This is the Everyday AI show. The everyday podcast where we simplify AI and bring its power to your fingertips. Listen daily for practical advice to boost your career, business, and everyday life. I think for the last year and a half or so, GPTs from OpenAI have largely been ignored. So, in November of 2023, Open AI announced their custom GPTs feature, a way that people could go in with no code and essentially create a custom version of their popular chat GPT for themselves and for their specific purposes. And I think at the time it was completely overhyped, number one, but maybe more importantly, the GPTs did not have access to the best that chat GPT had to offer. it couldn't it uh you know really take advantage of all of the tools and modes within chat GBT at the time. That now has changed because OpenAI recently updated custom GPTs. So in today's episode, we're going to be going over uh not just what's new and how they work, but why it matters for your business and show you some live working examples of what the upgraded GPTs can do. All right, I hope that sounds exciting to you. It sounds super exciting to me. Uh, so welcome to Everyday AI. This is your daily live stream podcast and free daily newsletter helping everyday people like you and me not just learn what's happening in the world of AI, but how we can make sense of it, leverage it to grow our companies and our careers. Starts here with the unedited, unscripted live streaming podcast. But if you really want to take it to the next level, be the smartest person in AI at your company, our website is your cheat code, your everydayai.com. So once there, go sign up for that free daily newsletter if you haven't already. We're going to be recapping the most important insights from today's conversation, but also go listen to now more than 550 back episodes uh from the smartest people in the world that I've gotten to interview. I steal all their secrets. I give it to you. It's a free generative AI university. Go check it out. Uh if you're looking for the AI news, we're going to be dropping that in the newsletter. Uh also, let me know, should we do a part two next week? So, listen uh to the rest of this uh episode. And I swear this time it's actually going to be a little faster. Um, and if you want more, uh, going over some more advanced elements of custom GBTs such as actions, uh, context stacking, uh, and building specifically for the 03 model, which is what's new. Let me know on the live stream, maybe just type in the word advanced, uh, or if you're, you know, a podcast listener, I always put my my email in there or just reply today's to today's email and just say advance. I just want to know uh you know I can only make this thing better if you tell me what you want or what you don't want. And what this is this is our new weekly segment on Wednesdays called putting AI to work on Wednesdays. So uh we're going over like I said the new update the biggest one uh inside uh the custom GBTS is the ability to use OpenAI's newest and latest model. uh not just their 03 model but all the other uh thinking and reasonings and some other uh kind of variations of the GPT series as well. Uh so uh you know what uh yeah. All right, let's first go over kind of what's new, then we're going to jump over start some things live. Yeah, you got to love doing live demos. Nothing ever goes wrong when working with generative AI. All right, so here is what's new in custom GPTs. So, uh, this is from OpenAI's website, but it is expanded model support for custom GPTs. So, uh, creators can now choose from the full set of chat GPT models, GPT40, 03, 04 mini, and more when building custom GPTs, making it easier to fine-tune performance for different tasks, industries, and workflows. Creators can also set a recommended model to guide users. Right? So when they say creators and users, if you're just building it for yourself, you are the creator and the user. Uh but if you didn't know, uh GPTs, there's also like a store element. So you can just put it out there to the open public. You could in theory keep it as a private URL and sell access to it. Uh so uh there's some different things you can do. So some key details and this is from OpenAI's uh kind of uh help docs. So GPTs with custom actions uh can use the model picker to select from all models uh or sorry uh without custom actions. Uh you can use any model if you do use custom actions and let me know like I said type in the word advance if you want to go over that next week. Uh this is where you can you know use things like web hooks uh APIs etc. Uh but if you are using that it can only use the GPT40 or the 41 model. Uh and right now building GPTs is still limited to only paid users on the web. Uh so even paid users on desktop cannot build uh GPTs in the enterprise and edu. Rollout is coming soon for the extended uh model support. So right now even if you're on an enterprise or edu account, you can still build uh GPTs, but you can't use the new Oer models. Right? That's the biggest one. And I do suppose there is the GBT 4.5 model uh as well that you couldn't build with previously. All right, so uh let's just jump and do this live. And uh as an FYI, y'all, we did uh about two weeks ago uh go over the difference between custom GPTs, which is what we're talking about now, uh Google gems and also projects inside of Chad GPT and Enthropic. So, if you do want to listen to that one, I recommend going there to episode 549. All right, so go listen to 549 if you are interested in that. But let's just start live. So, we're kind of starting at the end. All right, so I have a series of GPTs that I built uh here on my screen. So, for our live stream audience, uh I already have these aren't like long prompts, they're like a sentence, right? uh because actually uh the uh the power of these is in the custom instructions that I've already built. So I'll actually probably uh open a new one here and jump to it later. All right, but for each of these custom GPTs, I'm going to be using the new 03 model. I could use the 03 Pro model. I think it'll actually just take too long and I swear every time I'm like I'll do this podcast in 30 minutes and then it ends up being 50 minutes and people are like this guy should stop rambling. Uh so I would have to ramble more. So we're just going to do the 03. Uh and you'll see uh in my settings at least I did say that's the preferred model. So if I end up sharing this with anyone I don't know if you want any of these just I don't know leave the comment of the or comment on the one that you want and I'll send it to you. All right. So, uh, I'll show you after I'm done how to build these. All right, but right now I want to get these different GPTs started. Uh, they're probably not all going to work. Um, I'm not going to say I one-shotted these, but these aren't exactly my finest GPT creations, but I wanted to try some things that I thought would be useful uh for everyday business leaders such as yourself. Uh, so the first one is called Insights Synthesizer. Okay. So this GPT acts as an instant research analyst and uh the user so me in this case uh provide a topic and it executes a structured multi-source web search for the most recent and relevant information for the topic that I put in. It will then digest everything performing a sent uh sentiment analysis and thematic clustering and renders a professional onepage dashboard in chatbt canvas mode. All right. So, uh, let's go ahead. Actually, you know what? Uh, I'm going to go ahead and get all of these started. All right. So, live stream audience, don't worry. I'm going to come back to these, uh, and explain what I'm doing, but I'm doing these live. They're probably going to break. There's going to be some issues. I've already I did just run them once before. They all work the first time. What you mean? Like if you've ever done a demo, if you do it once and it works and then you go do it live in front of a bunch of people uh or in my case, you know, at least thousands of people uh on the uh on the podcast, um it's it's going to break. It's not going to work. But that's fine. That's why I do these things unedited, unscripted, so you can see uh how AI actually works because generative AI, it's generative. You get something different every time. All right. So, the next one is data storyteller. And I already have my short little prompt in there as well as a spreadsheet that I'm uploading. So GPTs are multimodal. All right, I'm going to the next one, which is meeting actionizer. And I'm really excited about this one. I'm actually I'm like, why didn't I build this one before? I'm going to be using this a lot. So I have a short prompt as well as a meeting transcript. All right. Uh then I have the investor snapshot. I have a short little prompt here. I'm hitting enter. Uh, and then I have the personal uh the personalized learning architect. I'm hitting enter. All right. So, hopefully that shouldn't take too long. All right. So, now I want to jump back into uh the kind of edit mode in a GBT. Well, actually, no. Before before I even do that, uh let's just go ahead. Give me give me a second here. I'm just going to bring up the actual like GPT interface. All right. So, uh, this makes makes a little bit of sense. So, there's different ways that you can use GPTs, okay? And in short, they are a smaller customized version of the main model. And you might be wondering like, okay, why would I ever need a GPT? Uh, why wouldn't I just use the main model? Well, there's a lot of reasons. Um, one, it's saving time, right? Think sometimes, you know, if you've ever been through our prime prompt, polish PPP course, you know, you, you know, you might spend 20 or 30 minutes uh just getting one chat to work exactly how you might want it. Uh, right. And then there are some things you know without getting too technical like context window uh you know memory some new things from chat GBT that impact it behavior uh that you know it might just make more sense to use a GPT. So number one is going to save you time. Number two, there's actually some uh some additional functionality and the and the biggest one is is you can just click the at button uh when you are using a normal chat. All right. So, uh let me go back. I'm just going to open another window here. So, if I open a new chat and I'm just going to click the add button. Okay. So, when I do that, I can bring up my recent GBTs. So you can be having a conversation or you could use as an example deep research and then you could transition right away and start using GPTs. So uh especially when you think of your work and think of you probably do a lot of the same things over and over and it could be very repetitive. It might be mundane, it might not be, but most of the work that a lot of us do it is repetitive knowledge work, right? We're working with documents. We're creating content. Uh we're we're we're summarizing. We're researching. We're synthesizing and personalizing information that we've ingested. All of these things, not just chat GPT can do, but custom GPTs can do as well. So using these different GPTs and then mentioning them at different points um of your uh kind of chat with chat GPT by using the at mention is a huge timesaver, right? So, let's just say you have uh five key tasks that you do pretty much on an ongoing basis or there's a three-hour project that you do once a week. Maybe it's a little bit of researching. It's uploading an old document. Um, you know, so you're researching, you know, new laws, new updates, new industry trends. You're then you're um, you know, updating the old document. Then maybe you're building some sort of dashboard, right? Those four different steps right there, those could all just be GBTs. So you don't have to sit there and reprompt each time and try to get it just right. Right. So you can get it right just once. Save that as a GPT and then at@mention each of those GBTs and then when I'm done. So as an example on my screen here I just clicked investor snapshot you know I can put in whatever prompt hit enter. It's going to go through and whatever custom instructions and uh knowledge that I have saved in there. It's essentially a literal custom version of chatbt. It's going to spit out the result, whatever I have programmed it to give me as a result, and then I can go on uh X out of that GPT. Uh and then I can click the next one and keep going. Right? So, uh it's an easy way to work with multiple smaller uh specific uh custom versions of chat GBT using the same context window. All right, so let's go back in and uh talk a little bit about the different ways to use GBTs. Uh so one is building your own which I'm going to show you here in a second. But the other one is there's a GBT store. So uh if you literally just go to your chat GBT account even on a free account you can use uh GPTs but you have to be on a paid account to actually build them. So you can share them with your team. You can share them across accounts. Right. That's something I do all the time. I have like I don't know I lost track eight paid accounts or something like that for Chad GBT. Yeah, we we do a lot of consulting work uh for other companies. So, we have accounts for them. But I think even for everyday AI, I I think I have like three or four different accounts, you know, I have a pro account, a team account, a plus account uh etc. Right? So, um you can share your GPTs across different accounts, but you can also go to this GPT store, right? So, there's like it's like an app store. So, there's top picks, there's categories, writing, productivity, research, analysis, education, uh etc. So, um, as an example, I'm going to use a writing one because I'm hoping that they will have updated their GPTs on the back end. So, uh, I'm going to go to this one that says, uh, AI humanizer. All right, so essentially, you put in some text and it makes it sound less robotic and more like a human. All right, I'm going to click start chat. So, again, it's as simple as that. Using a GBT, there's a store. You go in there, it's done. So any old GPTs, whether they're GPTs that you made or someone else made and put them in the GPT store, uh they can be upgraded and use the latest models. It's a one-click uh thing in the settings. That's the good thing. You don't have to rebuild it. If you built it, you know, in November 2023 when GPTs first came out and you're like, "Ah, these aren't that great." And it's been sitting there, well, you can just go in there and change the model. Uh so all you have to do is click. So, in this case, I'm clicking the AI humanizer uh humanizer uh kind of drop-down menu in the upper leftand corner of chat GPT. I can hover over model. So, yeah, this one did not update their settings yet, but it's super simple to do. All right. So, then I can go in here and use a G any GPT in the GPT store. All right, but I wanted to show you all real quick. There we go. Uh kind of the basics of how these are built. All right, so I'm going to go in and edit this GPT. So, this is the insight synthesizer. All right. And I'm just gonna quick uh live stream audience, don't don't worry. Uh if if if you're seeing uh uh a bunch of things flash on my screen here, um I'm actually just going to go through each one of these if they are done. I'm just going to say make it prettier and more useful. All right. If if any of these GPTs are already done, it's something I always tell people. Never use the first version of something. And in case any of them are broken, I just got to fix them. Otherwise, this uh the latter half of this podcast probably won't make too much sense. All right, so bear with me. Uh live stream audience, you get a little preview on if things are working or not. All right, I'm just going to go in and drop for ones that are working. I'm dropping in my, you know, make it uh make it prettier, make it uh work better. Uh some of these it looks like have some bugs uh because I'm I'm using some uh some coding uh in here. Good thing is when I'm using canvas mode, uh there's a thing that just you can click that says fix bugs. So we'll see how many of these uh actually uh actually work. Like I said, doing it on the first shot, it can be hit or miss. All right, I'm just going in here. Looks like most of these I had five of them. I think four of them used canvas. Um, so or and I I think only one of them did work on the first try. So, not bad. All right. So, going back into our GBTs and how you can create them. So, there's different ways. So, it's simple. Don't think you need to be uh technical. You don't need to know a lot about prompt engineering or coding or anything else. You can literally just chat like you would with chatg and say, "I'm trying to build uh a a GPT that does blank." And it will go ahead and build it for you. So you can build it in a chat interface which is kind of meta uh or you can go if you're a little more advanced you can go into the configure uh section. So uh your screen is split in two and the left side that's where you build it and the right side uh it renders the preview anytime you make a new uh update or a new change. So essentially anything that you uh that the GPT bot builds for you automatically goes into the configure tab. For me, I've obviously built a lot of these, so I like to build them by hand in the configure tab. So, I can type what uh goes in the instructions manually because you have a little bit more control. All right. So, uh here's kind of the uh description of what's new. So, now I'm in the configure tab again inside the GPT builder. So, you can give it a name, give it a description, and then here's the important part. This is the instructions. All right, I'll quickly show my instructions on the screen. I do this a lot, guys. Don't worry. Uh, it looks Well, all right. This one is a little crazy, right? Uh, I may or may not have spent way too many hours putting these GPTs together because I wanted to show you guys some impressive things, right? So, I I I have a lot of custom instructions in here, which probably looks like gibberish maybe to some people, uh, but it's actually not that crazy. All right? uh or at least not compared to things that I've built in the past. All right, so I have some custom instructions in here. You can add conversation starters and those essentially uh appear then as little buttons that you can click and get a conversation started. For me, the way that these are built, they're all very specific. So, I don't necessarily want a conversational starter. And you'll see as I describe what I put into each of these five GPTs. Uh you can also upload knowledge files, which I didn't do. All right? And I did that um kind of intentionally because I wanted to ensure on a quick demo that this worked. However, you will see uh that I did upload files on the front end. All right. And it's kind of again built to do that. And here is the big new thing here, the recommended model. So, uh on the front end, uh users or creators, right, can choose which one, but you can also recommend a model. So whether that's using it for yourself, your team internally, right? If you have an enterprise plan, if you have a a chat GBT teams account, uh and if you do, by the way, reach out to us. That's one of the things that we do is we uh train teams on the right way to use chat GBT enterprise and chat GBT teams. Uh I don't know many people who spend more time in chat GBT uh than myself. Um you know, yeah. So just trust me, reach out to us. And then you can toggle capabilities on and off. So those different capabilities are web search canvas uh which is essentially a way to render uh python html in react uh inside uh chatgbt in the canvas mode 40 image generation and then code interpreter and data analysis and then there's a section that says create new action. So this is actions. So, like I said, if you want uh not just actions, but a couple of other things, uh if you want kind of an advanced uh version of this next Wednesday, just type advanced in. If you don't, that's fine. All right. And that's really it, right? So, just in that, you know, three, five minutes of me talking, I gave you a way that you can essentially create your own version of Chad GBT. Uh right. The crazy thing is um I think a lot of companies in you know 2021 2022 spent millions of dollars uh before all of this you know nice no code technology was out uh creating essentially this right literally countless companies spent millions of dollars to create this right essentially a version of chat GBT that was kind of fine-tuned for their purposes and that worked with their data granted you know if if if you're thinking that you're going to upload you know um 100 files in this knowledge it doesn't really work like that also keep in mind the context window uh in the retrieval uh mechanisms that GPT use that GPTs use without getting too technical they're a little haphazard in the way that they tokenize all right but that's that's more for our advanced users so it's not like you can go in here and upload you know 50 files or anything like that um I would say you start to see uh kind of a degraded quality uh usually after like 10 files depending on how large those files are although you can you know push it for a little bit more and that's it right so now you know in this insight synthesizer I can go in and use it at any time whether in a new chat by hitting the add button and starting to type it or by going into the GPTs section and clicking on it and working on it in GPT mode. All right, so let's quickly wrap up why these updates matter. Number one, better guidance. Uh, so all the different models, whether you're talking about GPT 4.5 that has a very high EQ, uh, you know, 40, which is a fast workhorse, you can go all the way up to, uh, 03 Pro in your GPTs, right? So now you can really control and even internally you might build some that use 03 pro. You might build some that use uh 04 mini high uh which is a thinking in a reasoning model that's a little faster. Right? So all of these different models from open AI excel at different things. Uh so now that you can use these multiple models, it really does change uh what companies can do internally just with chat GBT. uh also the domain expertise. All right, I think now that you can use these reasoning models that are agentic in nature that's the key thing is you can use if you look at the 03 model you can use everything that that model can do that model can research uh it can agentically decide when it uses certain tools. So it might start researching then it might start writing some Python to try to uh solve your query and then halfway through writing Python uh it might go look at your knowledge docs that you uploaded then it might go research again then it might go write a little bit more code right so it is agentic in nature uh especially 03 I think 03 was one of the more impressive models I've ever used right up there with Gemini 2.5 Pro um so that's the key thing is you know before nothing wrong with you OpenAI's workhorse GPT40 model. But the gap in terms of what these things can accomplish, what a GPT can actually do with a GPT40, a non-reasoning model in the 03, it's night and day in terms of capabilities. And the biggest thing is now there's no more model limits, right? Uh because you're not just stuck with GPT40. That's why, if I'm being honest, I haven't used GPTs a ton over the past year. uh especially not over the past six months until this update mainly because I'm constantly working uh with these reasoning models and uh we were able to use them inside of projects. Although if you like I said go listen to episode 549 there's some key benefits to GBTs that projects don't have. All right. So, [Music] are you still running in circles trying to figure out how to actually grow your business with AI? Maybe your company has been tinkering with large language models for a year or more, but can't really get traction to find ROI on Gen AI. Hey, this is Jordan Wilson, host of this very podcast. Companies like Adobe, Microsoft, and Nvidia have partnered with us because they trust our expertise in educating the masses around generative AI to get ahead. And some of the most innovative companies in the country hire us to help with their AI strategy and to train hundreds of their employees on how to use Gen AI. So whether you're looking for chat GPT training for thousands or just need help building your front-end AI strategy, you can partner with us too, just like some of the biggest companies in the world do. Go to your everydayai.com/partner to get in contact with our team or you can just click on the partner section of our website. We'll help you stop running in those AI circles and help get your team ahead and build a straight path to ROI on Genai. Let's get back. Uh we're going to wrap this puppy up. Well, after we look at what was actually produced. All right. So the first one, Insight Synthesizer. So let me first tell you uh what these different GBTs do and then we're going to look at the results on what they did and hopefully we'll see. Uh and all of these GBTs were created specifically with the 03 model in mind to show off what they're capable of. So, even if you can't envision yourself taking advantage of these exact GPTs or the simple prompts that I used, think outside of the box and think what are those repetitive knowledge work tasks that you do over and over. And when you think about it, if you're honest with yourself, and I will argue, AI is better than you at those individual tasks, right? you the human, you the expert, you're still needed, right, to on the front end, the back end, human in the loop putting these pieces together. But if I'm being honest, right, I spend so much of my time just orchestrating large language models, right? I'm not going to pretend that I can research better than Gemini. I'm not going to pretend that I can write code better than Claude, right? I'm not gonna pretend that I can synthesize information better than Chad GBT. I can't. Right? So again, think where you spend your most manual time. And then what if you had a small version of custom or you know a custom version of Chad GBT that could do that one thing very very well. So insight synthesizer this uh oh I think I did already read this but let me reread it. This GBT acts as an instant research analyst. You provide a topic and it executes a structured multissource web search for the most recent and relevant information. It then digests everything performing a sentiment analysis and thematic clustering and renders a professional onepage dashboard in Chad GPT's canvas mode. Uh so my uh prompt very simple I said generate an insight uh synthesis dashboard on the topic the impact of generative AI on the creative marketing profession in June 2025. So, very specific. And I said, "Make it pretty." Uh, and the info should be specific. And then I just did my, you know, I announced it for our podcast audience. Uh, halfway through anyone that was done, I just said, "Make it prettier and more useful, right?" I always like to do that just to see what it's going to come up with. All right. So, uh, when we look at what was created here, not pretty necessarily. Uh, but I did, FYI, I was very strict in my custom instructions, uh, in terms of instructing it what to code and what not to. Uh, so I knew that I wouldn't get the most beautiful thing, but I sacrifice this working on a live demo to make it not look that great. We could obviously make it look better, but that's not the point here. All right. So, uh, what we got here, uh, we got a nice little quadrant. Uh, it actually, I mean, it looks fine. It's, you know, plain HTML. Nothing exciting, nothing that looks great. Uh, but we have an executive summary. Uh, and I do want to see. So, it says, "Generative AI solidified its role in creative marketing in June 2025. Brands like Adobe rolled out tools that optimize visibility across AI interfaces. Broadcasters like Channel 4 uh began serving fully generated AI ads and CMOs at CAN's lines reported workflow efficiencies and deeper personalization. This is all this is good. This is uh interesting. Uh so then we have a sentiment analysis. It says 80% of the news was positive, 20% was negative. We have some key themes here and then we have some sources uh that we can click on. So overall looks like it did pretty good and I can go check to see exactly what it did uh by clicking the thought section on the left hand side uh of this GPT. So you'll see here it broke the task down into multiple parts. Uh it first started by searching the web. It reflected on what it found. It realized it needed to go search a little bit more. Uh it did it again. Uh search a little bit more. It was look at this. It was doing some advanced boolean search which is pretty cool. It was searching for file type PDFs uh with the word generative AI in creative marketing which is pretty cool. It was specifically searching for PDFs probably to find like more in-depth like white papers or something like that. So very cool. Uh it's going down there then it starts analyzing code then it reflects on everything analyzes creates more code. So you'll see here this agentic step that the 03 model goes through. You couldn't do a third of this uh with the old GPTs when they were using GPT40. So, you'll see here it actually does a very good job uh going through. And then we get a uh a dashboard, although the dashboard's not super pretty, but that's fine. All right, let's look at the next one. Uh let's see if it actually worked. We'll see. Got a little error message, but all right, looks like it worked. Cool. So, and again, if you want to use any of these, um, just drop the name of it in the comments. I'll send it to you. All right. So, this one is, uh, the data storyteller. All right. So, this is a GBT that transforms raw spreadsheet data into a clear, compelling narrative. So you upload your data and it automatically cleans it, identifies the most important trends and generates a 10 slide data story in canvas mode complete with well we'll see if it worked complete with charts and bullet point in uh bullet point insights. So all I did for this one and you'll see uh if live stream audience you can see the amount of data that I uploaded here uh pretty pretty decent amount of data. It looks like uh 500 I uploaded podcast episodes. So, uh, 500 and it looks like 10. So, at least, uh, you know, 5,000 rows of data here. And I just said, here's our podcast data. What are the most important trends here? Be specific and unearth the most valuable insights, not topical and obvious findings, right? Uh, the rest of the instructions on how it could complete this were obviously in the custom uh, in the custom instructions inside GPT. But you'll see here I got like the world's most basic uh like slideshow, but it's not bad. All right. Uh so on the right hand side here, uh I got a little slideshow that I can flip through. It looks like a very basic like PowerPoint deck, but again, I did this with I didn't do anything. Uh right. So again going through here and again I'm calling this out because I want you to see and understand and for a podcast audience. The big difference here in the GPTs that you didn't have in GPT4. Number one obviously the quality uh in in what the 03 model can do. But why I built these the way I did uh which was a little intense um was to specifically show you its agentic abilities. Right. the 03 model in from OpenAI and Gemini 2.5 uh from uh Google they are agentic in how they work because they make decisions on their own. So in this case, it started by writing code, right? So it started writing code immediately. I don't think I had it uh research anything. We'll see if it ended up researching anything. It looks like it just wrote a lot of code with Python. It thought about it, analyzed it, etc., etc. Uh did created a chart down there. Cool. We'll see if that shows up. Uh so pretty good. So we have a 10 slide. So it says podcast audience explosion. Uh downloads are up 152%. It's actually a nice little like uh animation, right? Not bad. So, I did see our chart was in the chain of thought, right? So, when I went and clicked on and and when I'm reading all of these things, y'all, it's on the left hand side, it should say like thought for and then a number of minutes and seconds. That's the chain of thought that I'm reading. And I'm kind of saying like, "Oh, it's a nature because A, B, and C." That's because that's what I'm reading. It's the chain of thought here. Uh so I did see that it created an an image but it unfortunately did not insert that image into the slide uh kind of this slideshow. Uh it looks like it tried to but it failed. Uh but let's see. It gave me some median downloads in that chart that didn't work. Uh some key takeaways. Okay. Pretty Yeah, pretty pretty decent stuff here. Uh okay. This is interesting. I didn't know this, but it said the single biggest leap occurred between quarter 4, 2024, and quarter 1, 2025. Uh, an 86% growth quarter to quarter, which I didn't necessarily know. Uh, but that's cool. So, some key takeaways here. Uh, some trend deep dives. Again, just going over my podcast data. Uh, segment breakdown. It said Friday releases outperform Monday drops by 20%. Huh? Didn't know that. Uh, also it said episodes featuring the term AI agents pull a median of 6,300 downloads, 67% above the series average. Uh, drivers of change. So, it's telling me some things that are helpful. Benchmark comparison, future outlook. Cool. Um, and then some strategic recommendations. All right. All right. I like this. Um, and then an appendix and methodology. Cool. All right, let's look at our other GBTs. Uh, see if they worked or if they failed. This is the one I was excited about. Uh, all right. It looks like this one worked. Sweet. Uh, so this is the meeting actionizer. And this is something I'm like, why haven't I just built this before? Right. There's so many AI tools and I have them all, right? and it gives you a summary. This person said this, here's the to-dos, sentiment analysis, blah blah blah, right? Uh, sure, cool. Uh, but none of them use reasoning models, right? So, all it does, you know, yes, the transformer models, GPT4, uh, you know, they do a good job, but when you can apply a reasoning model to a meeting transcript, it picks up it picks up on so much more nuance. Not only that, what I did here and again all all this uh prompt was I said generate the meeting hub. That's what I called it. Make it useful and pretty. It wasn't really pretty. Uh again, I was very restrictive in the code that it could write inside canvas mode so it would hopefully render and I wouldn't get a bunch of bugs because uh you know the more sleek and modern and bells and whistles you throw inside while trying to render this code, the more likely it is to uh fail. Uh, but what looks looks like what did happen. Let's see. All right. So, again, I'm looking at the chain of thought and it's just kind of reading through. Yeah, here we go. Here we go. This is what I wanted. Right. So, I had this uh and the instructions on this one were a little intense, but I essentially said, yo, like, yeah, go do the normal meeting analyzer stuff, you know, fine. Give me an executive summary, which we have here on the screen. Give me decisions and action items that were discussed. Okay, there we go. This was a an internal meeting of ours uh of our team from a year ago uh talking about some different ad strategies. We were just testing a couple of things out. Uh so nothing crazy, right? Uh but what's cool here is the things that we talked about in this meeting that we're like, "Oh yeah, we should look into A, B, and C. let's go, you know, hey, next week when we meet, let's research this and and talk about it and come to some conclusions and and come up with some it went and did this, right? So, this GPT because it's using 03. So, it it went and did the normal, you know, AI meeting transcript stuff, right? Gave me uh, you know, an executive summary, decisions and action items, key decisions, uh, dates, charts, all that stuff. It gave me a discussion mind map. But here's the gold, y'all. Um, I should probably just build this. Should I just quit everyday AI and just build this thing? It'd probably make a trillion dollars because this is what people want. It actually went out and did all of the work that we talked about. It went out and researched it. So, you'll see here, you know, it's in the middle of this. It's going out and it's searching the web. All right? It's talking about things that our team was talking about. uh it went out uh it made kind of like hey here's the to-dos and then it went out and it just went and did the to-dos and it's recommending things. So uh that was called the research brief and it already uh provided potential solutions that are actionable. They're up todate because I did that in the custom instructions I made sure and it's really good. Like I'm looking back, this meeting was like a year ago and I'm looking back at some of the recommendations and I'm like, you know, that's that's what we came to. So very cool. Uh man, anyone else feeling this one? This one's called uh meeting the meeting actionizer. Oh, I love that one. I'm going to go I'm going to make this one a lot better. Uh, and I'm probably gonna duplicate it inside uh Google Gems uh and duplicate it inside of uh Claude uh in inside of Claude project and uh using artifacts as well. I can't wait to see and I'm going to spend some time on this one. I think it's going to be really good because everyone hates meetings and then it's like all right you like everyone has to do the same thing and like I have all the AI meeting tools and they provide me summaries and all this but then I still have to go out and do all these things. I I would love for this uh GBT to just start the process for me and then I just make the decision and you know I can keep chatting with it from here. That's the other great thing. All right, we're going to go over the last ones really quick. Uh because once again, we're already at the 39 minute mark. Uh I should stop geeking out about this. Do I need to make these podcast shorter or do you guys not hate geeking out? If you do, that's fine. All right, so this one is the investor snapshot. Here's what this one does. It generates a one-page financial and news snapshot for any public company. It browses for the latest financial data and news, then renders a concise briefing report in canvas mode. All right, so all I did for this one, I said, "Give me an investor snapshot for Nvidia. Make it pretty and ultra detailed and recent." Uh, it didn't make it pretty. I did save the one I did earlier because I thought it looked like way better. Uh, you know, this one at least made it a little prettier, right? We got the Nvidia green and and all that, right? So, uh but overall this is really good, right? This is something I can imagine you either have to have you either spend a lot of time to put these type of charts uh and data together or you just pay for a service that does this. So, uh, is this going to be as robust as, you know, like I don't know what people use, the Bloomberg terminal or No, absolutely not, right? But you can with this GPT any company that you care about and you can tweak this and personalize it and make it your own. You know, I got the current price, the 52- week range, market cap, PE ratio, uh, revenue growth year-over-year, dividend yield, shares outstanding, all for Nvidia very quickly. And then I got the latest news like up to like yesterday. This is news, you know, this isn't from, you know, months ago. But it's also giving me things over the last week or so. Uh, right. So, it said Nvidia could be days away from a $4 trillion, uh, you know, valuation. Oh, weird. I told you guys that like two and a half years ago. Um, so another great GBT that shows uh the utility and the power of the 03 model. All right. And then last but not least, uh, this one is the personalized learning architect. So, this one creates a custom week-by-eek learning plan on any topic. It researches the best resources online and presents a structured syllabus as a clean, professional web page in Canvas mode. All right. And all I did here, uh, this prompt was a little bit longer, but nothing crazy. I said, create a four-week learning plan for a beginner to learn Python for data analysis. Uh, and here I really wanted to test the personalization. I said, 'I don't know much about Python, but I'm a big AI enthusiast, so I understand its importance. I'm also a basketball fan. If you need to make any analogies, make it pretty. All right, so here we go. It has a learning plan, uh, Python for data analysis, uh, four-week plan. It has four different modules, uh, and then it has, uh, you know, it kind of explains them a little bit, explains the key concepts, uh, with a basketball twist. So, pretty cool. Then there's some resources over there on the right side. Uh I can click on them and it brings them up and they all work. There we go. Very cool. All right. So that y'all is a wrap. Anyone else really freaking impressed? I am. Right. So yes, we did cover these GBTs a little bit in episode 549, but I think they're actually this impactful that they deserve their own episode. Uh, so again, if you do want that advanced show, just type advance. But I just really want to quickly recap everything. So what's new is you only uh before could use the GPT40 model inside custom GBTs, right? So if you wanted to make your own custom version of Chad GBT, upload your data, your own uh custom instructions, and then use it in a lot of uh different places inside the uh Cad GBT ecosystem. Before you could only use the GPT40 model, which was fine, but you know, when we had access to these other models, it felt like GPTs uh were just kind of neglected for almost a year or longer. That has completely changed. Here's why it matters for your business because now as you saw as an example in that uh meeting actionizer now you can combine your c your company's data um the ability for a thinking and reasoning model to go make decisions uh and to perform actions and to personalize it all for you and also to automate it. Right? You can now as a business owner, as a business leader, you can now start to automate huge chunks of your company with GPTs and keeping it all in the same context window, which is something we can go over uh in the advanced mode. And the live working examples, I showed you all that. And hey, not too bad. 43 minutes, we've done worse. All right, I hope this was helpful. If you're liking these AI at work Wednesdays, let me know. Uh or give me an idea what should we do next. I'll probably put that in the newsletters today to ask you all uh what we should do next, maybe after part two if we're going to do a part two of these. Uh so, I hope this was helpful. If so, if you're listening on the podcast, please subscribe and follow the show. Tell a friend about it. If you're listening uh on the live stream, please click that repost button. You know what? If you click the repost button, I'll just send you all these GBTs. I'll just put them in a doc for you. Uh and you can go play with them yourselves, right? I spend so much time doing this, y'all. It means a ton to me anytime you go repost a show. Tell your friends about it. Email uh your brothers uh mothers, which is your mothers, your brothers, mothers, best friends, babysitters, teacher, uh and say, "Hey, this is helpful." I'd appreciate that. I'd also appreciate you going to your everyday.com, signing up for the free daily newsletter. See you tomorrow and every day for more Everyday AI. Thanks y'all. And that's a wrap for today's edition of Everyday AI. Thanks for joining us. If you enjoyed this episode, please subscribe and leave us a rating. It helps keep us going. For a little more AI magic, visit your everyday.com and sign up to our daily newsletter so you don't get left behind. Go break some barriers and we'll see you next