Leveraging AI

226 | How to use AI for the most important factor today - learning new knowledge and skills faster and more effectively

• Isar Meitis • Season 1 • Episode 226

Share episode

Are you still treating AI like a glorified spell-checker?

If so, you're missing out on at least 90% of its power and that power can save your team hours, boost productivity, and give your business a serious edge.

In this solo masterclass, host Isar Meitis walks through the real-world, tactical ways you should be using AI, especially ChatGPT, Claude, and Gemini to automate complex workflows, enhance proposal writing, improve learning, and cut down time spent on repetitive tasks.

From uploading documents the right way to building custom GPTs that can practically write your RFPs for you, this episode is packed with actionable techniques that most professionals have no idea exist — and it's all tailored for business use.

In this session, you’ll discover:

  • The 4-part prompt framework that stops hallucinations and delivers reliable citations
  • How to build and share a prompt library for your team’s efficiency
  • The secrets of NotebookLM, Study Mode, and Custom GPTs for business use
  • Real examples of interactive AI tools that go beyond text — from simulations to training games

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!

GMT20250922-133742_Recording_avo_1280x720:

Hello and welcome to the Leveraging AI Podcast, a podcast that shares practical ethical ways to leverage AI to improve efficiency, grow your business in advance your career. This Isar Mateis, your host, and I'm fighting some really bad allergies, so I really apologize in advance for my stuffy nose, but I promise you this is going to be worth it. This is going to be an incredibly tactically valuable. Episode for probably each and every one of you. And while it is based on a workshop that I recently did at my son's schools to all the teachers in like a teacher enrichment day, it will be highly applicable for everything you do at work because we're going to touch on more advanced functionality of the AI models that you all use every single day, whether it's ChatGPT, or Gemini or Claude. One of the interesting things we've learned last week is from the release of the research done by OpenAI and by anthropic, sharing how people actually use their models. And what the model found is that first of all. Less than half the people use Chachi PT for actually work. A lot of them are using it for personal reasons, but the people who are using it for work, over 70% of them use it to help them write better. Meaning how to write better emails, how to edit things that they wrote in, in different documents and so on. And that is a very, very small portion of what AI can actually do for you. And so some of the capabilities, more advanced capabilities that are built and baked. Into your regular day-to-day AI tools are not being used by most people, and we're going to cover a lot of them today. And yes, we're going to cover them through the lens of teaching in a school, but I promise you I will give relevant examples for each and every one of them, how they could be applied in business as well. At the beginning of the workshop, we worked mostly on prompting and what are the best practices for prompting, which I'm going to skip because I assume that most of you in the audience know how to prompt. But the next thing we dove into, and I'm gonna be sharing my screen, but I will explain to you everything that is on the screen. So immediately after prompting, we dove into how to prompt using reference materials. When you upload documents to Chachi, PT Claude, Gemini, and so on, there are ways to make the effort significantly better. So let's talk about. What is the difference between using a document and not using a document in each and every one of these models, and what kind of documents you can upload? Well, first of all, you can upload anything. You can upload images, PDF, word documents, et cetera, and they could be any kind of document you can imagine. These could be reports that you're getting from your team. These could be reports you're getting from your clients. This could be exports. Statuses from existing systems such as your C-R-M-E-R-P, et cetera. These could be proposals, these could be RFPs, this could be lesson plans. This could be any kind of document that you want. Now when using documents with ai, there are two potential problems. Problem number one is the AI hallucinating and making stuff up that's not in the document. Problem number two is that it is going to use information that is not in the document that it finds in other sources that is accurate and correct, but it's not necessarily the information from the document. So when you are using documents in an AI platform, you want to add several things to your prompt. So I add four components to the prompt and I'm gonna tell you what they are, and then we're gonna look at an example, and then I'm gonna tell you how to make it easier for you every single time. So the first part of this edition is use only information from the document. The second part is complimentary to that, is do not use any information. Not from the document. And I know that sounds a little redundant, but it reduces the chances of the AI pulling information from a source that is not the document that you provided it. So these are pretty straightforward. Number three is really critical, and this is the one a lot of people miss. Number three saying, if the information I'm asking about is not available in the document, simply say. Insufficient information or whatever you wanna put in those quotation marks, you can say, not available or whatever other thing. Why is that important? Because AI systems are built to please us, period. They want to provide you an answer if you ask the question and the answer does not exist in the document, there's a decent chance it is gonna either make it up or find it from another source because it wants to answer your question. By the way, we covered a lot of that in the recent episode this past Saturday when it comes to how can AI labs trade their models better to reduce that? But either way, it may provide you the wrong information instead of telling you it doesn't know. However, if you're telling it what to do. When it does not find the information, that is a better way to please you because it's actually following your instructions. So telling it what to do with information is not available is actually a very good thing for reducing hallucinations. The fourth. Component that is also very important is asking for clear citations. So what kind of things I ask for in the citations? I have a standard format. The format is telling me the name of the document because in many cases I would upload more than one the page. It appears on the name of the heading, and an actual quote from the document that helps answer the question. And if there's more than one. Give me several different citations with several different quotes. Why do I do that? I do that for several different reasons. Reason number one, it forces the AI to ground itself in the actual document it needs to find a quote, reason number two, which is as important. It is going to save me time verifying the information. So while yes, you told it to use only the document and you told it not to go anywhere else, and you ask it for citations and you ask it to tell you the information is not there, it may still make stuff up, which means you still need to verify the information that it gave you. But if you know the name of the document, the page, the paragraph, and the exact quote, the time it takes you to verify the information is. Five times less than if you had to figure this out on your own. So let's look at an actual example. In this particular example, what I've done is I've taken a government RFP for construction and renovation. Why that? Because government RFPs are multiple documents and they have more. Multiple pages and it's not easy to follow and there's lots of ins and outs and it's hard to find information in it. Those of you who've done any government work knows exactly what I'm talking about. Those who haven't, you'll just have to trust me. And then the prompt that I use is you're an expert government proposal writer who specializes in writing winning proposals for government construction RFPs. You will be provided with a document as an attachment, and several questions that you should answer. A few important rules for this process. Number one, you must use information only in capitalized letters. From the document I attached. Number two, do not in capital letters, use any other sources for any steps of this task. Number three, if you cannot find information that is directly related to the questions that you are asked in the original document, simply respond with. Insufficient information in quotation marks. Number four. For every question you're asked about this document, you must include in every segment of your answer a citation in the following format, document name, page number, heading exact quote, and then ask that to review the document. And then I started asking questions. What you see in the results is really remarkable. So a great example for this is I asked it what is the performance period once the job is awarded? And the answer I got is perfect because it says the performance period is 365 calendar days from the date of notice to proceed in parentheses, NTP. Is issued by the contracting officer. And then I get an actual quote that says, period of performance, 365 calendar days from Notice to Proceed. And then it tells me the name of the document, which is elicitation number and the, in the PDF page three continuation sheet. And then it says the actual quote. This is perfect. And then there's another quote from a different section in the document that is saying the same thing. Now, in addition to the fact I get something that is very, very specific, I can go and actually verify that. I can go to page three of the document and go to the section that he talks about and then find the exact quote. And it's gonna take me about five seconds. It can take me five seconds because all I need to do is copy and paste the quote, paste it into the search inside the pa, inside that. Paste it into the search box in the PDF document, and I can find that exact quote. And if I don't, I know that the AI made it up. Now, by the way, this works extremely well with GPT five. It works very poorly in Gemini. Why? I don't know, it still makes stuff up, or Gemini, it still gives me quotes that don't exist. But this is a situation right now, but this works very, very well with. ChatGPT, especially in GPT five. So if you're using any kind of documents, these tips should be very helpful to you. Then you may think, this is a lot of work. If I have to do this every single time, I have to write all these things. Just add, so much text. Well first of all, it's gonna save you a lot of time. But the trick is, is obviously to use a prompt library. So what is a prompt library? A prompt library is a centralized location that you and other people that work with you. Whether you team your department, your entire company can save prompts, or in this particular case, segments of prompts that work well and deliver results consistently. You need somebody who's gonna. Manage that library and it can live wherever is a shared place. This could be on Slack, this could be on Notion, this could be on teams. This could be on a shared document on Google Drive. It doesn't matter. The way I use it is I use a tool called Magical Chrome Extension. I'm not. Affiliated with them. But I really like the tool and I've been using it way before AI has existed. All it is is a text expender that lives within Chrome. What do I mean by that? What I mean by that is you can see the little M button, those of you who are watching the screen, there's a little MI code on the side of my Chrome browser and when I, and I don't even have to click on it or do anything. So in this particular case, when I showed you how I add these four rules, I have shortcuts for each and every one of these. Prompts. So if I go to the prompt line and all I have to type is AI doc in one word, which is my shortcut that I invented for it to bring the next little prompt. So when I type AI doc into the prompt, this entire prompt shows up everything that I read before between number one and number four with asking it to do all these different things. So every time. I upload a document to chat GPT or to any of the other tools. I type AI doc and this addition to the prompt shows up. How does this work? Again, if I click and expand this, you can see that there's multiple templates and each and every one of them has a long segment of a prompt, like you can see here. When I'm sharing it, you can see the whole four steps of the prompt and it has a shortcut. Every time I tapped I, every time I type the shortcut anywhere. In Chrome, which means any tool that I use, the whole prompt will show up. So the way I use this, I use this across everything that I do. I'm sharing this in different folders with different teams in the company, and everybody has access to prompts or segments of prompt little Legos, building blocks that we can use for different things that we need to do. So if you don't have a prompt library for yourself or for your team right now, this is a great place to start while adding capabilities that everybody can use and benefit and save a lot of time while getting consistent results. But there are other ways to get consistent results from ChatGPT or these other tools, two ways in ChatGPT to do the is using projects or using custom gpt. So what are projects? Projects are these libraries that exist right under where gpt are, right above where your conversations are on the left menu bar. Now, in addition to being a folder where you can just put different chats, there are actually many universes of context. Meaning you can create a project for a project, you can create a project for a client, you can create a project for a supplier, you can create a project for a product, you can create a project for a sprint, whatever it is that is a new topic that you need reference information about, and you need that reference information again and again and again. So in this particular case, I'm showing you how I'm using it for my clients. You can see this is a sample client project, but I have one for each and every one of my clients. And you can see here that it says. That I added multiple documents. I added a document about the culture of the company. Some of it I've written, some of it comes from their website. You can see the course proposal I sent them, the consulting agreement I have with them a document that summarizes the people from the company. So I have an AI that does a research on each and every one of them from LinkedIn and other sources. It creates a document about the people I work with that's in there as well. And then a workshop proposal I give them, and then the About us section from A PDF from their website. So now every conversation I have in here, instead of just from the regular new chat, has all of that information in there. I can also add instructions, and so the instructions will give it even more guidance and more context about this particular project or folder. So every time I'm creating a new conversation, just a regular conversation, it has. All of that as a context, and I'm not starting from scratch, meaning I don't have to add all of that information manually for the AI to know about the project, the client, the the product, whatever it is that you're working on. So this is one way to save you prompting while still getting better results. The other way is obviously to create a custom GPT. What is a custom GPT. A custom GPT in addition to being reference information or context information for the ai. It also provides a set of instructions, that set of instructions it can be anything you want. So you can see for me here, I've got multiple of these and I got probably got 25 more. So if you go to GPT up here, you can go to see all the gpt that exist in the GPT store and there are millions of them that other people or companies have created. But you can also create your own gpt. If you go to my gpt, you'll see that I have. I don't know, 20, 30 of them that you can create on your own. So how do you create A GPT? You just click all the create GPT button. You could do it from here or you could do it from the previous steps. So if you're just on the GPT page, there's a create button here, and all it has is you need to give it a name, you need to give it a description. These don't really matter other than you knowing what they do. And then you write instructions. These instructions will tell it exactly what to do. So this could be writing a proposal for you. I don't write my own proposals. I write my proposals. What does it have as far as the instructions? It has a very detailed process and as far as knowledge, you can see where it says knowledge. Here, you can attach files. It has two files. It has a very comprehensive template that I created specifically for that, that has all the different aspects that I provide as services and goods to my clients. And it has a PDF that I send to companies who ask me about my services, who have more description or longer descriptions about each and every one of the things that I provide. And the AI instructions tell it to use both these things, but relate to. What happened in a recording of a conversation? So the input to this GPT is actually a transcript of a call or calls with my client and emails that I shared with them that are related to the services that they want me to do for them, and then just writes the proposal. The benefit of that are immense. First of all. I'm now writing a proposal in about 15 minutes instead of about two and a half hours that it took me before. These are still 10 to 15 pages long proposals. Second, it is amazing at capturing the actual words and the way the client describes their problems, and it makes that positive proposal. Now, in theory, everybody should know how to do that. It definitely does it better than I can do it myself. And the last thing is that it knows how to combine all of this together in a fluid seamless way. That just looks good. The formatting is great and I need to invest very little time. I still read each and every one of them the proposal is created in Canvas. Those of you who don't know Canvas, it is a mode in Chachi PT that opens the actual document on the right, and then this document is editable. So you can highlight sections and ask the AI to fix it for you, or you can fix it yourself. So very, very quickly, I go from. Conversations with clients to a written proposal that then are just copy and paste into my template on Google Docs and I can send them the proposal. So this is just one example, but you can use it in multiple other ways. Going back to why I'm sharing this with you, we talked about three ways to shorten the time to getting great results from ai, and it all has to do with giving it the right instructions in the right context. So one is having a prompt library where you have either entire prompts or segments of prompts ready to go. The second is using projects where you just give it context, and context is king when it comes to any AI tools. And number three is creating custom GPTs where the instructions are already built in, and then you're just gonna give it the standard input that it's expecting and it's gonna give you the right output. by the way, if you're not a ChatGPT user, the same exact concept exists in Claude and in Gemini. In Gemini, they're called gems. In Claude, they're called projects just to confuse it from the projects in ChatGPT. But projects in Claude are more like custom GPTs rather than projects because you can give them detailed instructions for them to follow every single time. And so. You can do that on the other platforms as well. If you want to learn more on how to use custom gpt, we've done an entire episode about it. It was episode 1 75. It's called Stop Wasting Time, automate Repetitive Task with Custom gpt. So you can go back to episode 1 75 and listen to the entire episode. But now let's continue. So there are two other great tools that you can use in order to get information ready or learn new information that you want to learn, whether it's for your personal good or for business needs. One of them is Notebook LM from Google, and the other is study mode from all the different tools. So let's start with NotebookLM. What is NotebookLm? So NotebookLM is a tool that allows you to drop in multiple sources that you can see here on the left. By the way, you can get to it by going to notebook lm.google.com, and then you can start creating new notebooks. If I go back to my main page, you can see that I have dozens of these notebooks already created. I create. Probably on average, at least one a day, sometimes more. Every time I have access to new information, whether it's news about ai, research papers that come out or anything else that I wanna know about, I just create a new folder. But in this particular case, I've done it about the school that I was working because I wanted to show them information about the school. So I dropped several different web pages and two PDF files from the county about the education in our area, and it created immediately. A quick summary of all of it, but in addition, on the right side, you have these pre-canned things that you can create. You can create an audio overview, which basically becomes a podcast that explains to you in five to 50 minutes everything that is in the information that is there, and it's not reading the information. It's nearly a podcast. It's a conversation between two people talking about the subject that you have given it. The second one is video overview, which is an upgrade of that, which is really, really cool. So. It is the same concept. So think about it as a lecture, but with slides. So it creates its own slides and the slides actually come from the content that you've provided. So if we look at this particular case about how does the school report system work, I will share with s so you can hear what it's actually saying. And if I click play, so every year Florida drops this big report card for all of its public schools and each one gets a simple letter, grade A, B, C, D, or F. But what is really behind that single letter today we're gonna dig into then divide by the total possible points, simple as that slides are changing our students taking on more advanced classes. And finally, you've got the graduation rate, which is exactly what it sounds, explaining what's happening. A whopping s those sections. So this is a five minute and 48 seconds long video that is more like a PowerPoint presentation, but it's narrated by a professional that knows everything about the content that I gave it. It's five minutes and 48 seconds instead of reading three entire websites and two very long PDF files in order to learn. And information that I asked it about. So that is very helpful. Other options that exist, there is a mind map. Uh, if you wanna build like a structure of something based on the information, you can use it for proposals as well. So a mind map can show you the structure of the proposal and even components in it and so on. Uh, you can create multiple types of reports, so if you click on reports, you'll see that I have different kinds. Uh, create your own briefing doc, study guide, blog post, and there's many other suggestions that it's going to suggest specifically for the content that I uploaded. You can create flashcards to learn, so I will show you that as well. So you can see I created flashcards for the school, and this particular case, it's general questions about the school. In what year was Lake Yola Charter School failed it? And then if you, uh, click on it, it will flip it and you can see so flashcards that can help you learn any content. And it created 50 questions for me to learn from these flashcards. Again, this could be for any business related things. This could be for onboarding of new employees. This could be for internal training. This could be for any, whatever need. Uh, you have either or that, or your personal needs. And the third thing that I created is a study guide. So the study guide has a quiz. With questions and then it has answers, and then it also has essay format questions that you can use in order to learn for a specific topic or in order to help other people or your kids learn for a specific topic. All of that is free to use from notebook lamb. The other tool that is extremely helpful that most people don't know that exists because it's very well hidden, that can help you or other people learn, is actually built into each and every one of the chat platforms. So in Chachi pt, there's a little plus button on the left side of the prompt line. If you click on that, it shows you different options. It says add photos of files, add from Google Drive, deep research, create. But on the bottom, there's more. If you hover above more. One of the options is study and learn. The same exact concept exists in Gemini, and the same exact concept exists in Claude. If you click on that, it says that it's in study mode, and then instead of giving you answers, it's gonna help you learn how to solve the problem. And I'll give you an example. In this particular case, I uploaded a sheet of fifth grade math worksheet with several different math problems, and I told it that I only need to solve the left column of the math problem and ask it for help inside of study mode. It says, okay, great. Let's tackle just the left column together. Here are the four problems we see and it gave me the problems, but then instead of giving you the answers right now, let's work step by step. That way you'll actually get to know how to do these big multiplications, step one, warm up an estimation. So it tells me how to do estimation. So instead of 1235 times 1432, it says, try to do 1200 times 1400, which is like doing 12 times 14, which is actually relatively easy to do and then add to zeros. But then it tells me how to do the actual math problem. So I said, okay, step one of 1235 times. Uh. 1432 just multiply the first digits, which is two times five. So it's asking me, what is that? So I told him two times. Five is 10 said, oh, exactly. Good start since two times five is 10, we write down the zero and carry over the one. Now let's keep going. And now it says two times three. Don't forget to add and carry the one after you multiply. Can you try that one? So I asked why two times three said, ah, good question. Let's slow down. And make it crystal clear, we multiply 1235 at 1432. We, when we multiply the two. The one digits of the 1332, we multiplied by every digit of the 1235. So first we do two times five. Now we do two times three, which is the 10th digit of. So it's a great explanation and it's gonna keep going and help me do this, ask you to actually show me a graphical representation of the process so it does, so I can see exactly where to write the different digits. All of that instead of giving me the answer. So this is study mode that exists in all these tools. So if you wanna learn something instead of just getting the answer, or if you wanna help your kids or people in your department learn something without just getting them the answer, that's a great way to do that. But then we get to the really cool stuff. So beyond all these things, they're just text and that are very helpful and powerful. You can do significantly more sophisticated things. So I created three different media applications that run within the large language models that can help. In this particular case, kids learn stuff, but you can do exactly the same to teach people how to do different things in your organization. So the first one I said, learn math while playing soccer. This is something I actually developed together with my 10-year-old son because when the summer started, and he really loves doing math, he asked me to give him math problems and. Don't know how to give him math problems that will actually help him. So I said, what if we create a game that will give you math problems? Say, oh yeah, I love game. Let's create a game. I said, okay, what game would you like to create? And at that time, he was actually playing a really low quality from a graphics perspective. A penalty kick shootout game on a website that he likes to play. And he said, what if we create something like this, but with math problems? Like, okay, that's a great idea. And so we created this game. So how does the game look like for those of you who don't have it, I'll actually gonna show you how it looked like when it runs. So when it runs, the first thing that opens is a set of instructions. And the instructions say, what is the game objectives? Two players compete in a five round penalty kick shootout using math scales, kicker in blue and goalie in orange, and then how to play each round, both players answer a math question, kickers answer first. Then the goalie. The penalty kick is resolved based on both answers after five rounds. The play with most goals or saves wins. So how does it work if both hit it right? It's a 50 50 chance, it's a random outcome. If the kicker is right and the goal is wrong, it's a goal. If the kicker is wrong and the goal is right, it's a save. If both are wrong, it's a 50 50 chance again. And then it tells you what the math topics are and then what the, how the to play the game. And then you just click go. And then what you see on the display is that we have a goalie. And we have a kicker and we have a goal and we have fans and it's all relatively low resolution. But that's how he wanted it. He wanted it to be a low quality from a graphics perspective because it's similar to the game he was playing. And then there's a question on the bottom. What is 50% of what? 96. So this particular case, the answer is 98. If I kick it says, oh yeah, that's correct. Now it says, okay, what is 50% of 180 7? That's the question that the, uh, that the goalie got. And let's say that goalie gets it wrong. So I would say it's 55 save, and it says wrong. The answer is that he gives you the right answer and the kicker kicks and the ball goes into the goal. So now on the right side, I can see the history round one kicker. What is the answer? He got the right question, the right answer. Goalie got it wrong. And then the goal was scored. And on top you can see that there's one goal round two of five, and the goalie has zero saves. The game goes on and on. After five rounds, it goes to the next level and there's gonna be tougher questions. And the same on and on for level three and so on. Why is this so powerful? It's so powerful because it's something I developed together with my kid. He was really excited creating the game because when we started the game, it did not look like this. The first round of the game where we just started working on it, looked like this. So I will show you. We created it in Claude, and if I'm gonna scroll all the way to the top. And show you the first round of it. It was very poor quality. It did not have the history on the side, but the concept was the same. The kicker was just a square. The goalie was just a square. But the concept was already there. And from that moment went on, we just kept iterating and giving it more and more instructions with ideas. So you can see how the display, those of you who are just listening, I promise you, the display just get better and better. It gets a little bit of a 3D vibe. And the people start looking like mini figures instead of just a square, and then it adds the actual kicking area. And slowly we added more and more stuff. In the end, we added the fans in the background, and made the questions more complicated and make it not repeat any questions and added the history on the side. So he was very excited about this because he was able to build his own game, and because of that, the whole family played this game for about three days, trying to beat each other in math questions, but even just in the process of creating the game, because every route we had to solve the problems to see what happens, then probably doing, developing the game, he probably solved. I don't know, 50 to 80 math questions, which is 50 to 80 math questions more than he would've solved otherwise in the first week of his summer break. And so again, you can do something very similar for your employees and you can just find something that will excite them as far as the process or create any other kind of application that can help your employees achieve and do different things. And you can do it in any of these platforms. The same exact thing can be done. Not just on Claude, but also ChatGPT and Gemini. So let's move on and look at the next example. The next example is me wanting to show that you could go beyond just math. So in this particular case it was talking to Greek philosophers. So you can talk to Socrates, Play-Doh and Aristotle. How did I do that? So in this particular case, before playing the game, I wanna show you how the game was created. So the game was created because I did not know exactly where to go. So I actually consulted with the AI again in this particular case, Claude, afterwards, I'll show you another example, but I started with what is covered in the curriculum of social studies for sixth to eighth grade. And then he told me what is covered in each and every one of them. And then I asked in the sixth grade curriculum. Includes any Greek scholars and they said, yeah, we talk about philosophers and scientists and so on. And I said, okay, please create a detailed curriculum of sixth grade through eighth grade. Uh, need to know about Socrates, Plato, and Aristotle. And I gave it to it as a deep research project. So it's kind of the same in all of them. There's a function that's called deep research, and when you select that, instead of just giving you an answer, it will go and research. Multiple websites. In this particular case, you can see 291 sources that it actually read. In order to provide me that information, it took seven minutes and 17 seconds, so a lot faster than it will take me to go through 291 sources, and it gave me a detailed review. Of everything that I need to know as far as what is taught in six to eight grades. And you can see that's a very, very, very long document. It's probably 20 pages long. And based on that, I ask it to recommend interactive games that can develop and run inside of Claude that would allow six to eight graders to interact with those Greek philosophers. And then it gave me several different options. I picked one option. And I ask it to use voice instead of just text. And we ended up with a game that if I scroll all the way, well actually, I don't need to scroll because I have the actual thing here. So if we look at the way the game looks, uh, it asks me for my name, I'll give it my name, ISAR, and then we refer to me and it says, voice on. I will keep the voice on and you'll be able to hear what's happening now. Welcome to ancient Athens Za. Choose a philosopher to begin your quest for wisdom. So I have Socrates, Plato, and Aristotle. Let's go with Plato. Welcome future guardian of wisdom. Let us explore what lies beyond the shadows of ignorance. Are you ready to see the light of truth? Is what we see in virtual reality real? How do we know what's truly real? So now I can type my answer, I guess, if we feel. And see it in all senses. It should be real. Right? Question mark. Now Plato is thinking. It's gonna give me his next answer. Ah, my young friend. But what if I made you feel as though you were falling in a dream so vivid that all your senses believed it completely? Would that dream fall be real simply because you felt it? You see, our senses can be like prisoners chained in a cave, mistaking shadows on the wall for reality itself when the true forms of things exist in a realm beyond what we merely touch and see. Now what you see here is a really cool combination of the data from the deep research that knows about Plato's Cave and the shadows on the wall, which is stuff that he talks about a lot combined with relating it to my answer. And the reason I developed this particular game in Claude is because out of these three models, Claude, Chachi, and Gemini. The only one that can actually use the Claudeed thinking brain, meaning the actual large language models, as it's running code is Claudeed. So really what's happening here behind the scenes is when you saw Plato thinking, quote unquote, it's actually Claudeed from its code in the artifact that it created on its own. Is calling the Claude API behind the scenes to provide these answers, which enable this very lively conversation. Again, you can use this to train your people or allow them to get any information about anything you want, whether it's how to apply for a PTO as far as an HR question, or how to set up a specific server in whatever IT environment or whatever the case may be. You can give it information from. Data that you give it or through the research process and then allow it to think through it, review the information, and provide you answers in a game voice conversation or any other kind of solution that you want in a few minutes of development and having something that you can share with your entire employees. I find this extremely valuable and extremely helpful, and again. 99% of people don't know that that's possible. So now you're one of a, so now you're a part of a really small, unique group that actually knows that this is possible and can take a benefit of it. The third elastic example that I've used is to show how you can use a sophisticated graphic display to help people understand more advanced concepts. Now, some of you may know this already, but I was a F 16 pilot back in the day many years ago, so I'm very well connected to flight. I was a flight instructor as well. I also have a private, license and so teaching people how flight works is something I'm very passionate about because nobody thinks about it. But when you board a 7 47, A 7 47, a takeoff is weighing more than 400. Metric tons. That's over 800,000 pounds. And we never ask ourself, how the hell does this thing get airborne? That doesn't make any sense. Well. Simple physics make it possible. But that simple physics actually breaks into four different forces. You have lift, weight, thrust drag, which actually impact how much lift an airplane can generate. So what I did here is I created a mini simulators that allows people to explore these concepts. So it starts with the first page with just different ideas. What are the four forces? What is an angle of attack? Uh, what is air speed altitude and how these things balance. But then the cool thing is there's an experiment, but there is an experimentation section, and in that section on the right, you see an actual diagram of the wing and you can see the air flowing much faster on top of the wing than it is flowing on the bottom of the wing, which is the whole trick because high speed generates low pressure, which then basically pulls the airplane up. But the other thing on the left side, there are sliders. If I change the sliders as an example of angle of attack, you can see the wing rotating and you can see two things that are happening. It's gonna tell us that from a level flight we're now climbing and it says current situation lift is greater. Then wait, so the plane ascends against gravity. Cool. Right. The other thing that you can see that it starts showing. These turbulence behind the wing. So if I keep increasing the angle of attack, eventually you sit. Now it's going to descend. Why? Because the plane is not generating enough lift to overcome the weight, and I keep on going. It says too much turbulence form at a high angle of attack. Lift decreases below weight and a stall can occur. This is really cool. Now the other thing, if I take this down back to a normal angle of attack and I increase the altitude. Then you can see another thing that's happening. The lift is going to decrease because now the air is thinner. It's gonna tell me that current situation, the plane is not generating enough lift to overcome the weight. Higher altitude means thinner air, reducing air density, and therefore reducing lift. So I can play around with the sliders and see how that impacts the actual lift on the wing. That's very cool. But again, you can take this to anything in business that you can explain in a graphical way and create it in a visual way that will help people interact with it and better understand how it works. This is not rocket science either. Going back, this was created in ChatGPT and not in Claude. Just to show you that ChatGPT can do the same thing. By the way, Gemini can do the same thing as well, and if I scroll back all the way to the top, you can see what I asked it for. I said, I am a science teacher in the eighth grade, and we are learning about the physics of elevation in airplanes and so on and so forth. I asked it for ideas on how we could do that. It asked me several different questions because I asked it to ask me question. I said, before you start programming this, uh, please let me know if you have any questions. So it asked me clarification questions about the level of physics I want to go into, whether, what kind of aircraft I want, what kind of units I want to use, and so on and so forth. And then we together, after answering the question, got to the conclusion what we wanna do. Version one was really ugly and not very helpful, and I iterated back and forth until we got to the version you just saw. So what does that mean to each and every one of you in your business? It means that all these tools, chat, bt, Gemini, clo, et cetera, can do a lot more than most people know that they can do. All you have to do is know how to use the tools. So, several different things we covered today. One is using a prompt library to save your better prompts. Two is learning how to use reference material in a way that will dramatically increase the chances of getting the correct answer, and that will help you verify the information much faster. We looked at Notebook LM as a way to summarize lots of information and get a lot of different outputs out of it. We looked at study mode inside of the models that allows you to learn stuff instead of just get an answer, and we looked at creating interactive. Dashboards, learning environments, call them, whatever you wanna call them, that you can use across multiple aspects of your business and personal life in order to help people around you, whether it's students, your kids, yourself, your employees learn things better and faster. I really hope you found this highly impactful. I really hope that you're gonna test and play with this preferably today, so you don't forget, uh, any of the things that we talked about and share this with other people. This is, again, a highly. Tactical episode, these are the ones that I love the most, and you can share it with other people that can learn how to do these kind of things and develop it for things they are interested in creating or teaching again, either in business or in school or in their personal life. If you found this episode helpful, please subscribe to the podcast. We really appreciate all the people who are subscribed. There's tens of thousands of you, but every single person. But if you are not one of them, then please join the people who are already subscribe, share it with other people who can benefit from it. And if you really in a good mood, then give us a five star rating in a short description of why you like this podcast on Apple Podcast and or Spotify. And until next time, have an amazing rest of your week.

People on this episode

Head Shot

Isar Meitis

Host