line of code in my life. I don't understand a single word that's in the code and yet I can do this and I can troubleshoot it because. Tools like Gemini or Claude or Chachapiti allow you to write code and allow you to troubleshoot code and so on and so forth. So not even going to like the real coding tools like cursor or GitHub copilots or stuff like that, just within the tools we use anyway, you can do a lot of stuff. So don't be afraid of that. If that's something that you're considering doing, if it's not too complex, just play with it. It's a fun experiment.

Pam:

Yeah, absolutely. I think that's part of it really like tinkering, the word tinkerer, I don't consider myself that, but I've become a really, curious, interested tinkerer when it comes to these tools, because you don't really know the full capacity of what they can do until you start playing with them. So this persona is now in here. So now this thing knows what it is. We're going to save those changes. And basically this is ready to go. Now, this is almost like a cooking show ISAR. So we have put this in the oven. Now we have given this a lot of stuff to absorb. So I think it's probably ready for us to interact with, but just because we're on live TV here, I'm actually going to go over. I have another project, which is exactly what I just built. Here, the beamery marketing AI engine. And this is ready to go. And I know this is ready to go because I trained it several weeks ago and I've already been playing with it. So it's just same thing that's in the oven. We just brought the beautiful Turkey out of the oven and we're going to interact with this one. It's the exact same thing, all the same training, all the same prompts. so let's get started. So there's a bunch of things you can do in marketing and I would love if anybody on the call has something they want me to try. I'm a long time. I always say I'm recovering software product marketer. So usually the 1st rule is always know what you're going to demo in advance. But what I found is that the prompts that, or ideas that people suggest on a conversation like this are actually super interesting and I'm always happy to give them a try. But let's go ahead and let's just start with the first thing. So you're going to interact with this prompt box just like you would any other chat GPT or any other tool. So a lot of things that marketers have to do is write a blog post. So I'm going to ask it, please write a blog post of 700 words. Based on Zalando, which is a customer case study that I know is in the training set, because it's one of the things we updated. So imagine the repurposing. So you've written a case study, you have gotten approval from the customer to publish it, and now you want to put it in all these other places. So the ability to take this and, get a pretty good draft right away that is through the style and tone of Beamery, which hits on Beamery's key product attributes, which has the key findings from the customer success story again, extracted right out of that case study. Now you could decide, this is great.

Isar:

So those of you who are not watching, we just got a nice 700 ish words long, blog post that takes into account all the information that we gave it that is related to Zalando's project. That is part of the training data that we gave it. So it's not something you can get from chat GPT because it doesn't have that specific data behind the scenes.

Pam:

Great point. And I just refined it to say, okay. Have I really want to make it 500 words. So it just did that on the fly. Now, of course, are we going to copy and put this on our blog? No, we're going to take it to a document. We're going to validate what we have. We're going to maybe have stakeholders reveal it, right? So we want to be careful always with anything that comes out of generative AI. It's only as good as the training data and we still need to check it. But if you get 85 percent there, rather than starting with a blank page, That's pretty good. so that's the first one.

Isar:

I want to pause it just for one second, because there's a bunch of questions coming in. So the first question, which I think is a great question, because you alluded to that, but we didn't explain why or how. So there's a question from Sarah on LinkedIn, and she's asking, how is this different than creating a GPT on ChatGPT? So basically the custom GPT in ChatGPT versus custom dpt. ai, the tool, what are the differences and why is this better?

Pam:

Yep. So you could certainly do that. Of course. what I think is you've built a more general purpose tool that lets you Do a whole bunch of marketing, activities with the same training data set and with that kind of consistent persona, I think the other thing that I like about it, it's not demoing app, the way that it works here, but all these are me. But what you get is you get actually the visibility of all the people on the team are doing with this environment. So as a marketing leader, you can coach people, right? So I have this situation with my other clients where I can see what the folks inside the client are doing and what questions, what prompts they're asking, and I can coach them. And say, Oh, that was did you think about this? Did you think about refining it further? How about using it for this use case? You only seem to be using it for LinkedIn posts. Maybe we should be using it for our webinar program. So as a marketing leader, I can coach and get all their skills up when it, with a custom GPT, that's not possible.

Isar:

So that's a great point. A few, two other points that I can think of. One is the amount and types of data you can put into it. So you can put in significantly more data here than you can put into a custom GPT. Custom GPT is actually relatively limited with the amount of data you can load to it. the other thing that I'm not a hundred percent sure about here, but in a custom GPT, you're also limited with the amount of instructions you can put into it. So I've hit the cap and I think it's. Either 8, 000 words or 8, 000 characters, that you can put in when you're creating a custom GPT. And I hit that more than once. And now you need to start making compromises, That you're like, okay, I got to cut this off. I got to make this shorter. I got to, and then it's not exactly what you wanted because you're limited with the amount of instructions you can give to it, which I don't think is the case here. And then the next thing is really the integrations, right? So you just showed us that there's all of these preexisting integrations like to your customer service system, probably your CRM, these kinds of things that don't exist on chat GPT. Now you can do it in. In custom GPTs on chat, GPT, because it has that API section at the bottom that almost nobody's using, but you can have chat, GPT, write your code to connect to an API of a third party platform. That's way above the pay grade of most people who are going to use these tools. And so if you have custom built integrations into existing tools that you're using in your company, like Zendesk, like Notion, like tools like that's a, Huge time saver. And now you can use them in specific projects back and forth. and then the last thing that I would say, and this one I'm guessing because I didn't use this tool, but it's the same in other tools is that you can embed the search bar, basically the chat bot into anything very easily. And it's not easy to do that with chat GPT. So if you want this thing to live. outside of custom GPT dot AI. You, it probably gives you like an embed code or something, right? But you can put it on your website, you can put it on your whatever, and then you can do that, which again, in, in chat, GPT is not easy to do. You got to build it as an assistant in their, In their other tool and then use the A. P. I. Like it's a little more complex than that. It is going to be right here.

Pam:

Yeah. Yeah. Great point. I think the data one is really a key part, right? Because as a marketing, if you have all of your resources, for example, sitting in Google drive and you already have a good mechanism for calling things out when they're dated, that automatically updates. Model\, right? So I think the integrations that they've built are the right ones, and I know they've got other ones on their road map. notion is a place where people are storing stuff and also SharePoint, depending on the company. So I would agree with all of those. And thank you for answering some of those questions. Do you have other questions before we go into the next? Yeah,

Isar:

one more small question. Which, comes from, Stefan, which is in Germany. He's asking, is this available in Europe? And they have, because of GDPR and the, EU AI Act, some of the stuff is not available. Do you know the answer for that?

Pam:

That is a great question. I know a couple of the folks from the CustomsGPT. AI team are on the call. So maybe Eli or one of the other guys. Yeah. Maybe somebody wants to put a response in the Zoom chat and, Isar, you can update Stefan and everybody else on that. Cause I don't know the answer to that.

Isar:

Okay. Awesome. All

Pam:

right. Great. Let's keep going. again, another oops, I don't

Isar:

want to do

Pam:

that. Say so, please. And, you might think I'm silly for saying please and thank you and great, there's some evidence. I don't know if it's true that you're more polite, that the model tries harder. I think there's a lot of things we don't know about these systems, but at the very least, if the robot overlords come for us one day, I want them to remember that I was polite to them. So that's why I always do that. so let's see. So please write a LinkedIn

Isar:

post for, I should have had this one ready to be typed in. and

Pam:

this is the CEO of Beamery based on the latest product. So that's the CEO of Beamery. custom GPT is going to know that because if it's training, so here again is a very basic starter. one tip that I have for folks, all these models, custom GPT, chat GPT. They love the rockets. I would say, please remove rockets. From any of your posts to me. That is like the ultimate red flashing to your followers that you did it via, an AI tool. So please do that. And it's not necessarily exciting news, but, edit it out. that's part of the part of it. Have you seen that as well? If you notice that.

Isar:

Yeah, there's the big telltales and at least for me, like in chat GPT in my custom instructions. So the one that run always in the background, it talks a lot about never use the word delve. Don't add too many emojis, do not use rocket emote. Like all of that stuff is built into my custom instructions together with a lot of other stuff. So those of you who don't use that, it's always a good idea to add that into the stuff that you're writing. together with some guidance on my style and the way I like to approach things and so on. So it's just good best practices.

Pam:

Great idea. Now, one thing we didn't actually train this on, because again, we are not involved with Beamery, but if this was being used, if this was the Beamery marketing department, we'd be able to upload samples of the CEO's other writing and other interviews so that it could, in the style and tone, we could say, Hey, refer to other of his writings. when writing this, we don't have that in our training model here. one of the things that these tools are great at is, going back to my report, synthesizer is distillation, summarization, beamery. Every year publishes a talent index. They're on their eighth edition. And we could just ask it to please distill. Now, again, if I worked at Beamer, I might already know that, but this is a, a good thing. And I could maybe able to use this for a variety of different things in the company. So summarization distillation is a great, is a great use case for these things. And again, we could only do this with some sort of, custom tool or custom GPT, because you need to have the thing in your training set. So I use all these tools a lot as an ideation partner. so I'm just going to ask what are some.

Isar:

Topic ideas or a

Pam:

memory thought. Oops, I'm not even typing. Hang on a second.

Isar:

What are some

Pam:

topic

Isar:

ideas for the femur y thought leadership webinar?

Pam:

I might work at the company, let's pretend that I do, but I'm like, oh, I'm so close to this. What would be some good things that we could do for a webinar? so here's some good ones. Okay, great. so this is good. The secrets of succession, better succession planning.

Isar:

So again, to explain like the broader implication and application of what Pam is doing right now, a lot of people diving into the final outcome with AI, because it's cool and it's obvious and it's something that we do every day, like creating the blog posts and creating the, LinkedIn posts and the stuff like that. But really these tools are amazingly good at brainstorming ideas. And as a. Another person that you can consult with on what is good content, what should we post, what should be our schedule? Like these kinds of things, these tools are very good at. And in this particular case, because we've uploaded a lot of information, so information from the website and a lot of other downloadable information that they had on their website, you can now ask it on here's my target audience, or here's a new target audience. I want to address what should I write to these people as top of the funnel, middle of the funnel, or bottom of the funnel kind of content. And it will. It will tell you that it will give you ideas and then you can ask it, Oh, I like idea number two, let's dive into that one and make it more specific and so on and so forth and go down the rabbit hole until you really crystallize the type of things that you want to create.

Pam:

That's a great point that refinement process so if you get what you something you'd like in that first result. Refine, refine, refine, refine. And unlike humans who eventually get tired of you asking it to refine and do something different, these kinds of tools always cheerfully give you an answer. So I think that's another great thing too. okay. Let's, I've got like kind of one more example here. So I'm going to say, are there any videos in your data set that, about So again, we've got it hitched up to this, imagine we've got this hitched up to all of our content, forget all the stuff we have maybe, right? And, oh, okay, I forgot about this case study. Okay, cool. So for this one, maybe this happened before I joined the company. please give me a summarization.

Isar:

So again, those of you not seeing the screen, we've got a list of videos. And now like, Oh, this one with kind of like what they are about and then with one line of what they are about and now what Pam is doing, say, okay, this one is actually something I want to use. I need to ask for a summarization of one specific video out of their YouTube channel, which could have hundreds of these videos.

Pam:

exactly. And say, I think, this is actually a pretty cool story. I didn't know much about this story before. So I'm going to post this to LinkedIn. I need some kind of, like maybe an ad. So please write me an ad for LinkedIn about this video. Pick LinkedIn just because it's could be any social channel doesn't need to be LinkedIn, but that's where obviously a lot of B2B stuff happens. So it's giving me something, LinkedIn, this case study, it's getting the highlights. And again, going back to style and tone. All right, that's good. But, please make it much more. Persuasive, but I can give it guidance on tone. I can say, make it more salesy, make it less salesy. So now it's using words like unlock the secrets to transforming your HR. How do you stay ahead? Why watch the case study? So I've gotten a totally different style and tone again. You want to make sure that it fits with your brand. You want to make sure that it's going to resonate with your customer profile. They're going to appreciate that kind of an approach, but it gives you the ability. And again, if you're have, if you think like a writer, use that nuance of language to tease the best out of the, the content that you have here in the tool. So I want to add

Isar:

to that one thing that a lot of people are struggling with, or they heard, and they thinking about how to implement. So the whole concept of prompt engineering for your tone of voice, right? Because people want to get something that doesn't sound like general custom GPT, because guess what? Everybody is going to generate content with chat, GPT or Claude or Gemini or any other tool. So it's going to sound like. Claude or Gemini, or so people already know that they need to create their own tone of voice. But many people do not exactly know how to do that and how do you create that and how to use it regularly and every time you create new content and what's really happening here is some of the knowledge base that we've already uploaded defines the company and the tone and the culture and how we want to write things and what kind of voice we want to use and brand guidelines and all this stuff already exists. And it's database. And so when you asking these questions, this is already a given, like it already knows how to write as this particular company, it already knows how to write for this particular use case. If there is a piece of data that shows it, if you are really smart, you're loading multiple files that are examples of what were your best successful. Blog posts. And what were your best successful LinkedIn posts and stuff like that? The other thing that plays a very big role with these tools is naming conventions, right? So if you, before you upload the file, instead of calling it, Gemma's blog posts and okay, that's not very helpful if you name it. best blog post for this and that audience from this and that type of company, example one, and then example two, and then example three, then when the AI categorizes that information, it knows what it is. And if you do that, and it's true, Some work upfront, but you're getting a huge benefit down the road every time you're trying to generate something new with it. So a lot of the work comes to do with figuring out what data to upload, what data not to upload, because it's crap and it's from 10 years old. So if you had a website that wasn't updated in the last 10 years, don't upload the entire website because it may have stuff in its databases that is not actually serving what you're doing right now. So first you should probably update your. website, but assuming you're not going to invest the time to do that, which most companies don't, then at least don't upload the same kind of bad data into this, because you're going to, it's going to use it as part of the training data. So prepping the data, knowing what to upload, what not to upload, how to name things plays a very big role in the outcome that you're going to get in the end.

Pam:

Such a good point, because sometimes when we maybe extract an audio file from a Zoom recording, it comes back with a gobbledygook, file name. So take the time to rename it, interview with ISAR on using custom GPT, right? If I was going to upload that to my own knowledge base, it is so worth it to do that. And again, linking to a Google drive or some other place where you already have that structure and you already have those proper naming conventions is so important. That's one of my personal pet peeves on file naming. So just, maintain that, maintain that, that hygiene. he said, I'm happy to do any other prompts. That's what I have prepared for you guys today, or we can stop the screen sharing and happy to answer some questions.

Isar:

Yeah. first of all, I'll answer a question that I assume is coming from one of the guys from, custom gpt. ai and he's saying yes, it is available in europe So those of you in europe who wants to use this tool the tool is available and it's going to work for you So that's good news if you're in europe, I want to touch on one last thing and then we can see if there's any additional questions from the audience Which is What are the main use cases that you see your clients using it for right now? So we gave the, okay, here's how, but what is the, what, what are people actually using it for just to give people ideas on how this could be applicable? we've done blog posts. We've done thinking about what content to publish. We've done summarization. what are some other capabilities?

Pam:

Yeah. I've asked it to do, give me some crazy ideas for appealing to our ideal customer profile. And then, name the customer profile. I've also said, give me 10 more, right? And they get, very creative. I definitely think the ideation partner is limited only by the kind of things you're thinking about and exploring in your own work. So I would, use it for that for sure. definitely anything to do with writing first drafts. a lot of the use cases that we've seen. And I would say, not every tool is the right tool for everything. So one of the things that custom GPT dot AI does not do, and it's very clear about not doing, doesn't do anything with imagery, right? So it's a rank system. So there's no hallucinations by definition and AI created image is a massive hallucination. yes, you could use Dali for that kind of thing. I think if you're a company, you're going to want to invest in the kind of authorized tools. I love what Adobe is doing. Adobe is a real leader in this space in terms of using authorized images. Really for a big company is really leading the way. not every tool is appropriate for everything. I use a whole suite of tools. sometimes I do want a generic answer. So I go to chat. Sometimes I want the power of what perplexity is doing. I wanted to find a particular stat that may be buried in 1 of our case studies. Within the training set, I'm like, Oh, there's a statistic here from Deloitte. I can't find the source. Let me take that to perplexity. So it's keeping in mind the right set of tools to use for the right things, just like you wouldn't use a spreadsheet. you wouldn't use Excel to write a document. You've got to, all of us have to get up to speed on the right tools to use for the right use cases.

Isar:

Yeah. Awesome. I agree with you. I think there's, you said it, right? it's your imagination is the limitation, but think about having the most amazing group of assistants or. Interns that actually have domain expertise in your world. What would you have them do if you have them for an unlimited amount of time and unlimited amount of attempts to get information or create information based on the information you already have. So today there's a lot of things you don't do in businesses because the ROI doesn't make any sense. yes, I don't have time to do this. I could hire two VAs to do this for me, but they're going to cost me X. And the return on doing this research is going to be 30. So it's not worth doing, or even 3, 000. I still not going to hire people just to make 3, 000. But if the cost of getting the answers of finding the information on summarizing the data on creating the report, like whatever it is that you're trying to do, if the cost is. very close to zero. You will do a lot more off that. And the only reason, again, we're not doing this and we somehow even don't think about these things because it never made sense. Now you can start any crazy idea that you have. Of things you want to try, things you may want to do, things that might be interesting for your audience, ways of content that you've never tested before, all these kinds of things that didn't make sense because of a simple business ROI. Now the ROI is there. And the reality is in many of these use cases, you're actually going to get better answers. Because if you're going to send somebody to look for a specific kind of use case through 350 videos you have on YouTube, the chances they're going to do this successfully is very, very low. And it's going to take them a very long amount of time. And these tools will actually get it done. Pretty damn good the first or second time around, especially if, as we both mentioned, if you keep on digging and asking more specific questions and go a little deeper into the rabbit holes, you'll find exactly what you wanted in three minutes and it will be what you needed. And with some of these tools, it will even get you to the right timestamp in the video. So you don't even have to look for that. And so there is a very. Unlimited number of use cases that you can figure out within a business. Once you have your data in a place that you can query, and this could be both for internal and external stuff.

Pam:

Yeah. great example. Like going, so just another example, like the personalization and customization. So again, our friends at Beamery. They serve as a whole bunch of different industries. So maybe they write an ebook, which is about talent upskilling. Now, all of a sudden they can write a talent upskilling for the manufacturing industry, talent upskilling for the financial services industry, talent upskilling, whereas before producing an ebook is a major lift. Not only the design and everything, but the creation of the content. So if you're able to create something that's much more customized and personalized, the assumption is that you're, it's good content. It's going to engage that buyer a little bit more, and you're going to have, better success with your content program.

Isar:

Great points, Pam. This was fantastic. I really appreciate you taking the time and sharing this. I really appreciate the fact that you took the risk and then this live, like a lot of people will show videos and we'll show screenshots. And you actually went into the tool and everything you've seen it happen in front of you. And again, those of you are listening and not watching the screen, we walked you through what's happening. So within seconds after getting in any question, any process, you get the response, which is extremely. Powerful when you bring in all your company data. So if people want to work with you, learn from you, connect with you, whatever it is, what are the best ways to do that?

Pam:

Yeah, exactly. why don't you, if you can stop screen sharing for me, maybe for just a second, since I moved that tool out of the way, I was just going to place my contact information. in the chat, I'm pam@bridgemarketingadvisors.com. I'm very easy to find on LinkedIn. I'm just gonna throw my contact details in the chat here for everybody and we'd love to hear from you, talk to about what you've got going on, and, connect you to the folks at custom GPT, if you feel like you would like to try out that tool.

Isar:

Awesome. Thanks again so much. This was a real pleasure. I really enjoyed the conversation. You shared a lot of great stuff and I know a lot of people will be interested in that. I appreciate you. I appreciate you sharing the time. Thank you so much.

Pam:

Thank you. I appreciate you.

Isar:

And for those of you who are with us live, thanks again for joining us. I know there's other stuff that you can do at noon on Thursdays. And yet there's a lot of people on LinkedIn and on zoom that join us every single week. So thank you so much for being with us. Thank you for asking questions or being active in the chat. And if you haven't done this, come join us next week. Again, every Thursday at noon, we do this. We also have our community getting together to just AI Friday hangouts. We'll do this at Fridays at one. And if you want to sign up. For any of these things, there's a link in the show notes of the show, if you're listening or watching this on YouTube, so you can find us over there and until next week, everybody have an amazing rest of your day.

People on this episode

Head Shot

Isar Meitis

Host