Ep 253: Custom GPTs in ChatGPT – A Beginner’s Guide

Custom Builder Generalized Pre-trained Transformer in ChatGPT: A Beginner's Guide

Exploiting the potential of Artificial Intelligence has become a staple for the successful business owners and decision makers of today. At the fore-front of AI integration, exploring the possibilities with the custom builder Generative Pretrained Transformer (GPT) in ChatGPT could be a game-changer. This beginner's guide aims to provide a comprehensive walkthrough on how to optimize your processes and cut down on repetitive tasks with the utilization of custom GPTs.

What is Custom GPT in ChatGPT?

The term GPT is derived from Generative Pretrained Transformer, a technology used to make predictions. A Custom GPT in ChatGPT is essentially a personalized AI variant that can be trained and optimized for a plethora of applications, including automating tasks, researching, and content creation. Unlike plugins, which are pre-defined codes inserted to perform certain functions, custom GPTs can be fine-tuned and customized according to the user's specific needs.

How To Utilize Custom GPTs without Prior Coding Experience

Many perceive AI integration as a complex process or one that requires coding skills, however, this is a myth. Custom GPTs in ChatGPT offer great flexibility in their creation and use. Users with no prior coding experience can easily upload their own data, knowledge base, and documents, and create detailed configuration for unique requirements. Further, intuitive instruction commands make it convenient for the user to operate the GPTs.

Potential Applications of Custom GPTs in Business

Custom GPTs can be seamlessly integrated into the business workflow to handle repetitive tasks and generate information from uploaded data. This offers a highly effective and time-saving tool for business owners and decision-makers. The ability to streamline processes and automate recurrent tasks empowers businesses, freeing up precious time for other core operations and strategic decision-making.

The Do's and Don'ts with the GPT Store

Hosting your custom GPT in the GPT Store poses certain considerations. While it's an easy and efficient way to publish GPTs, it doesn't come without risks. These GPTs become searchable and public, making them susceptible to being copied or cloned. Selling custom GPTs is an option, but the monetization model is largely based on usage. Though it has been reported that this has not yielded significant revenue unless a GPT goes viral. Hence, a prudent strategy is needed when publishing or selling a GPT in the store.

Conclusion

The possibilities of optimizing business processes with custom GPTs are vast. With the advent of AI, repetitive tasks need not be a bane for knowledge workers anymore. The power now lies in understanding how to harness this technology effectively within businesses, which as proven by the GPTs, does not require commanding expertise in coding. The paradigm of business operations is changing, let's lead the way by integrating these smart machines to augment our potential.

Topics Covered in This Episode

1. Custom GPTs: An Overview
2. Utilization of GPTs in Everyday Tasks
3. Creating Custom GPTs
4. Monetization of GPTs in GPT Store
5. GPTs in Action: Automating Work Operations


Podcast Transcript

Jordan Wilson [00:00:16]:
What the heck is a GPT? Yeah. We've heard of chat GPT, but did you know that you can create your own and that it only takes sometimes a minute or 2 to create a custom version of chat GPT that can honestly completely change the way that you work. So we're gonna be showing you how and going over some of the basic questions in today's episode, a beginner's guide to custom GPTs inside of ChatGPT. What's going on y'all? My name's Jordan Wilson, and I'm the host of Everyday AI. And Everyday AI, it's it's your guide. It's your guide to learn what's going on in the world of artificial intelligence and how you can leverage all of that knowledge, all of these updates to grow your company and to grow your career. So if that sounds like you, welcome. You are in the correct place.

Jordan Wilson [00:01:11]:
And we do this livestream and podcast every single morning, but also know that there is a free daily newsletter. So if you haven't signed up for it, you have to go to your everydayai.com because there's a lot of great information there, so more on that here in a minute. But before we get into custom GPTs and what they are and why I think you should be using them a lot, let's first do as we do every day and start with what's going on in the world of AI news. So Slack has released its AI tools to all paid users. So Slack has just released its AI tool suite for all paying users including AI generated channel recaps, thread summaries, and conversational search. The tools also offer language support and integration with third party apps. So Slack's AI generated recaps and summaries can help users catch up on missed discussions and stay informed on important topics. The conversational search feature allows for natural language queries to find specific information in the analyst channels of Slack.

Jordan Wilson [00:02:15]:
So, some may argue that the AI tools are just a marketing gimmick for Slack to promote their use of AI. I'm not sure. I stopped, thankfully, using Slack a while ago. I I guess Slack won't be a sponsor of the Everyday AI Show anytime soon. I'm not a big fan, but hey, if you do use Slack and if you are drowning in all of these messages, this new AI feature might help you. Second piece of news which came out just about an hour after our podcast yesterday, but we snuck it in the newsletter. Boston Dynamics has released its newest AI powered robot. So Boston Dynamics has unveiled a new version of its humanoid robot, Atlas, designed for real world applications and powered by electricity.

Jordan Wilson [00:02:56]:
Despite its impressive capabilities, the release has sparked skepticism in comparisons, in comparisons to the Terminator franchise. Right? Anytime there's, some unbelievable advancement in AGI, we immediately skip to Terminator. Right? So, Boston Dynamics has released a new version of its humanoid robot, Atlas. So the the old Atlas has been around for many years, but the new version boasts improved strength and range of motion compared to its previous hydraulic powered model, which was officially retired. So while Boston Dynamics robots have been used in industries such as manufacturing and law enforcement, the release of the Electric Atlas has sparked comparisons to the fictional killer robots from the Terminator franchise. And if you read our newsletter yesterday, we included a video of that and you probably know why that those comparisons are being made. Last but definitely not least, Microsoft has just released an image to video model that could and probably will unfortunately be used for deepfakes. So Microsoft has released a new AI model called Vasa 1 that can generate hyperrealistic videos of talking human faces from just one photo in an audio clip.

Jordan Wilson [00:04:09]:
Wild. The company has no plans to release it to publicly, thank goodness, and aims to use it for creating virtual characters. So Basa 1 can generate high quality videos with synchronized lip movements and facial expressions from a single image. The AI model also offers granular control over different aspects of the generated video. Microsoft wants to use this technology for positive purposes such as accessibility and therapeutic support. However, there are obviously huge concerns about the unethical use of this technology when and if it is ever released to the public, particularly for creating deep fakes. And, hey, especially here in the US, we have this whole, election thing coming up. Right? So make sure we're gonna have more about that in the daily newsletter as well.

Jordan Wilson [00:04:54]:
So let's get into a beginner's guide to custom GPTs in chat g p t. So, whether you haven't created a a GPT yet, you're brand new to chatGPT, or if you've created 5 or 10 of them, I I still think that you're gonna get a lot of value, out of today's show. So I'm just putting that out there. This is a beginner's guide. Right? So also, I wanna hear from you all. I wanna hear questions and, you know, I I I referenced the the the newsletter earlier. Right? And why you should be reading it? Well, number 1, there's, exclusive insights that literally are only found in our newsletter. There's dozens of AI newsletters.

Jordan Wilson [00:05:33]:
They all cover the same thing. We bring you exclusive content every day, including I let you all pick the show. And by one vote, this show won out over perplexity. So, was that was that fun for those of you that voted, that that you get to control, you know, my morning and, our team's day? Hopefully hopefully, that's fun for you that you guys are in the driver's seat. But I'm also curious, you know, to our livestream audience or, you know, if you're listening on the podcast, hit me up. How many GPTs have you built? And and what's been your experience so far, and and what are your biggest questions? So, to to our livestream audience, that's that's joining us, like, Anili, and Jay and and Tara, Brian and Harvey joining us from from the YouTubes. Thank you. Thank you all for joining us live as always.

Jordan Wilson [00:06:20]:
But let me know what are your biggest questions and also how many GPDs have you built? I'm always curious. I feel people have either built like 1 or 2 or like 50. And I think a lot of that lies in, how useful people are or are not finding these GPTs. So I hope that what this, that's what this episode, can help you with. So let's just, dive straight in, and and talk a little bit about some of the most common questions, about GPTs. Alright? And at the end, as as long as I don't accidentally go on some some side rants, at the end, we will, jump in live. But let's just go over the basics y'all. This this is for beginners.

Jordan Wilson [00:07:04]:
So some questions some questions I will post to myself, but get your questions in as well. So some questions I will post to myself and answer. Why would I use a GPT in chat GPT? Well, to put it very shortly, a GPT is a customized version of Chat GPT. So if you've ever found yourself using Chat GPT and you're like, hey, this is okay. However, you know, it's it's struggling. It's it's, you know, I I can't use my information about my company or my brand voice easily or, you you know, there's there's a certain part of Chegg GPT that I don't like. It's acting in a way that doesn't work for me. That's what g p t's are.

Jordan Wilson [00:07:44]:
Think of them as a very easy way to go under the hood of chat g p t and change things in a very easy way. Alright? So that's why you would want to use a custom GPT inside of chat gpt is is to make it your own, is to maybe add or remove features from chat GPT to to add in your own knowledge. So what are custom GPTs for? Well, custom GPTs are really for anything. Right? Any anything that you can do inside of ChatGPT, you can create a custom gpt around that. Right? And I think that also goes to a common misconception that people have about chat gpt. I think a lot of people think, oh, it's, you know, it's it's for writing blog posts or it's it's to help me brainstorm ideas. Yes. It is.

Jordan Wilson [00:08:32]:
Right? But that's like saying, okay. This, Ferrari is an umbrella. It keeps me dry when it's raining. Yeah. Sure. But that's that's like not even scratching the surface. Right? So what, like, what are custom GPTs for? Think of this. So I talk a lot about knowledge work.

Jordan Wilson [00:08:52]:
And so many of us, myself included, but so many of us and so probably so many of you out there listening are knowledge workers. So what that means is a company pays you for a specific skill, or a a type of knowledge or expertise, and you generally sit in front of a computer and perform, that that knowledge or that expertise somewhat repetitively throughout a course of multiple knowledge based tasks, right? So that's what a knowledge worker is. And that is where GPTs can really, help. And then we're gonna go through some examples of that, but, that's what GPDs can really help for. Think of all those, manual tasks that you do repetitively that that require your knowledge. And then think, what if you inputted that knowledge into a customized version of ChatGPT that you can use at any time and you can kind of train it and go back and forth and, you know, kind of unload the knowledge that's in your brain that that your your company is paying you for or maybe, you know, you're you're working on a on a side project or you're an entrepreneur. Right? Take that that domain expertise that you have as a knowledge worker, give it to chat GPT. Right? Which I know that sounds weird.

Jordan Wilson [00:10:01]:
Give away all your expertise. Right? But that's where the world's headed. And you can create multiple specialized versions, of your own knowledge. Right? Or of your company's public data. Right? We're gonna get into that, but don't upload confidential proprietary sensitive information, PII, PHI. Don't upload that into chat gpt, but all your public data, all your your knowledge, your expertise, your own internal decision making, you can very easily create a custom GPT that can then perform those manual tasks that we all do day to day for you anywhere inside ChatGPT. We're going over the basics. We're going over the basics y'all.

Jordan Wilson [00:10:40]:
Cecilia said, I need this course to help build my confidence to build my first GPT. Well, hey. Get your questions in, y'all. Get your questions in. I'm going through the basics here, and and then we're gonna build one live. Alright? So let's let's go over some more of the basic, questions about GPTs. So can I create my own chat GPT? Well, kind of. Right? So you are creating a, a version of chat GPT.

Jordan Wilson [00:11:04]:
Right? So, you are essentially starting with the base model when you are creating a GPT, and you are giving it kind of custom instructions. Right? So, a a lot of people were, were confused when I said don't use custom instructions. Right? So if you're new to ChatGPT, that was a feature that ChatGPT released, oh, I don't know, about 7 or 8 months ago called custom instructions, and you could essentially give ChatGPT custom instructions. However, I told people don't use that. It's going to be bad. Right? Because if you're using ChatGPT for a variety of of purposes, which I would encourage you to do. Right? So for writing, researching, analysis, to help you plan your day to connect to third party services. Right? So we've always had these things called custom instructions.

Jordan Wilson [00:11:49]:
However, those applied unilaterally to every single chat. Right? Which was bad. Right? It was a marketing gimmick if if nothing else. Right? So that's where creating your own kind of, quote, unquote, version of chat GPT through GPTs really comes in handy because essentially you get this, this concept that we had many months ago of custom instructions that I think was, you know, marketing gimmick and not very useful for very many people, but now it's it's fully fledged. Right? So now you have more, kind of fine tune control over you know, you can build an army. Right? If if you have 10 specific skill sets that you do on a daily basis, you can build all of those skill sets into little GPTs and then you can call them or mention them at any point, which we're gonna show you live. So, yes, you can create kind of your own version of chat g p t, but it's it's essentially you're either, you know, adding some features, adding some knowledge, or maybe taking some features away, from chat gpt, which which we'll get into. Are custom GPTs free? Well, the answer to that is yes and no.

Jordan Wilson [00:12:57]:
You do need a paid version of Chat GPT Plus, which starts at $20 a month. You could also opt for, chat GPT teams, which I would encourage everyone to do. It is $30 a month and requires a minimum of 2 users and a maximum of a 149 users. However, when you do that, it is you have a little more control over sharing your GPTs which we'll get to it, in a second. But however, and you do get double the usage. Right? Double the message cap, which is something that we, you know, talk about. We go over in our free prime prompt polish PPP course. So, they are not technically free because you do need a paid chat GPT account.

Jordan Wilson [00:13:40]:
However, once you have that chat g that paid chat GPT plus account, they are at that point technically free to make. Right? So it's not like you have to pay for each one, that you create or you do not have to pay for each time you use it. Once you have a paid account, you can I I I don't even know if there's a limit? You know, you could create hundreds of of GPTs and and use them for all different purposes. So, yes, they are technically free once you have a paid chat gpt account. Can they only be used in chat gpt? Yes. Technically, there are kind of ways around it if if we wanna get a little more technical, by instead working in, with the assistance API, within OpenAI's, playground. But by default, if we're talking beginners, if we're talking about the kind of quote unquote simple GPTs that you can create inside of chat GPT, they can only be used inside of chat GPT. They cannot be used elsewhere.

Jordan Wilson [00:14:37]:
They cannot be embedded on your website. And, yes, you can share them, but anyone, that is using them has to also have a chat g p t account and a paid version at that. Right? You can't just, you know, have a paid account, create a gpt, and then just share it with people who have a free account. So to use a gpt, whether you create it or not, you do need a paid chat GPT account. Alright. And and hey. As a reminder, we're doing this live. We're doing this live for for you all.

Jordan Wilson [00:15:07]:
So, I I I do see a couple couple questions in here, but make sure if you do have questions even as I go along, if you have clarifying questions or if you are listening on the podcast, you know, we always check out the show notes. Always put my, my my email, my LinkedIn. So feel free. Ask any more questions. I'm gonna do my best to answer them. Alright? So next common question. How do you use your custom GPTs? It's a great question. So there is a default GPT mode, which I'm gonna show you here in a minute when we kind of dive into this live.

Jordan Wilson [00:15:40]:
But at any point, you can mention a g p a recent GPT or a GPT that you can use. Right? It's also important to, to denote. There right now are 1,000,000. I think the last count I heard is something like 4,000,000. There are millions of publicly available GPTs that you can use that are already kind of built. Right? That other people have gone through this process and they've built their own and they make them publicly available. So the way that you use your own custom GPTs, and I'll show you this, your most recent ones are gonna be on the sidebar on the left hand side of your chat GPT Plus account or at any point in any, chat that's using GPC 4, you can at mention and use a GPT that way. So you can use the dedicated GPT, kind of interface, which I would not recommend.

Jordan Wilson [00:16:29]:
And if you've taken our PPP course, our updated version 2 PPP course that we, just updated this month, you know why. But you can use it in the dedicated GP GPT mode, which I would not recommend, or you can use it in the default mode or anywhere just by at mentioning, that GPT. So you're gonna give it a name and then you can call on it at any point. Alright. Next common question for our beginner's guide to custom GPTs in chat GPT. Do I need to know how to code to create a GPT? Absolutely not. We're gonna go over this. If you can talk to chat g p t, you can build a g p t.

Jordan Wilson [00:17:07]:
It's actually kinda meta. Right? Because you can actually use the gpt builder to build a version of chat gpt inside of chat gpt that then you'll later use inside of chat gpt and you can improve it with chat gpt. Right? It's it's this weird loop of of, you you know, GPTs. But short answer is you do not need to learn how to code, to to to learn to to use a chat gpt, to to build a custom gpt. Can you add extra features and and functionalities if you are a coder or developer? Absolutely. But you can create a basic yet extremely useful GPT in minutes without even learning to code. You can do it conversationally, which we will show you here in a second. Alright.

Jordan Wilson [00:17:52]:
Next common question. How are custom GPTs different than chat g p t? Which is a great question. Some people are confused. Technically, you can make it not different at all. Right? You can go in and essentially give it no instructions and just say, alright. Here's my version of chat gpt. Right? You can make it only slightly different. You can make it extremely different.

Jordan Wilson [00:18:11]:
Right? The options are endless, in terms of how they can how custom GPTs can or can't be different than chat gpt because, we're gonna go into the back end and just go over some of the simple options. But, yes, you can make it extremely different. You can limit chat GPT's capabilities. You can limit, kind of the the the feature the the features and functionalities that it has depending on the the results that you want to drive from it. Right? So and also in the configuration instructions or by tapping into 3rd parties. You can make it extremely different. Right? In theory, you know, maybe the leveraging the GPT technology is only 10% of the power of the GPT that you're gonna create and 90% of the power maybe is in the configuration constructions and third party services that you can connect via actions, which we're going get into in a minute. Or maybe it's 95%.

Jordan Wilson [00:19:04]:
Just a chat GPT, the default clone, and you just have a couple things tweaked to give you better output. So we're, you know, maybe all you you have is you're just uploading, you know, a couple documents, to to, you know, kind of do what I like to call, which is not technically accurate, but I like to think of it this way, you know, doing some like mini rag. Right? So some mini retrieval augmented, generation. Right? So just like an easier way to bring in kind of this domain specific or industry specific knowledge, that you want chat gpt to to refer to. Right? Because there are downsides. Right? There's downsides to using extremely large language models that are trillions of parameters because sometimes they know too much. Right? So, that's another great benefit in a way that's custom, GPTs are a little bit different than the default version of Chat GPTs because you can upload, your own documents, your own knowledge base, and you can, kind of tell or encourage ChatTVT. Sometimes it'll work, sometimes it won't, to first refer to your documents versus first referring to its knowledge base.

Jordan Wilson [00:20:06]:
Right? Which is essentially what RAG is. Right? That's the, you know, kind of all the rage over the last year with large language models has been around fine tuning, has been around, RAG, you know, bringing in your your company data. But this is a very overly simplistic way of, hey. You can bring in your company data pretty quickly with with custom GPTs. And that's the way that it's definitely different. So, how are custom GPTs different than plugins? Well, plugins are gone RIP. All plugins have been depreciated as of April 10th, so as of about a week ago. Super sad.

Jordan Wilson [00:20:43]:
And I'm I'm I'm super bummed about it. I'm gonna go on a short can I go yeah? I can go on a super short rant here. I'm looking at the time. Livestream, you're still with me. Right? I can go on a a short little rant here. I truly believe OpenAI made a big mistake when they got rid of plugins. There's reasons I don't understand, obviously. You know, they wanted to kind of move everyone into, GPTs versus plug ins.

Jordan Wilson [00:21:11]:
They cited a variety of reasons. One one reason that GPTs are extremely different is you can only use 1 at a time. Right? So technically, over the course of one conversation while keeping the results of everything in chat GPTs context window, you can work with an unlimited, amount of GPT's. Right? So that was kind of the counterargument when OpenAI faced a little bit of backlash by getting rid of plugins. The difference is, right, you have to have more manual human input when you switch between GPTs. Right? So I'm gonna give you examples, but you could, as an example, ask for something from GPTA. Right? It spits it out. Then you then have to take that information and then you can manually then, hey, based on this information from GPTA, use GPTB and do this task.

Jordan Wilson [00:22:01]:
Right? So yes, you can work with multiple g p t's in the same chat, but you used to be able to do it autonomously. Right? Which is something that I only think maybe our listeners and a couple people on the Internet were actually using it for. So I think with chat GPT plugins, we had a very small, very, you know, I'll I'll say archaic or a very, duct tape version of agents. Right? You could choose any 3 plugins. In one prompt, You could have all those plugins work together and with each other autonomously. I just I we did it live here on the show, like a year ago. Right? And I don't think people understood the power of plug ins because those 3 plug ins could work back and forth autonomously. Right? And they could, you know, hey, plug in a could go retrieve, send it to plug in b, send it that information, plug in b could complete a task, could send it back to plug in a, plug in a could go look something up, send it to plug in c, right, and do that all autonomously with one prompt without any additional human intervention.

Jordan Wilson [00:23:00]:
Now, however, with, GPTs, you can only mention one of them at a time. So I personally miss plug ins. Right? But that's one way that they're different. Yes. There's technically it is technically easier. You know, the average person couldn't create a plugin. Right? You might have had to pay a developer. You might have already had to kind of know your way, around development to create a plugin.

Jordan Wilson [00:23:22]:
So it does make it easier, to create a GPT. However, it does greatly, I think reduce or limit the output of what you could get with chat g p t by using g p t's instead of plugins. Next common question. And and hey. Thanks, you you know, Hector. I see a couple questions. TC joining us from YouTube. I'll get to your questions here in a minute.

Jordan Wilson [00:23:45]:
So if you do have questions, I'm gonna get through mine and take all yours at the end, so make sure to get them in. Can I publish my GPT in the GPT store? Yes. Of course, you can. However, know that if you are doing it, if you are like I talked about, there's I think more than 4,000,000 GPTs in the GPT store. You can search them, you know, any anything that's in the GPT store is open for use and it's free for anyone to use. However, if you don't know what you're doing, it's actually pretty easy for someone to copy or clone your GPT if you do publicize it in the GPT store. Like I said, if you don't know what you're doing and there are obviously some security things to keep in mind. That's another episode for another day.

Jordan Wilson [00:24:24]:
But anyone can publish their GPT in the GPT store, but I caution you, you should really know what you're doing if you make your GPT public. But yes, it is fairly simple. Also, can you sell custom GPTs? Oh, yeah. So you can't sell them in the GPT store. That's the thing. Because once you publish them, they are public and they are searchable. Right? They're indexed. So anyone can then use them for free.

Jordan Wilson [00:24:51]:
You can monetize off the, GPT store right now that is for the US only. It is based on usage and, according to early reports, it's not a lot of money. It seems like the most popular GBTs in the world among, 1,000,000 have gotten a couple $1,000 so far. So, you know, if you think of this as kind of like the App Store. Right? And there's literally, you know, companies that went from 0 to 10,000,000,000 plus dollars in revenue just by creating apps in the iOS app store. And they did that over the course of a year or 2. Right? It's not currently a a feasible, at least right now with the monetization structure, within the Chat gbt, Chat gbt's gbt store. I sure do hope, that OpenAI increases, the monetization amount, and and looks at it more like a display ad.

Jordan Wilson [00:25:45]:
Right? And you get paid, you know, I don't know, a fraction of a penny every time someone queries, you you know, your GPT or something like that. I don't know what a fair model is, but I would say if if the most popular, GPTs for a company like OpenAI, that is, I think, valued at 90 +1000000000, they're doing a 100 +1000000 dollars in, in ARR and your recurring revenue. I would hope that the most popular apps or or sorry, the most popular GPTs get more than a couple $1,000. Right? These are GPTs that are being used by, presumably 100 of thousands of people. So can you make can you sell custom GPTs? Well, you can if you're lucky and if you, if your GPT gets super viral and tens of 1,000 or 100 of 1000 of people use it, you might get a couple bucks, but not a lot. You can sell them externally. Right? So there's options and I'll show you that. And eventually, yes, we are gonna have a dedicated course.

Jordan Wilson [00:26:37]:
So those those of you yes. Y'all, I I talked about this months ago. I didn't forget. I promise, you know, all of a sudden we had, you know, big companies, NVIDIA saying, hey, Jordan. Bring every day a out to California. And, you know, couple of Fortune 500 companies saying, hey, Jordan. Can you come teach us this and that? Right? So I promise you we're gonna have a dedicated, in-depth, multiple step, you know, GPT course inside our, community. So I didn't forget about that.

Jordan Wilson [00:27:03]:
Don't worry. But you can also sell custom GPTs, throughout, in in a different way. Right? So, it's not really a beginners, but you can essentially make it private and then use a third party service to charge for your GPT. Alright. Then how can I share my GPT with my team? Well, I'm gonna show you that but essentially, there's different options when sharing your GPT. You can make it public, you can make it just for you or you can make it unlisted. And essentially if it's unlisted, that is the way that you can share it with anyone on your team. There are some better controls if you do have a team account, just just so you know, it's a little easier to share or revoke access to those GPTs with team members.

Jordan Wilson [00:27:47]:
Alright. Let's go rapid fire on your questions, and then don't worry if you're still if you're still hey. Is anyone still there? I always wonder. Right? Sometimes if if the episodes go a little long, are you still there? Should should we dive in live here? I think we can make it quick, but I think it'll be helpful. And if you are listening on the podcast, if, hey, if our livestream audience wants to keep going and, explore things live, I'm gonna do my best to describe it. But this might be one of those that's most helpful to obviously check out the show notes and and watch the video. Alright. So let's go over some of these some of your questions, rapid fire here.

Jordan Wilson [00:28:23]:
Alright. So, TC, I'm wondering if custom GPTs could streamline the prime step in the PPP. So without getting into details, yes. Kind of. It can. There there there are some, I'm gonna say there's some ambiguity with how the document retrieval process impacts tokenization. In our testing, it's it's different every single time, so it's hard to keep memory in mind when using GPTs. So, without getting into the weeds, kind of.

Jordan Wilson [00:28:53]:
Hector, where can I find a guide to build my own custom GPT? There's tons of them. We we did a video, on that, Hector. I'll make sure to include it in the newsletter. Another question, want, seeking custom GPT for job seekers. Where can I find them? So, yeah, you can just go into, the GPT store, search anything. Search job seekers, search career builder. Right? Like, what whatever. And there's probably dozens or hundreds of different GPTs.

Jordan Wilson [00:29:17]:
You can quickly try them all for free if you do have a chat gptplus account. How can I eliminate another question? How can I eliminate hallucinations when building a custom GPT? Well, you need to increase the quality of your data. You need to know how your instructions impact how chat gptx. And and we'll go over that here in a second as well. Another question, Hector. Love all the questions. Where can I find a searchable database of custom GPTs available for specific tasks or use case? Well, the GPT store is not the best. We do also have our own custom directory on our website.

Jordan Wilson [00:29:51]:
So just reach out to me if you want access to that. And then Hector, another question. How can I publish a custom GPT as a Chrome extension? So you can't. There's not the way that you would build it inside chat gpt with the, GPT builder. You could build it in other ways, but, that's a different different question for, or a different show for another day. Alright. Frank says, how can we get the latest free and previously paid PPP? Well, hey. Our PrimeProp Polish course is always free.

Jordan Wilson [00:30:22]:
We do paid engagements like this for companies. Right? But our free one, we mentioned it in the newsletter every once in a while. So, Frank, if you've ever registered for our course before, it's the same link. You can go up there. Alright. Looks like one other question from Jay. How do you know which custom GBT in the store would be best to start without trying them all? Luckily, a couple weeks ago, and if you follow our show, we mentioned this in the news, ChatGPT just released some more statistics on GPTs. Before, there wasn't a lot of that information, but now you can see, the average users, the average score.

Jordan Wilson [00:30:57]:
So normally, just like with searching an app, right, you would want the one with the most reviews, the highest score. Same thing. Right? Not saying that, you know, new GPTs with no reviews and no usage can't be good. But if you wanna know a good place to start, find something with, you know, 4.5 stars and, you know, 10,000, you know, uses. I I think is a good place. Another great question from Doug. Doug saying, our custom GPTs created in Copilot Pro available to non paying or to non paying users? So this what today's episode is about? And Doug, thank you for the question. We are not talking of Copilot Pro.

Jordan Wilson [00:31:33]:
There is kind of a way to build a a version of of custom GPTs and Copilot Pro. That is not what today's episode about. We're just focusing on them in chat GPT. Alright. That was a lot. Let's do this quick, y'all. Let's let's build this live, shall we? We're not gonna build 1 live from scratch, but I want to show everyone, a quick example use case, and maybe something that I would use a GPT for. So, go back and I said, what is it that you do repeatedly as a knowledge worker? Right? You have some level of expertise.

Jordan Wilson [00:32:08]:
You have some level of of knowledge, some level of, domain specific experience in a certain sector, that someone pays you for. Right? So think to categorize that knowledge and think, okay, what are these repetitive tasks that I do that involve either, you know, writing, research, analysis? What are these, you you know, repetitive tasks that I do over and over that I could make a GPT? So just as an example, something I do a lot right here as the host of Everyday AI is I plan a lot of podcasts. Right? We do this every single weekday, Monday through Friday. Right? So as an example, am I an expert at planning a podcast? Nah. I mean, I'm okay. Right? I've done it 250 times, but I use Chat GPT to help me. Right? So let's let's look a little behind the scenes here if if if y'all don't mind, and let's, just give it a an an example here. Alright.

Jordan Wilson [00:33:05]:
So, let's let's dive into this here. So I have an example here of a podcast planner. Okay? So I am in the GPT mode here and you can always access your GPTs, like I said, on the left hand side, of your toolbar. So there's some of my GPTs and this is the one that we're gonna be doing an example of here. This is called the podcast outline planner. Alright. We're not gonna build this from scratch, but I'm gonna show you kind of how it's built and kind of show you around the interface. Right? So if you are brand new, to GPTs, it's very simple.

Jordan Wilson [00:33:39]:
So there's essentially a create tab and a configure tab. You can do work in ether. Right? So essentially, the create tab is, is is is more of a it's like using ChatGPT to build ChatGPT. So you can just have a natural language conversation with ChatGPT to build, a custom g p t. Right? So you can say, hey. I wanna build a g p t to help me plan podcasts. Right? And then it's gonna ask you some questions. It's gonna go back and forth.

Jordan Wilson [00:34:12]:
Right? And then you can answer those questions. And essentially what happens is chat GPT or the GPT builder is going to, take away what it believes are the most important instructions essentially from that natural conversation that you're having with it. So like I said, you don't have to know how to code. You have to know how to have a conversation with a bot, which is extremely easy because the GPT builder kind of guides you through it. Right? And maybe you, you know, played around with GPTs when they first came out in November and, you know, early December, and you haven't been back since because it was a frustrating experience. Right? This the experience has improved a lot. Right? I remember it used to sometimes take 15, 16, 17, especially in the 1st week or 2, generations, and and the GPT builder would just time out. It's not like that anymore.

Jordan Wilson [00:35:01]:
It's it's pretty reliable. Right? So in natural language, you can essentially create custom instructions and tweak, and make a version of ChatGPT for a specific purpose. So let's just say as an example, you're a CEO and you wear a lot of hats. Right? And you're managing or you're helping manage, you know, your marketing department, your finance, your sales, your HR. Right? In theory, in theory, right, you could create a custom GPT and upload custom knowledge in each one of these things. So like I said, after having a conversation with the create kind of, tab, it creates configuration instructions. Okay? So if you're, on the live stream now, I have the configuration instructions for this, GPT that I use that helps me plan podcasts. Right? So I'm not gonna go through these, like, step by step, but it essentially is a series of steps and there are some formatting that helps, ChatGPT kind of better understand this.

Jordan Wilson [00:36:05]:
But essentially I'll kinda read the steps 1 through 9, right? I'm not gonna go into it, but it says prioritize guidelines is step 1 and there's a description. Step 2 is receive topic. Step 3 is document recall, and I'm gonna show you the document that I uploaded. Step 4 is initial research. Step 5 is in-depth analysis. Step 6 is engage in conversation. Step 7 is further research. Step 8 is prepare outline draft, and step 9 is present final outline.

Jordan Wilson [00:36:31]:
Right? So I've tweaked this GPT a little bit by using both the builder and, the custom configuration. So you can also, especially if you've used ChatJPG a lot, you don't have to go through the create process because it can be time consuming and especially if you know what you're talking about. What I like to do is I write my own configuration instructions from scratch because I've done this a lot and I'm I'm pretty okay at it. So then I'll do that and then I'll use it. So essentially, on the left side, you have your 2 different tabs. So you have your create and your configure. And then on the right side, you have a preview. Right? So I can actually, in real time as I update something, I can test it out to see if it's working, as I want it to.

Jordan Wilson [00:37:14]:
And then if it's not, what people don't even I think one of the the most underutilized features of of, the GPT builder is using it in this way is essentially, especially if you've built 1 or 2. So I know the beginner, you you know, this beginner's guide, maybe a lot of our audience you've you've built a lot. So this is a tip that I think a lot of you can can benefit from, especially if you built a lot because you know how these work and you'll get better. So here's here's a little tip. Right? I like to write configure instruct the configure instructions from scratch. So I go straight to configuration. I don't use the g p t builder. Right? So you have your instructions which you can type.

Jordan Wilson [00:37:53]:
You have your name. You need to give it a name, a description, and then a photo. You can upload your own photo or there's a DALL E option that you can just click on and it'll, generate a photo using DALL E. You have conversation starters and those are, you know, I'm just gonna say, let's plan a podcast even though that's not gonna do anything. But now when I update this, that's going to be a conversation starter the next time that I use this. I believe my view is a little too small there. Okay. Also, then you have your knowledge base.

Jordan Wilson [00:38:24]:
Right? So this is where you upload documents. Right? So when I say this is mini rag, it's not really, but it's the concept of this, you know, retrieval augmented generation where you can, tap into the power of chat GPT. And this is where I think GPT has become extremely powerful. Again, don't load private, sensitive, confidential, PII, PHI. Don't upload that, type of documents unless, you know, someone at your organization has told you to. Otherwise, don't do it. However, this is where you can upload custom documents, your knowledge, your brand voice, you know, examples. Right? So in this case, this this PDF that I have here is examples of a podcast outline.

Jordan Wilson [00:39:08]:
So that's exact that's essentially what this custom GPD is. So I give it all these instructions. Right? And I'm gonna bring up these instructions because I wanna point a couple of things out and maybe this will understand, oh, here's why it could be useful. And I'm gonna show you, how it's used. So this is really why it's it's useful. So, I'm having it, in step 3, do a document recall. So it's looking at the document and in the document, I give explicit examples of exactly how a podcast outline should be formatted, what it should include. So I give it you know, we talk about shots, quote unquote, shots and prompting and how zero shot prompting is is terrible and you gotta get bad results.

Jordan Wilson [00:39:44]:
So in theory, I'm giving it examples. I'm giving it input output pairs, which are technically called shots, which should improve outputs. But I'm doing that, in a document. Right? Because sometimes when these configuration instructions get super long, the performance can go down. So in this in my, series of steps, I'm telling it at step 3 to always anytime that there's a new podcast topic that I type in to always go in and do a document recall, to look at that document, to understand that, this GPT needs to be outputting a podcast outline exactly how I need it. Also a couple other things here. Right? And if you've taken our free PPP, you can see where some of this is coming in handy, right? I'm telling it to do initial research, and I'm telling it to use the browse with Bing tool to source recent information from the year 2024. So I'm doing what we call a targeted browse with Bing call.

Jordan Wilson [00:40:38]:
I don't just say use the Internet. I say use browse with Bing and find recent information from the year 2024. Okay? And then I'm saying, for it to visit at least 10 pages and to gather comprehensive details about the podcast topic that I suggest. And then you'll notice, hey. And for anyone that's taken our PPP course, I'm not asking it right away to give me a podcast outline. I'm saying, first, go do research. Right? So think, RAG, mini RAG. Right? And this is priming.

Jordan Wilson [00:41:08]:
Right? This is essentially what we call priming. This is a very small version. Right? I'd still personally prefer to do this via a chat. But then I'm telling it, first, understand the topic. Go read the documents. Go research, then ask me specific questions based on your research that'll help you best fill out this document. Do you see how much time we're already saving? That's all ready. I'm telling it to go to 10 different sources, read the outline.

Jordan Wilson [00:41:35]:
I'm already saving probably an hour or 2 just and we're not even done yet. Right? Then it's supposed to ask me questions based on what it finds. I, the user, you're right. And if if you're reading this, it's this is what I'm telling it to do in each step. Then I answer the questions. Then based on my questions, it goes out and it uses browse with Bing again here in step 7 based on my answers. Right? So, again, this is the the concept of priming. Right? And you don't just want a cold prompt because you're gonna get bad results.

Jordan Wilson [00:42:06]:
So first, it researches everything, comes back, asks me questions based on my answers. It's gonna go do another round of research, at least 10 pages. Does it actually use 10 pages? I don't know. I've researched, I say 3, 5, 10. Do you get better results? Sometimes, right? It's it's arbitrary. There's no way to to to know if it's actually using 10. But I do find at least when I give it a a higher number, it usually comes back with better results than if I just don't give it any guidelines. And then after all that, it's going to prepare a draft.

Jordan Wilson [00:42:36]:
Alright. So let's do this. I'm gonna do this real quick y'all. So So I'm gonna go into the default mode. Alright. So I'm gonna start a new chat, and hopefully this makes sense. So I'm gonna start. So we started.

Jordan Wilson [00:42:53]:
We started by talking about how you should be using this not in the dedicated GPT mode. Alright. So I'm in I'm now gonna call a web reader plug in. My, my my chat gpt is being a little finicky here. Let's try it again here. Alright. So now I am mentioning the web reader plug in. Okay.

Jordan Wilson [00:43:15]:
And what I'm telling it to do is I'm telling it to visit a specific URL. Okay? Oh, I didn't do my full, let's let's redo this one. I just realized I didn't copy my my whole prompt. It's nothing crazy here. Let's try this again. Alright. So what I'm doing is I am using a web reader plugin. The reason that I'm doing this is because, browse with Bing cannot visit specific URLs.

Jordan Wilson [00:43:41]:
Other GPTs, again, this is one very popular one that's in the GPT store can visit a specific URL. So I'm giving it a URL that takes it to recent AI news from the past 24 hours only. So I'm saying I'm using the web reader GPT. I'm saying go to this page and give me, 20 podcast potential podcast episode titles based on recent news. Okay? So now it's it's visiting all these this this recent news from this Google News, results page, which I think gives you 50 results, and it's suggesting different podcast episodes. Right? So I'll do this a lot. You you know? Yes. I can do this manually, and it still gives me right? People are like, oh, Jordan, is everything AI? No.

Jordan Wilson [00:44:25]:
This is just a way for me to more quickly research. Right? So as an example now, instead of me reading through 50, you know, news articles I have, and I I have links that I can always go back and read these. So I have links to recent, news articles and, ideas. Right? So, let's just say number 4 here, generative AI in the future of content creation. Okay. So I copied that. Now I'm in the same chat. Okay? So I'm in the I'm in the default mode of chat GPT.

Jordan Wilson [00:44:57]:
So now I'm gonna mention our new podcast outline planner. So this is called an at mention just like any social media. I type the at key and my recent GPTs are going to be there. And there's the one that I just built. Right? Or the the one that we just kind of went over, you know, by default. So the way I built it, right, is I just give it a topic. Right? So now what this GPT should do is it's going to right now, it's going back and it is going through all those steps. So this might take a while.

Jordan Wilson [00:45:32]:
We'll see if, ChatChippity is being a little being a little finicky today. I did just do this right before the show started, I swear, but this is sometimes how it goes. So now it's it's it should be going through, all of those steps. So the first thing, obviously, it it didn't do it even though I did it, did it earlier. So now instead, it just spit out the entire, description, which is which is funny. Right? Because I literally just did this. But, hey. That's another thing to know about generative AI.

Jordan Wilson [00:46:04]:
It's generative. It's deterministic. Right? It's you're not always going to get, ideal ideal results. Right? So now as an example, I'm just gonna go into I'm gonna try the same thing in the dedicated GPT mode. I actually have a couple podcast planners. Hopefully, I didn't just call on the wrong one. So here we go. Okay.

Jordan Wilson [00:46:24]:
So now when for whatever reason, maybe I should have done a hard refresh there. But now when I'm using the dedicated GPT, it's giving me it's going through correctly. It's asking me questions. Right? So, I'm gonna try to quickly answer this quickly. So one, it's asking me a question. Who is your intended audience? So I'm just gonna say, US professionals, 35 to 55. We're gonna go quick here. I don't like typing live.

Jordan Wilson [00:46:52]:
Are there, so so it's it's this GPT is doing its job. Right? So this is what I would normally be doing in my head, but it's doing it for me and it's making sure the result's gonna be customized. So then number 2, are there specific aspects of generative AI? So I'm gonna say, I'm gonna say creative aspects in general. I'm I'm not giving it good feedback because it's gonna take a while to type live, and I'm typing like a T Rex with short arms. Number 3, do you have any guest speakers in mind? I'm gonna say no. I don't have guest speakers, but you can suggest guests for this podcast based on your research. Right? So then question 4, what type of format do you prefer for this podcast? I'm gonna say, fun fun and conversational for the live podcast. Right? And then number 5, it says, is there a particular tone that you're aiming for? So I'm gonna say casual.

Jordan Wilson [00:47:47]:
Alright. So now I answered all these questions, and now based on the configuration instructions that I gave this GPT, what it should be doing now is it's taking all this information. It should be going back to browse with Bing, find sources from 2024. And now the next generation that I should get is my podcast outline and it should follow the exact template that I put in our knowledge base. So here it is. And it's it's doing it right here. So it is giving me the exact podcast outline, that I wanted based on the document that I uploaded in the knowledge base. And you'll see here it's just kind of it's gonna keep spitting it out.

Jordan Wilson [00:48:28]:
It did all my research for me. Right? So people always ask, Jordan, how is it possible to do a podcast every day? It seems like you do a lot of research. Yes. I do. Do I use, AI tools like custom GPTs, like Perplexity, like Google SGE? Absolutely. All the time. Do I use you know, do I visit web page pages manually and read them like a human? Yes. Do I visit web pages manually and have saved prompts via Chrome extensions? Yes.

Jordan Wilson [00:48:59]:
But, hey, here's one way that here's a task that I do repetitively, literally every single day. And if I didn't use AI, this would probably take me 3 to 4 hours longer than if I do use AI. So this is a very simple way that you can use a GPT based around a knowledge task. Right? And and, you you know, the more that I use this GPT, I'll go in and add more configuration instructions and kinda like one of the quote unquote hacks I was talking about, is is going in and talking in the create tab and saying, hey, This GPT is working pretty well. However, this step is producing bad results. Here's what's happening. Here's what should that should be happening. Can you please update all of the configuration instructions accordingly? Don't take anything away, but help me fix this one problem.

Jordan Wilson [00:49:50]:
Right? So then on the left hand side, you can have a conversation with ChatGPT about your version of ChatGPT to make it better. Right? So oh, that was that was kind of a long one, y'all. That was a long one. So, I hope this was a good beginners and maybe we got a little bit into intermediates, but a good guide on, custom g p t's in chat g p t. Again, to quickly wrap it up, GPTs are a version of chat GPT that you can configure on your own. It doesn't require any coding experience. All it requires is you need to have, at minimum, a paid account, $20 a month to ChatGPT Plus. At that point, you can go in the GPT store and use millions of GPTs that have already been built, or you can create your own.

Jordan Wilson [00:50:41]:
Like I said, to create your own, you can create a decent version in a minute or 2. If you spend more time, obviously, it can it can be much better. There's more advanced customization, customization, options that we didn't really get to such as, you know, using third party APIs, different actions. You can use JSON, YAML, you know, yet another markup language. So there's more, advanced things that you can do within these, custom GPTs tapping into third party services via their API, via JSON, etcetera. But for for basics, anyone out there, you don't need any technical experience. Think of the knowledge work that that the the what you get paid for. Right? Think.

Jordan Wilson [00:51:22]:
What does not require private data? Right? What what in my head? What is that expertise domain specific knowledge, those repetitive tasks I do over and over? Can I create a GPT that can help me cut that down cut that time down by 30%, 50%, 80%, 95%? And the answer to so many of those questions is yes, if you do it correctly. So a GPT is a customized version. You can limit, kind of ChatGPT's, functionality by default. You can add more functions to it. You can add your own data, your own knowledge base, your own documents, and your own configuration instructions. GPTs, I still believe, to this day, are one of the most useful, one of the most useful generative AI tools out there and one of the most underused tools. I I I think people have this thought that they're they're difficult, or that they are extremely time consuming. And don't get me wrong.

Jordan Wilson [00:52:22]:
To create a very polished one, that is consistently giving you accurate, results, it is it is difficult. Right? Especially when you're talking about tapping into 3rd party services. Right? Maybe your company has an API. Maybe you wanna use Zapier. Right? And but use, I think there's, like, 20,000 different actions within Zapier. Right? So, yes, they can be very complex and, great ones can take a lot of time. But you can create simple, time saving GPTs to grow your business, to grow your career in a matter of minutes or hours. And those are going to pay off exponentially because the more you use them and the more you go in there, you know, tweak the the the the settings, add more knowledge, tweak your configuration instructions, the more time you are going to win back.

Jordan Wilson [00:53:09]:
Alright. I hope that was helpful y'all. If it was, please, hey. We spend a lot of time on this thing. I sometimes don't sleep a lot. If you could repost this, we'd greatly appreciate that. If you could leave us a review if you're listening on, on the podcast, on Spotify, on Apple, we'd appreciate a review. And like I said, if you are listening on the podcast, this is one of those that might help to come back and watch.

Jordan Wilson [00:53:32]:
I try to do my best to, you know, to to narrate, but some of these things are very visual. So, if if this was helpful, please consider telling others. Tag someone if you're, you know, on LinkedIn or or Twitter, x, whatever it's called. Repost this, to your friends, family, coworkers, and more importantly, go to your everyday ai dotcom. We did cover a lot in today's binner, beginner's guide to custom GPTs, in chat GPT. We went over a lot, went on a couple side tangents. So if you want the too long, didn't read version, make sure to go to your everydayai.com. Sign up for that free daily newsletter.

Jordan Wilson [00:54:07]:
And, hey, maybe we'll keep doing this thing. Should we keep doing this thing where we ask you all, you know, what we should be covering? Maybe we will. So, hey, this thing is for you. This everyday AI thing is for you, so make sure to get in on that daily newsletter. Make sure to join us tomorrow and every day for more everyday AI. Thanks, y'all.

Gain Extra Insights With Our Newsletter

Sign up for our newsletter to get more in-depth content on AI