35 | Elon Musk, Jeff Bezos and Jim Collins can be on your advisory board! Learn How to Build Your Dream Team, with Raphael Mansuy CTO at Elitizon

0:00Hello and welcome to Leveraging AI. This is Isar Maitis, your host, and I've got a special and very interesting episode for you today. Wouldn't you like to have people like Jim Collins, Elon Musk, Seth Godin, Gary Vee, Jack Wells, Jeff Bezos, Gina Wickman, people like that on your advisory board? We all would want that, or at least some of them, or at least the heroes and the people that we really believe in and that we think have done things in a way that we would like to follow. Well, that's obviously impossible, right? Because these people are either dead or will require a lot more money and influence than most of us have in order to have them on our advisory board.

0:41Well, in the current era of generative AI, you can actually have these people or at least their digital representation in order to consult with them on any business or strategy question that you have. If you want to learn how to do that, stick around because it's exactly what we're going to share in this episode. This episode is brought to you by Multiply. Multiply is spelled like the word multiply, but instead of Y in the end, AI in the end. So M-U-L-T-I-P-L-A-I dot AI. If you go there, you'll be able to find multiple AI educational concepts, anything from this podcast and also many other ways of education.

1:25such as board and C-suite level masterminds through courses and consulting services to businesses and how to understand and implement AI from a basic technical level all the way to business strategy. At the end of the episode, like always, I will share the most exciting AI news from this week. And now let's learn how you can create the dream advisory board for your business. In the next three years, AI technology will change our world dramatically. Whether you are a business executive trying to catapult your business forward, or just somebody who refuses to be left behind and want to advance your career, this is the show for you.

2:11I'm your host, Isar Maitis, a serial entrepreneur and an AI enthusiast. You'll hear invaluable practical tips from innovative business leaders, AI practitioners, and some of the brightest AI minds in our world today on how you can leverage AI in ethical ways to advance your career and grow your business.

2:34Hello and welcome to Leveraging AI, the 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 very special and interesting topic today. Maybe the most underestimated and underutilized capability of large language models like Chachipiti and Claude and Bard, etc., is using it as an ideation and brainstorming partner. Most people jump first and foremost to generating content and maybe summarizing documents, but the reality is it's an extremely powerful tool to ideate and iterate around ideas that you want to develop either for yourself or for your business.

3:14To put some numbers into this, a recent study from last week, actually, done by professors of the Wharton School from the University of Pennsylvania, compared innovative ideas generated by ChatGPT compared to their MBA students. So they run this contest between the students and ChatGPT. And what they found is that ChatGPT came out with more ideas, better, faster, and cheaper. And they've ranked all the ideas that came from both students and ChatGPT. And within the top 10 % of innovative ideas in the experiment, 87.5 % of those came from ChatGPT and not the students. So hopefully this intro gives you the thought in your head of like, how can I use that knowledge, meaning the ability of large language models to make better decisions in your business?

4:04If that's what you're thinking, you came to the right place because this is exactly the question that we are going to answer and going to take it even a step further. We are going to show you how you can build an amazing C-suite or advisory board for your business that will be with top-notch A players from your industry without paying them anything just by using large language models. Our guest today is Rafael Monsui. He is the CTO and the co-founder of Eliteson, and it's a company that helps other businesses take concepts and ideas, develop them to services and products, and sometimes even spin them off as separate companies.

4:42So they've been doing this process at scale for other businesses since April of 2020. So way before the GPT craze started at the end of last year, which makes Rafael the perfect person to learn this process from. And hence, I'm truly excited and humbled to have him as a guest of show today. Raphael, welcome to Leveraging AI. Thank you very much. So I'm there today. No, go ahead. I really want to dive right in. And my first question is, what problem are we trying to solve here? Because this is obviously the first question, right? Okay, what are we, what's the issue and what are we trying to solve?

5:25Yeah, so many small businesses struggle because they don't have the staff, they don't have the expertise that big companies earn. Before my venture, I was a CEO of a subsidiary of a Fortune 500. So when I work for this big giant company, I have at my disposal a lot of experts. I share experts, supply chain experts, legal experts. So every time I have a problem, I can find someone in the booth that can help me. But it's not the case when you are at the end of a small business. Because you have a small team, they don't have all the knowledge, all the capabilities, and you need to solve your problem yourself.

6:11So, there is this idea that tools such as Claude or Shadrion have a lot of knowledge, because they are trained, so many books, so many stuff you can try. You can use the power of these tools to create your Advoiser board. And as you said before, it can be very easy, it can be cheap, and it creates a lot of value. Of course, it's not always perfect, but I will guide you step by step how to do it, and how to start in a very simple way using ShadGPT or Cloud, tools that already exist. On that, if you want to go further, you can create very sophisticated model AI that can even be the expert. So I love what you're saying so much.

7:15I think, again, I think this is maybe the most underutilized part of large language models, and I think you've taken it a step further by basically saying, I'm not going to ask it general questions. I'm going to give it a specific hat, make it an expert on something very specific. And then I quote unquote, have that person on my board or on my C-suite or as a consultant, but without paying them$5 ,000 an hour, which these people will actually charge you if you could ever get to them. So let's start the process. What is the first thing that I do in order to identify the problems or the people that I want to address?

7:55First of all, as in a true company, you need to recruit your board. So you need to choose and select which expert can sit at your board. So for example, you can recruit a asher expert, a marketing expert, a legal expert, and so on. For each of them, you describe who they are, what they are expert of, and very important, you need to find books that crystallize, that contains the most don't expertise on each aspect. For example, if it is marketing, you choose the three top books you love the most about marketing. When you design your pro, you say, okay, my world is composed, for example, of a marketing expert, and this expert actually is specialized on this aspect of marketing on very well this theory that is describing this book, because There is a different way to do marketing.

9:19So you need to choose your school. On each book is a school of marketing. So you need to select each expert on what I call a mega prompt. A mega prompt is a prompt that describes who are these experts and what are their knowledge. And that's all for the first part of the prompt. Then, you need to describe yourself because for LLM, for ShadGPT, context is old. Because from the context, you can ask the right question. But if the model doesn't know who you are, what kind of business you're talking every day with, I cannot give you good advice. And it's the same if you want to see a lawyer. You need to describe who you are, what kind of business you are doing, and what is your problem.

10:25The same with LGBT. I see there are often the people, they just ask very short questions and they just design a very short call. But it doesn't work like this because if it is okay, so can you solve my problem? Okay, you get a very, not a very strong answer from that. So you need to describe honestly who you are, what you are doing, and what are your pain points. So first part of the prompt, you select your team, you describe who they are. Second part of the prompt, you describe what is your business, who you are, And what is your pain point? The third part of the prompt is your specific question.

11:16For example, you are the CEO of a small consulting company that are, for example, specialized in Microsoft technology. The business is good, but you don't know how to grow. It's difficult, for example, to work with people. They are expensive. They often leave your company or something like this. So you describe exactly what problem you want to solve the most, and you ask the question to the board. And the very, very funny aspect is because it is a board composed of different kind of professions. So your question will be analyzed from each expert, and you can get an extraordinary answer from each expert.

12:10And of course, once you get all the answers, you decide you are the pilot. An AI is not a pilot. You are a co-pilot. You ask someone to help you and give you, with all the knowledge, what is the best advice. With this advice, you decide. You have the best. I want to pause you just for one second because there's a few very important points that you touched. I want to summarize them very quickly. The first thing is to make people understand that what ChatGPT knows, or Claude, or all these large language models, is basically any data that is out there available. That could be, like you said, books.

12:50It could be research papers. It could be articles that they've written. So you can identify people, in many cases, people you already follow. You've read two of their marketing books because you think they're brilliant or their general leadership books or whatever topic you really like. You can use that as the resource that the large language model will use in order to model the answers that it's going to give you. So you're not just giving it a name of a person, you're giving it a name of a person in a list of resources to pull from, which makes it very specific because this is a model that you trust and you've seen it to produce results either for yourself or for other people.

13:32So this is number one. Number two is it made me smile when you said you got to write the megaprompt and not write two lines for it. Because think about if you would have done this in real life, let's say you had access to somebody who is a global expert that you would pay$5 ,000 to$50 ,000 an hour to come and consult you. How much effort will you put into preparing for that one hour that you're going to pay$5 ,000 or$50 ,000 for? You're going to put a lot of effort in giving them every possible information and explaining exactly what you need so that hour will be the most productive possible. And yet when we get it for free, because it's Chachy PT or Claude, we're like, oh, I am this and that, you're this and that, tell me how to proceed from here.

14:18I'm like, no, it just, it doesn't work that way. So the more effort you're going to put into explaining, like you said, your business, the client's business, the context, what you're trying to achieve, what the role blocks are like, write a story, prepare it as if you're preparing it to a very high-end consultant, you will get results that are at that level. And if you won't, the results may disappoint you. So these points are critical and amazing. The last thing you said I also did, which is you can build a board, meaning you can create multiple of these personas, ask them the same question and get their viewpoint and their approach on how to do this, which A, lets you consider this from multiple angles, but B, I assume you can then also use ChatGPT as an expert consultant from McKinsey to help you figure out between all these approaches how to do this.

15:17So what's the next step? So we got all the answers. What do I do then? So once you get your mega pro with all the desktop, you submit this mega pro to the system. Because it's a mega pro, it's better to choose a large language model that supports a very large context. So I got my best result with Cloud2. Yeah, because Cloud2 supports 100 ,000 tokens as context. So it's large enough to, of course, to get your very big story and then to get your very big answer. One important point is when you ask the system to answer, you need to give the system a minimum number of words. Because if not, of course, the system will optimize to give you the shortest answer.

16:19But it's better, for example, if you say, okay, I would like you answer me at at least 7 ,000 words. You get the most of it. I want to pause you for two points there because they're both very important. One is to explain what's a context window for people who don't know that. So each large language model within each chat has limit memory that it will use for that chat. And it's counted in what's called tokens. and a token is less than a word. So if you have 100 ,000 tokens, that's about 75 ,000 words. So that's the limit in Cloud2. I think Chachupetina for paid users is like 30 ,000, which is still a lot, but it's significantly less than Cloud.

17:05And what happens, think about it. You wrote your very long question. You get a very long answer. You're going to keep on going back and forth because you want to drill deeper to get better things. Once you hit that limit, the chat, the large language model, will forget what happened in the beginning. And the more you add, the more it will forget, which means it will become less and less efficient because it won't have all the information that was included. So it's important to pick one that has a long enough window. So that's one aspect that is very critical. Now let's continue with the process.

17:39Okay, so how it works, actually. It works because when you use a large language model, Then large-framid mole is just a function. It's a function that predicts from a few words the next word. Okay. But in order that function works for your question, you need to put constraint on the input in order that the story that will be elaborated will be constrained by the input. It's like a latent space. just like an impaired space with multiple dimensions. The more you contextualize, the more you shape your story in a specific area. It's why it's very important to describe your problem, describe what are the personnel and how they will answer your question.

18:41Yeah, and I want to add one more thing to something you said before as far as defining the format. You talked about how long you want it to be. I go a layer deeper. I actually tell it which format I want it in. Use bullet points, use headings, use subheadings. How many levels of subheadings should you use? It should be modeled around this kind of formal standard document that is delivered. It should be written as a business plan. You can tell it how you want the outcome to be and not just how long you want it to be in order to fit your need. You may want it as a script for a video that you're going to record with somebody else.

19:13Whatever you want the outcome to be, you can ask for that outcome to be in the format you want it instead of you now having to reformat it to the format you want. And if you don't like the outcome, you can just ask it to reformat it or change whatever you want to change and it will do it for you. Yes, exactly. The simple process is to, okay, you buy an access to cloud and you create this megaphone. But if you want something that is better, because there is this limit of context, maybe it's good to ask the question not to all the experts at the same time. But what you can do is you can create your problem for each expert.

20:02And you ask the same question for each expert. So if you do that, actually, you can use the 100 ,000 tokens for each expert. So suppose you have 10 experts, you multiply the memory by 10. If you do that. And you can even program it because if you do that, of course, by hand, it's not fun. But if you know how to program it, I've created an example how to do just kind of stuff. What you do is you just ask your question one time, and then you send the question to each expert. Each expert has his own context. And that's all. And if you do that, you get more than just create a big prompt. And there is another thing that is good because each expert is very constrained by expertise.

21:07Actually, the answer will be better if you ask the answer to all the experts at the same time. I agree. So I want to touch on a few points you said, and then I have a follow-up question. One is, how do you really duplicate this in several use cases? and I will explain how I do this and then we'll let you give your solution on how to get this multiplied by 10 or 12 or 5 or how many things you use. I have what I call a prompt library where I have a complete prompts, but I also have snippets of prompts. And I use a tool called Magical, which is just a text expender for Chrome in which I save all these things.

21:48So I can type a few letters, which is the shortcut, and then it pops up a whole segment. So if we take the use case that Rafael just shared with us, you can have a snippet of the description of who you are and what's your background and what is your company and what is the problem that will be duplicated across. You can have a snippet of the problem as a separate snippet that you may want to use in some context and some you don't, you want to use something else. And then you just combine these together. So when you want to create the long prompt, you don't have to copy and paste it and then make changes to it because it's a different character and a different expert.

22:27You literally just use slightly different combination of shortcuts in order to get each and every one of them and still get a very long prompt by typing four words instead of 4 ,000. So that's how I do this. How do you do that? Like, how do you duplicate across the different experts? Actually, I use the same process when I'm doing my experimentation because you need to first tell your problem it works well, so you need to experiment. But I'm a developer, so what I've done, I've created a full web solution. In this web solution, I can enter my problem and this system actually is implemented with what for the long-chain that use the same is the same we use some snippets some prompt with variable and we just shifted to the variable for example for each expert so what i'm doing is exactly the same but i have created an application for that so it's just like a chat gpt but is a chat gpt with many experts so once i ask the question the question will be sent to each expert, the poll will be created specifically to represent this expert on that call.

23:46Then the answer will be collected in parallel because each expert will reply in parallel and they get all the reply and they do a summary of each reply. So I love this. So this basically saves you the effort of opening all the different chats separately and copying and putting in. And so for those of you who do not write code, you can do this with no code, low code solutions like definitely Maker and N8N. I love N8N. It's my new favorite toy. So it's N, the letter N, the number eight, and then N.com. And it's basically a completely flexible flowchart. So if we take this particular use case, you can create a open field like in a form, like a Google form that you will type the question that you want to answer this time.

24:32And then think about a view of a flowchart, splitting this into the eight different people, already adding the background of your company that it already knows, adding the specific definition for that particular expert, the books it's going to use, all the stuff that we talked about before. And then it will send it separately and we'll collect all the answers. So you can do this without writing code just by using these tools. I want to ask an interesting follow-up question because I know you've done this a lot and I know a lot of people also fall short in that aspect. Once you get the first answer, how many times do you go back and forth with each expert to really hit gold?

25:10Because I assume, in many cases, the first answer is not optimal. Yeah, you're right. Very often, actually, it depends on the expert. There are some experts, actually, they are not very relevant for your question or your problem. They just give you some advice, but okay, but they can't do better than that. For example, if the legal expert, you have a problem of supply chain. The legal expert will give you something, but your problem is really a problem of supply chain. So once you get all your first surprise, you choose which expert actually can answer your question, and you go to each expert and you ask further questions on his dialogue, actually, where you try to understand why this decision has been taken, how to implement it, how to implement that.

26:10or if it is a plan you have never done that before. It can give you tips how to implement, for example, to optimize the supply chain or something like this, or you can recommend more key command training or something like this. Once you get your generic answer, you need to select the expert and you continue to dialogue with each expert. And that's all. And of course, at the end, you make the decision. You are the decision maker. Yeah. Yeah. Again, I think I love what you said. The idea is you need to remember when you use these models, in many cases, the first answer, even if you've written a very detailed and great prompt, it's going to give you a good answer, but maybe it's not exactly the answer you're looking for.

26:51Or maybe it's a great answer that gives you follow-up ideas and questions that you want to ask. Keep on digging. It's a conversational solution. It's not a one and zero solution. Keep asking questions, keep iterating, ask for clarifications, ask for a process, ask for a system, ask for recommendations for a book to read, ask for somebody else you may want to ask about this. Literally what you would do in real life with an actual consultant until you have a solution that can really support your decision. So again, extremely powerful suggestions. What else can a company do in this realm of concept of building an advisory board?

27:34Yeah. So actually, what I describe is just a very cheap solution because we just take a model that already exists on the market, but it doesn't give you a competitive advantage. Because, of course, for certain professions, actually, they are very well-known, they are very generic. But for example, if you work in a field, I worked in industrial gas before in my career. Industrial gas is a very specific business. It's an oligopold. There are just three companies in the world that are in this business. It's a very good business model. But actually, nobody teaches you in school how it works. You need to be an employee inside and you know how it works.

28:21So, suppose that you are a company that is unique and you want to leverage a very specific knowledge. Actually, the best asset you have with your company is the documentation of your process. If you took the chance in the past to document very precisely, what is your process? What is your business model? how you operate on companies like initial gas companies. They have a, I remember my father's company, Air Liquide. They have a book called the Blue Book. It's like the Red Book of Mao Zedong. The Blue Book is all the operational procedures. So when you are a CEO of a subsidiary and you are far away from the headquarter, you have this book with all the procedures.

29:11What you can do, what you cannot do. Okay, suppose you take the specific knowledge and you use this specific knowledge to do what we call fine-tuning of a model. So what is fine-tuning? For example, if you take OpenAI, ShadGPT, if you switch right to their API, what you can do, you can create your own specific model. To create your own specific model, what you need to do is to feed and train a model with your specific data. So you take all the information from the book, you create question or answer or other stuff like this. Piece of knowledge, just chunk, a lot of piece of knowledge. the more you have.

30:04If you have a very good quality piece of content and you feed and train a model with that, you add to the layer of the model all your specific knowledge and you can create the best expert on the market because only you have this knowledge. Of course, it's more expensive, neither IT team can do that. But if you want to compete with the best, it's the way to go. Yeah. So this is really the next evolution of what we discussed before. And this is like for a different scale of company, right? So the first solution works amazingly well for small businesses. This solution works extremely well for, it doesn't have to be a really large business, but it has to be a larger business for two different reasons.

31:02One is you need a lot of proprietary data. Otherwise, it's not worthwhile doing. And two is you need the resources to do this thing. And to add another point to what you were saying, you were talking about, yes, you can take ChatGPT and train it. That's true. In many cases, what you'll probably do is take Lama, which is an open source model, install it locally on servers that you own that are safeguarded that nobody gets access to that information. And then you can train an open source model that is now installed on your servers. And when I say your servers, they don't have to be on premise. They can be in the cloud, but it's your server.

31:41It's not shared with any other resource. And then you can be a hundred percent sure that it's guarded behind some kind of a firewall and that data is not getting used by anybody else to do anything else with it. And then, like you said, now you can apply the same model of asking questions, getting answered, developing ideas based on proprietary data that nobody else has access to, which means by definition, you're getting a competitive advantage. but instead of before there were three people the CEO, the founder, the president who knew some of it and you have to go to them now literally every person in the company that you give access to this has the ability to ask questions and ideate based on the entire history of knowledge of your business which is extremely powerful yes exactly under under under as you said before it helps you to be more creative team, because what system like OpenAI or large-scale mobile is very powerful to connect the dots.