The Personal Finance Podcast - How to Use AI to Research Stocks (With Brian Feroldi)

Starting point is 00:00:00 Local news is in decline across Canada, and this is bad news for all of us. With less local news, noise, rumors, and misinformation fill the void, and it gets harder to separate truth from fiction. That's why CBC News is putting more journalists in more places across Canada, reporting on the ground from where you live, telling the stories that matter to all of us, because local news is big news. Choose news, not noise.

Starting point is 00:00:27 CBC News. Okay, when I sell my business, I want the best tax and investment advice. I want to help my kids, and I want to give back to the community. Ooh, then it's the vacation of a lifetime. I wonder if my head of office has a forever setting. An IG Private Wealth Advisor creates the clarity you need with plans that harmonize your business, your family, and your dreams. Get financial advice that puts you at the center.

Starting point is 00:00:56 Find your advisor at IG Private Wealth.com. On this episode of the Personal Finance Podcast, how to use AI to research stocks with Brian for Aldi. Everybody and welcome to the personal finance podcast. I'm your host, Andrew founder of MasterMoney.com. And today on the Personal Finance Podcast, we're going to be diving into how to research stocks by using AI. If you guys have any questions, make sure you join the MasterMoney newsletter by going

Starting point is 00:01:41 to MasterMoney.com slash newsletter. And don't forget to follow us on Apple Podcast, Spotify. YouTube or your favorite podcast player. And if you want to help up the show, consider leaving a five-star rating and review on Apple Podcasts, Spotify, or again, your favorite podcast player. Now, today we're diving into something that could completely change the way. You research and analyze stocks without replacing your judgment or turning you into a robot investor. Now, if you've ever stared at a 200 page 10K and thought, there has to be a better way. This episode is for you, because AI won't make investment decisions for you, but it can make research.

Starting point is 00:02:17 businesses dramatically faster, cleaner, and way more structured. And to break this down, I brought in the perfect person to talk about it, who is Brian Ferraldi, a long-term investor, author, and educator known for making fundamental analysis simple and approachable. Now, Brian has been on the show many times. I think this is his fifth time on the show, and any time we're talking about stock investing, we're bringing Brian on the show. Now, we're going to unpack how to actually use AI like a junior analyst, how to give it structure so it finds the signal, not noise, and how to demand citations, so you know you can trust the data.

Starting point is 00:02:48 Plus, we're going to talk about how to break down companies into business models, moats, financials, and risks without getting lost in a black box. And we'll even walk through a live demo of prompts that Brian uses in real life to break down companies step by step. The same kind of workflow that can help you analyze businesses faster and smarter. Now, if you want to watch as we do the live prompts, you can watch this on YouTube again. Search my name, Anderjcola on YouTube, and you will find us there.

Starting point is 00:03:15 And we're going to be doing live prompts. and sharing the screen on YouTube. So that's a great place to watch this if you want to, but you can also listen along if you are listening to the audio version. So this is a great episode, an action-packed episodes. Without further ado, let's welcome Brian to the Personal Finance Podcast. So Brian, welcome back to the Personal Finance Podcast. Andrew Austin would be here.

Starting point is 00:03:37 Thanks for the invite. I am really excited to have you here because I think today we're going to be going through a bunch of cool things that you can utilize AI when you are investing in stocks. And we're going to do a bunch of research here. And we get a lot of questions about this. This is one thing I think most people are trying to figure out, A, you know, how do I utilize AI when it comes to my finances? B, how do I utilize it when it comes to investing? And I think it's going to be a very powerful investing tool. It is already today, but then it's going to become even more powerful here in the near future. So we're going to just get right into some of the tactics that we want to dive into. And most of you have heard Brian on here before. Brian, this is probably your fifth time on here, I think. And every single time that we have you on here, you know, a lot of people come away with a lot of tactical things that they can do right. away, which is why I absolutely love having you here. So this is going to be really, really fun. So first, I want you to kind of talk through just your long-term mindset when it comes to investing that you learn from Buffett and Munger, because you and I align on this a lot. And we are long-term

Starting point is 00:04:30 investors. We are investors who like to invest long-term. So can you kind of talk through your mindset and how you think about that? So I tried every investing style that exists out there. And I failed miserably on every other style. And it wasn't until I started to study the investing grade. like Buffett, like Munger, like Peter Lynch, that I really found a style that fit my personality well and actually generated positive returns for me. So if you study the biggest investors, the best investors at all time, they all talk about the same fundamental principles. Think of stocks, not as tickers, but as businesses. Only invest in businesses that you understand and you think have good long-term growth prospects. Use valuation techniques to buy those companies below their

Starting point is 00:05:13 intrinsic value and let the companies do the hard work. Before doing any of that style, which is my current investing style, I tried day trading. I tried penny stocks. I tried going for high dividend yield stocks. If I was just starting investing today, I guarantee you I would be on Robin Hood trading crypto. I would be trading options. I would be doing all the things that new investors they're doing today simply because they don't have the right mindset for actually building wealth in the market. So there's nothing wrong in my book with trying to create money in the short term through the market. I just don't know how to do it reliably. So my fallback is buy and hold great businesses for the long term because that's the style that works. I went through the same exact cycle where I was

Starting point is 00:05:56 trading penny stocks. I day traded for six months full time. Literally did not make any money. I lost money while I was doing it. But for six months, I thought I could figure it out and just never did. I started to invest in just a bunch of different things and then realized, okay, long term is the way to go because every single time I try to figure out, you know, how to time the market. or anything like that. I'm wrong. And so for now, we're going to go long term. That's when I started to kind of go into individual stocks, index funds, and ETFs, those types of things. So that was a big, big difference maker for me. Now, AI helps a lot of people with a lot of different things right now. And specifically, it can really help you when it comes to researching specific things. So why do you

Starting point is 00:06:32 believe AI can kind of help us accelerate our process when it comes to researching as an investor? Because this is going to be a tool that a lot of us can really help utilize. We're digging through 10Ks and all these different things. But instead, how does it actually help someone like an investor out there accelerate their process when they are researching stocks? So AI by its basic design is a wonderful resource for investors to use because at its core, AI is really fantastic about ingesting gargantuan sums of data and then using what it learned from ingesting that data to help users come up with insights from huge amounts of information. When you boil it down investing to its core are investing the way that I do, which is individual company analysis and then adding

Starting point is 00:07:15 them into my portfolio. That's a perfect use case for what AI is built for. So with AI, you can take a long, multi-hundred page annual report of a company, upload it to AI. And if you prompt AI the right way, it can parse through all that information very quickly and help you to glean some insights from it. It can also go through conference calls. It can go through earnings reports. It can go through proxy statements, and it can explain to you in plain understandable English what you need to know about that company. So it dramatically lowers the skills that you need to get started with analyzing individual businesses, and it can act as a tutor slash buddy for figuring out what the terms means. So it is a godsend for new investors that are trying to learn how to analyze

Starting point is 00:07:59 companies. I think that's the most powerful thing is for most people out there, this can tremendously help you, especially if you're a brand new investor. This is going to help you so much more than what we used to have to do. We'd have to kind of read all these books and figure out what we need to do. I have to figure out, you know, how do I even look at this 10K and how do I read through all this stuff? And so this is going to help you tremendously when it comes to that research process for sure. Now, can you explain your junior analyst analogy and how that mindset helps investors utilize AI more effectively? Yeah. If you are going to be using AI to help you research companies and make decisions, it's really important that you approach AI with the appropriate mindset.

Starting point is 00:08:34 And I stole this from somebody else, but they basically said, Think of AI as a junior research assistant or think of them as an intern. If you were a fund manager and you have analysts working for you, you would not outsource all of the key critical information to that junior analyst, nor would you just did that junior analyst unlimited control over what it does. If you were going to be using an intern or an analyst the right way, you would give them a specific task, give them a specific set of instructions to follow, you would limit the number of resources that they could use,

Starting point is 00:09:07 and you would have that analyst or junior analyst ask you questions to make sure you're getting the information that you want. As an example, if you've ever gone to chat GPT or Claude or Grok and say, hey, is Amazon stock a buy? That is way too broad of a question to possibly ask an AI because it doesn't know what specific steps or instructions you want to follow. So it will do exactly what you tell it to do. So it might go out and look at Amazon's recent earnings report.

Starting point is 00:09:36 It might look at sentiment. It might look at technicals. And none of that might be useful to your specific investing process. So if you don't constrain that the AI into the instructions that you specifically want it to do, it's not going to give you anywhere close to the right analyst. The same way, if an intern fresh out of college, you said, hey, is Amazon a buy? If it knew nothing about your investing philosophy or your investing process, it's going to go out, find information and present you,

Starting point is 00:10:02 information that is basically utterly useless to what you want. So if you have the right mindset of thinking of the AI as a junior analyst, that's really going to help you to come up with a prompt to give that analyst instructions to follow to make sure you get exactly the information that you want and none of the information that you don't. I think that's one of the most powerful mindset shifts that people need to have is you can't just take every single thing that it says kind of utilize that information to take action. You have to utilize it as someone who is an advisor or a junior analyst in your life that can kind of help you make decisions as time. goes on. Now, when do you think investors should kind of think through and utilize their own

Starting point is 00:10:37 judgment? Because your judgment still matters in today's day and age. So when should they utilize their own judgment rather than AI? Yeah, you have to be the ultimate decision maker. After all, if you're into making investment, this is your money that's on the line. And if the AI makes a mistake in the analysis, it's going to cost them nothing. And if anybody here has been using AI, you've probably noticed that the AI gives you the wrong information or the analysis back. related to investing. And then when you push back or correct the AI, at least for me, it always says, you're right. I totally overlook that. Way to go. And it has a very positive bias to it. So I would never outsource all of my decision making and thinking to AI. That would be a bad use of AI,

Starting point is 00:11:18 especially with investing. Again, this is my money that's on the line. So I want to make sure what AI is doing is the task that it's most well suited for. Go out, find information, ingest information, analyzing it using the rules that I said, and then present that information back to me so that I can make a more informed decision. That to me is using AI the right way. It is. And I think there's all these memes that are coming out now where I saw this commercial the other day where a kid was walking into a gas station and the gas station attendant, you know, asked him, hey, how's your day going? And he looked at his AI and said, my gas station attendant just said, how's your day going. What should I do next? And like that's how some people use AI. They think of it and

Starting point is 00:11:52 they use it as their only thoughts, especially with stuff like this. And you got to make sure that you're still utilizing your own judgment because it's really, really important, especially as we start to go and AI keeps advancing, and this is going to be really, really important for a lot of people to be able to do that. So a lot of people also worry about AI hallucinations. And so how do you personally make sure that the information you're seeing is trustworthy and kind of vet that information? Yeah, this is a huge, huge problem. Again, if you've used AI for any decision making or research in any other aspect of your life, you've probably seen it bring back information and you just intuitively know that's wrong or that's not right. And AI tools that are out there are unbelievably

Starting point is 00:12:29 complex and sophisticated, but they can provide you with wrong information or they can make up facts and then present them to you. So that is a huge problem. In fact, when I was doing research and how to use AI the right way, I was talking with lots of investors that are in my community. And this was the number one concern that they had before they would bring AI into the research process. They were basically, how can I possibly trust the information that's coming back from AI, given the hallucinations that happened? I do think there are steps that you can take to minimize the number of hallucinations that exist and to make sure that you can actually trust the information that comes back. But again, this is why you can't ask it broad, unbounded question like,

Starting point is 00:13:07 is ABC stock a buy? You have to get much more granulated than that, and you have to provide it with very detailed, highly specific prompts to make sure the information that you get back is trustworthy. And that's, I think, one of the most important things is kind of breaking it down and understanding how to prompt it properly. I know for a lot of times, we do a lot of really deep research with AI when it comes to just even looking at historic market data, or we'll look at statistics and kind of break down some really advanced statistics when it comes to people's finances. And when we do that, if I try to do one big, large prompt, it is something where I don't get the information back that I want. And so I have to break down the prompts and the research into

Starting point is 00:13:42 much smaller chunks. So why for you is breaking, you know, research into smaller modular prompts so important? Yeah. So with any complex tasks, again, researching a stock from scratch, at least for my process, there's lots of little micro tasks that are embedded in that question, such as what does the company do? What is its business and business model? Another task is, what is the company's moat in competitive advantage? Other task is what are the company's financial statements? Another one is, what are the company's growth prospects? Another one is, what are the company's risk? What are the company's management teams? What's the company's valuations, etc., etc., etc. Again, if you ask a very broad question to analyze a business, and it's going to have to go

Starting point is 00:14:18 through each of those steps. If you don't break those steps down into miniature steps for the AI to tackle on, it could be reasoning up from faulty information. So if it gets the business and the business model wrong, how could it possibly have the moat and the growth potential, right, if it's literally looking at the wrong company or the wrong competitive advantage? So breaking complex tasks down, like researching a stock, into smaller steps, and you can verify the information of those steps as you go, allows you to use building blocks that you can trust and building on top of that as your research up. So yeah, just an overall great thing to do with AI and general is to take big tasks, break them down into smaller microtasks, verify the information of

Starting point is 00:14:58 each of those tasks as you go, and that will give you much more confidence in the final output. And for those of you out there listening who just have not been prompting properly, you feel like you've been using AI and you use just, you know, a couple of lines and all of a sudden, you're getting all this information back and it's not as detailed as you'd like it to be. If you break it into smaller chunks like what Brian's talking about here, this is going to make a big, big difference and just get way more granular and specific. That's going to help you tremendously. And if you develop processes like we're talking about today, that is going to change the way and the information that gets spit out to you every single time you have these conversations with AI. I remember when I needed to hire someone fast, but finding the right person quickly felt impossible.

Starting point is 00:15:37 And if you've ever been there, you know how stressful this can be. That's where Indeed comes in. When it comes to hiring, Indeed is all you need. Instead of struggling to get your job post noticed, Indeed sponsor jobs help you stand out and hire faster. Your post jumps up to the top of the page, making sure it reaches the right candidates. And it makes a huge difference. Sponsored jobs on Indeed get 45% more applications than non-sponsored ones. And there's no need to wait any longer.

Starting point is 00:16:04 Speed up your hiring right now with Indeed. And listeners of this show will get a $75 sponsored job credit to get your jobs more visibility at Indeed.com slash personal finance. Just go to Indeed.com slash personal finance right now and support our show by saying you heard about Indeed on this podcast. Indeed.com slash personal finance. Terms and conditions apply. Hiring, Indeed is all you need. So lately, I've been noticing how fast things are changing at home. The kids are growing like crazy. Clothes don't fit anymore and routines are changing. And it just hits you. Life is expanding.

Starting point is 00:16:40 And when your life grows, your responsibility grows with it. That's something I've been thinking about more this spring, making sure the safety net we have in place actually matches the life that we're building. And that's where PolicyGenius comes in. PolicyGenius is an insurance company. They're an online marketplace that helps you compare life insurance quotes from some of the top insurers in America, all in one place for free. And their licensed team works for you, not the insurance companies. So they help you find the right coverage for your situation without all the guesswork. And they walk you through everything. Answer your questions, handle the paperwork, and help you get the coverage that actually fits your life today and where it's going. So protect your family,

Starting point is 00:17:19 with a policy that grows with your life. With PolicyGenius, you can see if you can find 20-year life insurance policies starting at just $276 a year for $1 million of coverage. Head to PolicyGenius.com to compare life insurance quotes from top companies and see how much you can save. That's PolicyGenius.com. Frozen lasagna, medium power, 15 minutes. Sounds like Ojo time.

Starting point is 00:17:44 Let's play. Feel the fun with Play-Ojo. The online casino with all the latest slot. and live casino games. What you win is yours to keep with no wagering requirements, instant payouts, and no minimum withdraws. Hey, I just won. Woohoo.

Starting point is 00:17:58 Feel the fun. Play, Ojo. Honey, forget about the lasagna. Let's celebrate. 19 plus Ontario. Only please play responsibly. Concerned about your gambling or that of someone close to you. Call 16-531-2600 or visit connectxontera.ca.

Starting point is 00:18:08 Amazon presents Jeff versus Taco Truck Salsa, whether it's Verde, Roja, or the orange one. For Jeff, trying any salsa is like playing Russian roulette with a flame thrower. Luckily, Jeff saved with Amazon and stocked up on antacids, ginger tea, and milk. Habanero? More like Habinier, yes. Save the everyday with Amazon. So when it comes to this, so we're talking about ways to research, we're getting this information back.

Starting point is 00:18:43 How do we kind of gauge the difference between our own judgment and what AI is telling us? How do we make decisions based on having two sides of the coin? Because we could have previously believed one thing. AI spits out some different information. So how do you kind of utilize your judgment and balance that with AI's information? Yeah. So there's a couple of core prompting techniques that I think are just good AI hygiene that investors can use to make sure that the information that they're getting back

Starting point is 00:19:07 is as trustworthy as possible. And again, if you don't have full confidence and full trust in the process of the information that you're getting back, doing this analysis will be utterly useless to you. won't give you any advantage at all. Having conviction in the information and making decisions making on solid information is absolutely foundational. So there are three techniques that I think listeners should know. And if you do all three of these techniques, I think your confidence in the information that you're getting back will just be sky high. So one technique that I think everybody should do when using AI is to assign AI to be a specific role. As a really simple example,

Starting point is 00:19:43 let's say you're a value investor and Warren Buffett is your investing hero. Hero. One of the things you put into the prompt is act as Warren Buffett. Act as Warren Buffett. If you give it that simple one sentence up front, what AI will do is go through its vast database of information that's using to making decisions and it will prioritize information that is pulled from analysis on Warren Buffett. So it might use Berkshire Hathaway's annual meetings transcripts. It might use interviews that Warren Buffett has done.

Starting point is 00:20:12 And immediately the AI will know that you're looking at value investments. It might look at Warren Buffett's portfolio to pull information from. It'll know what the terms like moat and management mean. It'll know to emphasize factors like return on equity and competitive advantage. And that simple one-word phrase, act as Warren Buffett, will dramatically improve the quality of information that comes after that. And of course, you don't have to limit it to Warren Buffett. You can say, act as a value investor.

Starting point is 00:20:39 You can say, act as Joel Greenblatt. My favorite investor to follow is a guy named Terry Smith of a fund Smith. So I would say act as Terry Smith. If you're a short seller, you could say act as a forensic accounting. So assigning the AI a role up front, wow, that one step alone will dramatically increase the quality information you get back. 100%. And I think that is one big thing that you could use in everyday life, you know, across the board. I've even done this where I have utilized AI and assigned it a role based on, you know, specific athletes. So one big thing I did over the course of the last year was trying to get in the best shape

Starting point is 00:21:12 I possibly could. And so I looked across the board and I was looking at, you know, different athletes out there and what they are actually doing. And so if you can assign that role to a specific person, it will act in that way and it will help you kind of make decisions. And I think that's really, really important. So you also have some other core prompting techniques. So the first one is assigning a role, making sure we have that role in place. But what other techniques can you talk through in terms of how people can actually prompt AI to make sure they get the right answers back? So prompting technique number one, force it to assign a role. Technique number two is to force it to use citations and force it to look up information from resources that you trust, that you personally

Starting point is 00:21:50 trust, because if you're restricting the resources that it can use to create that information, you're building on a solid foundation. Now, for me, when researching companies, resources that I trust are very, very few and far between. I trust the SEC filings. I trust information that comes directly from the company, and then I trust a few other sources such as Morning Stars Motes scale. So when it's presenting me with information, I force it to put a citation with a link to where it got that information from. So as I'm reading the results of the prompt, if I'm like, where did it get that information from or why is it saying this? If you click over to the citation, it will take you directly

Starting point is 00:22:30 to the SEC filing or the company filing that that information came from so that you can confirm easily that the information that it's building on top of is correct. So again, if you limit the places that the AI can pull sources from, and you force it to give you a citation of where it came up with that source from with a direct link, that dramatically increases the trust that I have and the information that's giving me. For sure. And I think these direct links have gotten so much better. I remember early on prompting AI, like, where did you get that information?

Starting point is 00:22:57 It would try to pull sources from just these random places. But once it kind of understands the core sources that you want to have in place, it'll remember that information. It'll make sure to pull from these places that you actually wanted to pull. For example, one of the places we always wanted to pull is all the Federal Reserve data that comes out when it comes to consumer spending and finances and those types of things. And so if you can kind of set it up in a way where it knows what sources you like, then that's going to be really, really important. And then you also talk about when we're prompting, we need

Starting point is 00:23:23 to make sure we have the proper order and the proper steps in place. Can you kind of talk through how we set that up as well? Yep. So step three here is to give the AI a step-by-step instruction to follow to make sure that it is following the process that you would use to analyze a company in its own way. So for example, when I'm analyzing, a business for the first time. The very first thing I want to know is what does this company do? What are its key products and services? Who are its customers and how frequently do they buy? What geographies does the company operate in? What are the revenue segments by a product line or category? And then I also want to just know about the company. Do I think this company can raise prices in the

Starting point is 00:24:02 future? What happens to this company during a recession? Are its product and services highly cyclical or are a recession proof. So a prompt that I built helps me do exactly that. So the prompt goes step by step through answering the specific questions that I want to know about any business in the order. And then it presents it back to me answering it in the exact stepwise function that I have. So not only are the prompts that I've built built out to answer steps in a stepwise function, but I use the prompts to analyze one part of a business and I give it specific instructions for how to do so. So if you have an investing checklist that you use, or again, if you're you, you're going to you wanted to analyze a stock like Warren Buffett, you can literally say to the AI, follow Warren

Starting point is 00:24:42 Buffett's investing checklist. And it will know the process that it should use to research information. So if you tell it, do A, do B, do C, do D in that order, and use citations, the trust that you will have and the information that comes back to you will be sky high. And this is why it's so important, I think, for a lot of people out there to start to build out a bank of prompts that they're going to be utilizing more frequently. Because a lot of people, what they do is they throw it into chat, gpT or whatever AI they are utilizing. And then all of a sudden, these prompts just kind of disappear. They forget where they left them and you got to build out the whole prompt again. But you got to make sure that you have this database in place that kind of helps you, when it comes to getting

Starting point is 00:25:17 started and utilizing those prompts on a regular basis. So, Brian, if we can, can we jump into a live demo to kind of show what this looks like and maybe we can analyze a company like, you know, IREN or IREN and kind of go through step by step using your prompting system. And for people listening here, if you want to watch us visually do this, you can join us. on YouTube if you're only listening to the audio side. You can join us on YouTube and we will share the screen so that you can see exactly how this works and what goes on here. Yep. So let's do that. So IREN is a company that you know well and honestly, I do not know it well. So I'm going to copy and paste over a prompt that I have here. Let me just walk through this prompt so that people

Starting point is 00:25:55 can understand. And by the way, we'll give you free access to this prompt. So this prompt that I call is called the business analysis prompt. And right up top, I tell the prompt, I'm going to zoom in here so you can a little bit easier for anybody that's watching at home. So I'm saying you are executing a business analysis prompt, and I'm telling the AI, follow each instruction precisely in order. The next thing I'm saying is your identity is you are an expert. You are an expert in financial analysts, specializing in business model analysis from SEC filing.

Starting point is 00:26:27 So I'm giving it a role right up top. And then I'm saying your mission is to request the company name from the user, that's us, analyze the most. recent 10k, answer the questions that I have down below about the company's business model, output them in a clean markdown filing, and provide information answers and being not too brief but not overly detailed. And then there's some execution data in here. There's a specific sequence that I wanted to go through, ABC. There's a verification process that goes here. And then there's the output method that I want. And I also insist on original sources. So this is a bit

Starting point is 00:27:03 of a meaty prompt. Again, people that are listening will get free access to this in just a little bit, but I've put that in there. And then if it does it correctly, chat GPT should then say, okay, I understand what company do you want me to do this analysis on? And that's the thing that I've learned. Have the AI ingest the information and then ask you afterwards what company want to do on, rather than happen to go into the prompt itself and put the company name on here. So I'm going to skip over and just say, what company, tick or simple, do you want me to analyze? And I will retrieve the most recent information as of today's date. So this is IREN, and I'm going to push enter. What's the name of the company? Do you know? Yeah, the full name is Irene. IREN, I-R-E-N-Llimited is the full name.

Starting point is 00:27:46 Yeah. So it's, I find it's best if you do the company name and the ticker symbol. So I-R-L-Limited, and the ticker is IREN. So let's go ahead and put that out there. And here's what we got back. So let's read right at the top. So it says using I-R-L-L-L-L-Lam, it's 10-K, so it's annual report. as of June 30th, 20205, and it's 10K from June 20th, 20204. And right next to it here, Andrew, where it says, SEC filings. So there's the link, and if I click that link, it should take me right to the annual report from 2025. This is where this prompt is pulling the information from. So we have confirmation that this is the right company, and this is the most recent 10K.

Starting point is 00:28:27 So that gives me a heck of a lot of confidence in what I'm about to read. Exactly. I think that's one of the most important things people need to understand is, we're pulling from the correct location, the SEC filing. Somebody lies on this, they're going to jail. So this is a huge, huge deal for sure. Yeah. Okay. So right, I have this prompt program to say, what does this company do? So let me read back and you can tell me if this is correct. Iran, which used to be called Iris Energy, is a company that operates in the digital infrastructure slash blockchain slash AI cloud space. It activities are Bitcoin mining, AI cloud data center services, where repurposes are augmented infrastructure. And it also generates other income from electricity, resales, and participation in programs. Now, each of these are point by points and there are. links next to each of those bullet points so I can double check if I want to click where it found

Starting point is 00:29:15 that information. So it says overall IRN is a hybrid between a crypto miner and a cloud GPU infrastructure provider. Is that accurate? That is accurate. And the thing that big one for sure is the data center services, but that is 100% accurate. Okay. Great. So it got that one correct. Next one. Next question I have is how does IRN make money? This is a key question for me. So based on its 2024 and 2025 disclosures, revenue sources include Bitcoin mining activity slash proceeds from the sale of mined Bitcoin, which is its largest and foundation of revenue driver. AI Cloud Services revenue, although small, this is a growing vector, and it brought in $3.1 million

Starting point is 00:29:54 in sales in 2024. And then other income include electricity resales, demand response program, gains of financial assets. So in last year, AI Cloud was negligible, just $3.1 million compared to mining income. So mining dominates and compare it to $501 million in total revenue from its Bitcoin mining business. And again, there are SEC filings, links next to all this information. Is that accurate? It is for sure accurate. And then for 2020 and then 2025, which is what's going to be kind of interesting is we'll see a drastic difference in some of the data center stuff, which will be

Starting point is 00:30:27 interesting. So if you've never heard of this company before, I know it's a Bitcoin miner with GPU cloud services businesses. And Bitcoin mining is the vast majority. already of sales right now, but this AI cloud services business is growing rapidly. Great. So next question, who are this company's customers? So it says for Bitcoin mining, the customer is just the open market, right? It sells Bitcoins to the open market. For cloud services, the customers are third-party compute clients like AI firms are enterprising that need GPU capacity. And for the electricity such resale demand response, counterparties could be grids or local utilities. What do you think of that response? That response, I think, is good.

Starting point is 00:31:06 And I think the order of operations at the grid and local utilities thing is, I think, is a huge portion of what's going to be coming forward, which is interesting. Okay. Next, where does the company operate? So this company is incorporated in Australia and uses U.S. operations for its mining and data center assets. Its revenue is not broken out by region, but its major operational assets are in the U.S., such as Childress, Texas for mining and data center expansion. and the geographic exposure is mostly U.S. operating assets with its corporate parent in Australia. Is that accurate? That's accurate. Yep.

Starting point is 00:31:40 Great. Okay. Next. Business dynamics. So these are some custom questions that I want to know about every company. The question I have is, so how often do customers buy? For me, this is a key question. I want to know do customers buy from the company continually or is an occasional purchase every couple of years. I prefer customers that buy continually.

Starting point is 00:31:59 So, what's it say? It says, in mining, revenue, is continuous and operational. Bitcoin is mined every day and sold every day regularly. In AI Cloud Services, contracts might be recurring, like a multi-year lease, but as of now, they are a small part and likely early adoption with multi-year commitments. And then retention is nascent in the AI business, but in mining, retention is not applicable because it's not a contract business.

Starting point is 00:32:25 It's selling to the open market. Is that accurate? That's accurate, yep. If we want to look up where to get information, we can just look at the SEC filings. Looks like this one came directly from the company's most recent earnings report. So the information that's pulling from, everything that we're talking about here is sourced, is sourced directly. Next key question for me is can the company raise prices?

Starting point is 00:32:44 Warren Buffett says that the number one most important factor of any business is pricing power, the ability to raise prices. So let's see what it says. Okay. In mining, pricing power is weak. Bitcoin is a commodity. The price is set by the market. So the company's ability to make profit depends heavily. on electricity costs and mining efficiency, not markup.

Starting point is 00:33:04 In AI cloud services, there may be more pricing power, especially if demand outships supply, but competition is intense and customers may negotiate. And the 10K mentions risk factors about exposure to volatility and crypto prices and electricity cost pressure, and their margins will depend on operational efficiency, discounting, and capacity utilization more than pure price marketing. Is that accurate? Yes, that is accurate. So far, so good then. Okay.

Starting point is 00:33:31 Next question I want to know is, what happens in a recession? I like to invest in companies that are recession resistant and have demand for their products no matter what's happening. So what's it said? It says Bitcoin demand or price may drop sharply during economic stress, hurting its mining revenue significantly. Cryptocurrencies tend to be volatile and correlate with risk appetite. Operating leverage and fixed cost structure, such as electricity and depreciation, means margin pressure if revenue collapses. And the company's annual report notes uncertainty about its ability to raise capital and sustain operations under stress. So last year, they flagged significant

Starting point is 00:34:11 uncertainties exist about the company's ability to generate positive free cash flow and raise capital. And that suggests that the business may be fragile in a downturn if macro shocks, reduce crypto valuations or raise borrowing costs. Would you agree with that? I would agree with that. And here's one thing I want to point out to people listening right now. This is a great example of how this prompt is going to help you when it comes to becoming a long-term investor. So if you're a long-term investor and you read something like this and you go through here and this research comes back, this means you want to dive deeper into this area because if you think that this is not a recession-resistant business, that's a huge problem for long-term

Starting point is 00:34:45 investors because we want to hold these companies for long-term. And so this can help you make decisions based on that. This is just one example of many that we're going through here. Yeah. And then the final thing here are sources. So it has links to all the sources that are used to create the document. So it has SEC filings from 2025, the annual report, and 2024. It's got the most recent earnings and public failure from stock analysis.com. And then it's got recent results commentary directly from the company's investor relation port. And I'm using chat GPT here.

Starting point is 00:35:15 And chat tip T is allowed you to click directly into any of these links and it will take you directly to the source. Now, as we showed, this was a prompt that followed the analysis to say we gave it a specific role. We gave it specific step-by-step instructions to answer the questions in order, and I insisted on direct sourcing of information with links. So while I've never researched this company deeply before, based on this, I really trust what AI put back to me because it followed the key principles of prompting. Exactly. And I think that the huge key here is, again, remember, these are pulling from the proper sources, the sources that you actually want to be looking into.

Starting point is 00:35:52 It's not any hype or any extra, you know, fluff that's out there. Instead, this is pulling from these sources there where you want the real information, the information that, you know, actual investors will be looking at before they invested in something like this. All right. We have plenty of time. Do you want me to do another prompt on this company or do you want to do a different company? Sure. Let's do a different company that maybe we'll do one that more people know and we can try to do

Starting point is 00:36:15 one that makes sense that goes forward. We can do a blue chip if you want or we can do something else. Whatever you'd like, man. I'm happy to go whatever you want. Let's do, yeah, let's do Apple. That's perfect. We'll go with Apple. Sure.

Starting point is 00:36:27 All right, so we're going to do Apple next. We're going to do a prompt for Apple since a lot of people probably know what Apple does currently. This is going to help you see what the prompt actually spits out. When you stop, shout GPT, let me put the prompt in. Same prompt, copy and paste them. We'll go through that same process there. And if this prompt is working correctly, what I should get back is what company do you want to research now, which is exactly what it says.

Starting point is 00:36:47 And I'm going to say Apple, APPL, and I'm also going to do the ticker symbol, AAPL. I find it's good to do both the company's name and the ticker symbol. All right. So here we have same prompt, and it says right at the top, I'm using Apple's 2024 10K, which ends in fiscal year, September 28, 2024, and the Q3 of 2025, the most recent quarterly report, which is from business ending June 28th, 2025. So it's using the most recent annual report and the most recent 10Q or quarterly report, so we can at least have confidence that it's pulling from the most recent information.

Starting point is 00:37:23 All right. What does Apple do? And Chat Chip-T says Apple designs, manufacturers, and markets, consumer technology products, heartware, and delivers a suite of software, services, and digital content. Its product line includes iPhone, IMac, iPad, wearables, home accessories, and its services include the App Store, ICloud, Apple Music, Advertising, Cloud Services, and licensing. That sounds pretty accurate to me. Yep. Great. Question two.

Starting point is 00:37:49 How does Apple make money? It says Apple's revenue is divided into two categories. products and services as of the six months ending march 29th 2025 here's an illustrative breakdown so products which are iphone iMac ipad and wearables were 167 billion dollars out of the 220 billion total so 76% of total revenue was products base and then services were 53 billion dollars out of the total so 24% of the company revenue was services based. And it says within products, iPhone is typically the largest single component with iPhone accounting for $47 billion as of the quarter ending March 29th, 2020, 2020, 2025. So again, if I click into one of these here, where did it get this information from? Actually, I'm going to go back and I'll click into the most recent 10Q to see where it got that

Starting point is 00:38:49 information from. And it should pull up the 10Q. So this is the company's most recent 10. Q. And if I scroll down, I can see the split between revenue in products and services. And this says, let's see, $219 billion in total revenue. Is that what it said? So there's a $219. I have the direct source of information from there, $166 billion in products, $166 billion in products, and then $53 billion in services. $53 billion in services. So I can click and see where to come up with this information from. I got the direct link and we verified manually that that information was 100% accurate. So good job, Chad Chip-T. Love that. And I think that's why it is so important to prompt this properly because you have those sources linked up and so you can see and you can double-check.

Starting point is 00:39:37 This is also a very important thing to do is when Chat Chip-T or whatever you use spits this back out, make sure you're double-checking some of these numbers and kind of going back and forth to ensure that it's actually giving you the right information. Yep. If you're going to make in making investing decisions, make sure you're making them based on solid information. And we've done everything we can. to make sure the information we're getting is solid, but it doesn't hurt to double check. Okay. Next question is, who are the customers?

Starting point is 00:40:00 Well, according to the chat, Chipit, and customers such as individuals purchasing Apple devices, enterprises and institutions using Apple devices, services, and deploying within IT infrastructure, developers and content providers, and third-party licensing technologies using Apple's cloud advertising platform. I'd say that that's pretty accurate.

Starting point is 00:40:19 Yep, I would 100% say that, yep. All right. Next, where does the company operate? So Apple operates globally with significant revenue coming from multiple geographic regions. As of Q2 of 2025, 42% of sales were from the Americas, $92 billion, 26% of sales were from Europe at $58 billion. Greater China was 16% of sales and Japan was 7.4% of sales with the other regions making up the rest of the balance. So it says U.S., Americas, Europe, and China are the company's largest and most important regions. So how useful is that, right?

Starting point is 00:40:56 Immediately we can know that Americas are the most important segment, but Apple has more sales outside of America than inside it. This is part of my argument about international, when looking at index fund portfolios and part of the international exposure of all these U.S. companies that are operating out there. And you can figure out how much international exposure they actually have by doing something like this. Yeah. And figuring this out, you can use SEC filings to figure this out, but isn't it solid? slightly easier to have chat TPT to it for you. 100%. Yep. I mean, you're saving hours of time right here. For sure. Next, business dynamics. How often do customers buy? So what's it say here? So hardware

Starting point is 00:41:29 tends to be purchased periodically. Devices upgrade every few years and seasonally around launches. That makes perfect sense to me. Services tend to be recurring in nature. So ICloud, Apple Music, Apple TV are more subscription-based and app store fees and licensing are more perpetual. Apple reports deferred revenue for some services like prepaid services and expects portion to be recognized over one to three years. And it had 13.6 billion in deferred revenue. Two-thirds of WISP will be recognized in one year. How's that for granulated information? Yep. And then finally, high retention is services is implied by the ecosystem lock-in and switching costs. So I've been an Apple consumer for many years and I would say that that is spot on analysis.

Starting point is 00:42:16 100%. I think they nailed it right there. Next, can the company raise prices? So what's it say? Apple has some pricing power, especially on premium devices via its brand value. In its risk disclosure, Apple cites currency fluctuations, competition, and components cost pressure as constraints. Service margins can expand, and Apple can raise prices significantly over time on cloud tiers and subscription bundling.

Starting point is 00:42:42 However, aggressive increasing risk customer pushback and competitive. situations. Again, I would pretty much agree 100% with this. Me too. Next question, what happens in a recession? During economic downturns, demand for discretionary hardware like smartphones, computers may soften. Services tend to be more resilient. Apple's scale, strong balance sheet, diversified geography, and ecosystem helps it to weather volatility. And in past recessions, the company maintained margins through cost control, supply chain management, and focusing on high margin services. So, and then saying, I can build a sensitivity analysis for Apple compared to its peers if we want to, and then we have all of the sources pulled from there. So yet again,

Starting point is 00:43:25 if you were a brand new investor or Apple investor, I bet that you, even if you've been investing in Apple, I bet that this prompt might even teach you something about the company that you've owned and think you know so well. I think so. And I think that shows right there. You know, we looked at one example of a company. Most people probably don't know. We looked at another example of Apple, which most of you will know, and you'll know even if you haven't invested in Apple before, you know all about its products and its services and everything it offers. And this shows how powerful this prompt can be to get you started. It's a starting point where really you can look at the analysis of these companies and save yourself hours and hours of time. I mean, to find out

Starting point is 00:44:00 all this information in the past, I would have spent hours just reading through 10Ks and making sure the information is correct. And did I remember that correctly? Did I write that down properly? And so this is all in one spot. And I think it's really, really important for people to be able to utilize this. It's really, really powerful. So, This is absolutely awesome. And have you kind of started and utilized this stuff in your everyday journey? Is this kind of where you started with a prompt like this when you're looking at a new company? Yep.

Starting point is 00:44:22 So I have a series of about nine prompts that I go through. So that's the first prompt that I do. Like to me, question number one is always what is the company and what does it do? Because once I understand what the company is and how it works, I'll know, am I interested in this company and learning more or am I not. So I think this is a great first filter. So this is one of several prompts that I have. I have prompts that just to analyze the company's moat.

Starting point is 00:44:42 I have just prompts to analyze the company's financials and key metrics. I have prompts to analyze the company's management team, the company's risks, the company's valuation, company's opportunity, and more. So this is the first prompt in a series that I use, but it's absolutely been a game changer for me to analyze companies quickly. And so if someone out there wants to start using AI for fundamental analysis going forward, what are some of the most important things that they should remember based on, you know, what we talk about here today?

Starting point is 00:45:08 Yep. So key things are one, give it a roll, assign it a role. Step number two, limit its uses of sources and insist that whenever it gives you information back, that it puts a link to the source that it pulled that information from. And then three, give it a stepwise function. Now, do A, do B, do C, do D. If you have a checklist that you use to make investments, upload that checklist. If you want it to help you create a checklist, give it instructions to help you make a checklist.

Starting point is 00:45:33 But putting time into building out a series of prompts for yourself will save you hours upon hours of research down the road. But if you would hear to those three core principles, I think that AI can become your best friend when it comes to stock analysis. Well, Brian, this has been so incredibly helpful. And I think it's just been a powerful lesson for a lot of people out there. They can go take action right now on this stuff and utilize this. So where can people find out more about this prompt and where can they access this prompt? Where can they find out more about you and everything else you have going on as well? Yep. So I'm available on pretty much every social platform. But if you want a free copy of that full prompt that we just did, the business analysis prompt on those seven questions, just go to longterm mindset.com backslash pf for personal finance podcast. And that will take you into a link where you can download a free copy of that full prompt. And you can even use that prompt as a template to create more prompts for yourself. But I think there's huge value in just seeing the way that the prompts that I've built are structured. So you know how to prompt properly. Awesome. This has been so incredibly valuable. Thank you so much again, Brian, for coming on. And we're going to obviously have you on again soon. Awesome, Andrew. Thanks for having me. Always fun to be here.

The Personal Finance Podcast - How to Use AI to Research Stocks (With Brian Feroldi)

There aren't comments yet for this episode. Click on any sentence in the transcript to leave a comment.