Hello and welcome to a live episode of Leveraging AI, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business, and advance your career. This is Isar Meitis, your host, and yesterday may have been one of the most critical events in AI adoptions. Ever. And if you don't know what I'm talking about, I'm going to explain.
OpenAI, the company that just over a year ago gave us in the world, ChatGPT, which changed everything, just launched a GPT store yesterday. So some of you I'm sure are asking what the hell is a GPT and why is that so exciting? a GPT is like a mini version of ChatGPT that already comes with detailed instructions and data. Focused on completing a very specific task and that task can be anything you set it up to do.
So it could be something in your personal life, something in your business, things like respond to a customer service query or creating a question for a specific job interview or analyzing reports from a specific kind or any something that is very specific that requires specific instructions and data can be packaged as this thing that OpenAI calls ChatGPT. Why is that exciting and exciting?
First of all, because it's make it very useful to people who don't know how to use ChatGPT and how to prompt and how to use the whole process because it's geared to do this one little thing with very simple instructions. But it's also really exciting because this may be the app store moment off AI.
If you think about everything we know about mobile phones today, it exploded when the app store became available, meaning it suddenly had Very functional capabilities, the apps that we all use every single day across everything we do that made mobile phones, a lot more usable for a lot more people for a lot more use cases.
And the GPT store may be exactly that for generative AI, which means it's really exciting times that we're in day one off the app store and think about what you would do if you knew what the app store is going to be 10 years later. So I'm telling you now this is where we are now. Our guest today, Matt Page is The VP of strategy and marketing at Hatchworks, which is a software company.
But in addition, he's an AI coach and his biggest areas expertise is developing these GPTs and he's been creating them for his business since they became available a few months ago. So he's an absolute expert on the topic and hence he's the perfect person to have this conversation with.
And in today's conversation we are going to review in detail, step by step, exactly how you can develop your own custom GPTs for any need you have, whether personal life or for your business and potentially monetize it in the future through the GPT store. So I am really excited to welcome Matt to the show. Matt, welcome to Leveraging AI.
Thanks Isar. so excited to be on and we really couldn't have picked a better timing for this. So we were chatting about when we should do it and we're like, it literally, I think it was that day. They had announced the GPT store and we were saying, this let's do it Thursday. It may be live when we, when it comes out and it came out, what was it yesterday? it's been a while since it happened. but so excited to, to dig into this and the potential here.
And just for background, like you mentioned, I'd head up marketing and strategy at Hatchworks. But early in my career, I, worked as a research analyst and I worked with data scientists and it blew my mind, first of all, how smart they were, but working with all of these models and all this type of stuff, it was so complex and so difficult. And my main role was. Making sense of it and telling the story with the data, right?
But it's become completely democratized over the past couple of years with everything going on with generative AI. You no longer have to be a developer, a data scientist, all of these things to start taking advantage of it. So super excited to be on and to go deeper into custom GPTs. And you mentioned like an analogy earlier, there's two ways I like to think about custom GPTs.
One is if y'all remember the movie, the matrix and Neo's taken, I think it's the blue pill, blue or red, somebody correct me if I'm wrong, but he's in there and Hank, one of the guys that's there, he plugs this thing into the back of his head and he spends 10 hours just learning all this stuff. and that's where you get the iconic line. I know Kung Fu like that. That is what a custom GPT is. You get to optimize this thing.
You get to give it its own brain, its own knowledge base, the custom instructions, like you mentioned for very specific use cases. It's like a hammer versus a specialized. I'm just really pumped to talk about these a little more today. I don't know if there's a specific area you want to get into, Isar if that triggers any other points on your side, but really excited to talk about this today.
Yeah, so first of all, before we jump in and we're going to be very tactical and really explain how to do this and share it with you. But Matt, let's really get started with how does it even look like? Where does it live? if I want to build the GPT, where do I go? Like, how do I get started? And feel free to share your screen. For those of you, for those of you listening at the podcast. Yeah. Can go ahead and do it. afterwards, we'll explain everything that we're seeing on the screen.
It will be available on our YouTube channel as well. But, we will be sharing a screen for the people who are here, live with us.
Yeah. Perfect. can you see my screen? Yes. It's showing up. Okay, perfect. Yeah, so I think this is a key elements. Like, how do you even get started? You hear about custom GPTs and that may trigger for some folks. Is this like a completely different tool? It's actually part of ChatGPT. it's very simple to get to it. The one, key thing I believe, you do need the plus plan. So it's 20 bucks a month. I've had it for so long.
I couldn't remember if that was in the plan or not, but you do need the plus plan. Best 20 bucks you'll ever spend. It'll pay for itself a thousand times over. So all I gotta say is just do it. it's,
I'll second that and I'll let you continue.
Yeah. And all you do over here is go to explore GPTs, right? So this is the new GPT store. Interface. And we can chat a little bit about this too, because this is brand new since yesterday. So there's some parts that are really cool. There's some parts that I think are a bit underwhelming. the biggest, I think, piece missing is the monetization element. So they launched the GPT store, but what they didn't do is they did not launch the monetization piece.
And if you look at their blog, go to open AI blog, check it out. There's a small blurb and actually have it right here. So why don't we just look at it? So they're introducing the GPT store. You scroll on down, here it is. Builders can earn based on GPT usage. So in Q1, we will launch a GPT builder revenue program as a first step. US builders will be paid based on user engagement with their GPTs. We'll provide details on the criteria for payment as we get closer.
So a couple of things like bummer, you can't monetize yet. And also a bummer that it's only launching initially with US folks. And of course, they'll expand that globally, but starting with the U S. The most interesting thing for me though, is they're paying out on user engagement. And I think this was a big open question. Was it going to be, you mentioned the app store, is it, was it going to be like the app store where. builders can set their own price. How does it work?
What cut does open AI take, but they're actually going to be taking a user engagement model and something that seems similar was the old, TikTOk, I think it was creator fund is what it was called. So based on the user engagement, the use of your GPTs. That's how you're going to be paid out.
and I think that's a very short term thing, right? I think they don't exactly know how it will evolve. If we look at probably the most successful model of this in history is YouTube, right? If you're a YouTube creator and you can drive engagement, you can make. Shit loads of money and yes, they sell ads. So it's a different business model than ChatGPT, but none of us knows where this will go six months from now, not to mention two years from now.
And so I definitely think there will be a monetization mechanism. I really hope they will figure out a way to make it significant because GPTs, just like we know from. The app store, or just like we know from the content on the bigger YouTube creators. But with that, let's really go back to ChatGPT itself and look at, so if I want to get started, let's first of all, explain, show where it lives, but then explain what are the components you need?
What are the building blocks to build one of those GPTs and examples of what they
can do? Yeah, definitely. And just for reference on the GPT interface, the store, there's different pieces you can scroll through to see other ones. Great way to get started. See how other people are building GPTs. But if you want to create your own right up here on the top, you have an option of create. So very simply hit that and it takes you to the GPT custom GPT interface.
And I'm going to walk through the couple of different elements here, but I think one key thing that's so cool about custom GPTs, if you think of back in the day, Excel, you were at a blank canvas. You can do tons of different things here, but what do you do? It's the same thing with ChatGPT. ChatGPT is amazing. I can do a million different things, but I'm with this like blank canvas of not knowing where to start. Custom GPTs are like templates to help people get started for specific. Use cases.
So the first point to call out at the top here, there's two different modes. There is configure mode, which this gives you full autonomy and control over your custom GPT. And you can completely configure it. And we'll jump into an actual example here in a second that I like to use, to take, to go through the steps. The other mode is create. And this is like exactly like interacting with ChatGPT. So it starts off by saying, Hey, I'll help you build a new GPT.
You can say something like make a creative, who helps generate visuals for new products or make a software engineer who helps format my code. And you literally just interact with the GPT. And it starts to configure and build based on your interaction. So it will start to fill out the configure pane. Uh, all
for those of you listening and not watching on the podcast, it's just two different tabs that you can, or button and modes that you can switch to. One is more, beginner's mode. That is the create, which is more of a natural language. And the other one gives you more. menus and options and things to fill out, which if you're a little more advanced, it's really not that hard. And we'll go through it right now. Like literally anybody can
do this. Yeah. Great call. It'll be a little more descriptive for the podcast guests. So in this pane as well, one thing you'll note is the right pane of the screen over here. This is essentially your preview mode. Think of this as like how you test your GPT as you're building it. So it gives you a way to interact with how the GPT will work. As you're building it. So to start with a, a pretty basic example. So I used to be in, deep in product management.
And one of the biggest, most important elements when you're working on the agile side of things is developing good user stories, right? So this piece in and of itself creates so much rework when there are bad user stories. So think of a user story essentially as requirements for what to build. And there's a very standard framework within Agile principles of how to create a user story. And more times than not, it doesn't get followed. A lot of times, it's pushed off to a junior BA to create.
And you'll have the user story. The developer will create the feature. And it's done incorrectly. There's something lost in communication. And a lot of times, it's due to a poorly written user story. let's create a GPT that helps you craft The perfect user story. And what's cool about this is a. Literal tool that anybody on this call podcast, whoever could build this and it provides direct value in terms of cost savings, less rework, especially with developers. Cause those are expensive folks.
so the first thing we do is we give our GPT a name, let's call it our user story pal. let's, give it a description. So when you think about the description, this is. publicly facing. So in the GPT store, this is what people are going to see when they're on your GPT. So think of a really strong kind of hook and value prop when you're creating here. And you can see on the right pane or testing pane, it's starting to fill this, these details out. So you see the name there, you see the description.
And
just to tell people how simple this is, because the description needs to be two things, a, it needs to be descriptive, it needs to tell you what it's going to do, but it's also a marketing thing, right? Because now it's a store and, people want people to pick yours and you can use it.
ChatGPT to help you write the description, tell it that it's going to be on the GPT store, tell it that it needs to be very detailed, but yes, attractive and irresistible to people use whatever adjectives you want, and it will help you craft the description and it's relatively short, but it will help you craft the description in a way that will be attractive to people to
actually test this out. Yeah, I'm glad you mentioned that. That's a big unlock that sometimes people forget. It's like you use ChatGPT as you're building your GPT to improve it. Have it as your sidekick as you go. It's a really important concept. So the next major piece is called instruction. So these are. detailing your GPT, how to interact its persona, what it should do all of those things. And the greatest thing here is you're building this into your GPT.
So the user in a blank chat, GPT interface no longer has to put in all this detail. It's built directly into it. so I'm going to add some detail here. We'll go through it. Pull it up here. I'm doing a nice copy paste to make a better use of time here. Sure. okay. So let's pop this in here. All right. So you're an expert user story writer with 30 years of experience writing perfectly defined user stories. So really important to set your persona. So what role does your.
Your GPT play another key piece, give it a very specific role. That's well understood. Don't give it like five different roles that may confuse your GPT. All right. The next step here is going through detailing the process of how the user will interact with your GPT. So this is where you're Instructing your GPT how to interact. So what we have here is when a user engages with this GPT, follow the below process.
So the first step, ask the user to provide a copy of their user story or provide details about a user story they want to create. Step two, after the user has provided a copy of the user story, give it a grade of one to five based on the quality of the user story. So you're giving instant feedback to the user, which is pretty cool. And you can use scoring type of ideas like this. number three, provide a clear explanation for the grade. people want to know why they got a certain grade.
We're going to give them that explanation and then provide clear instructions on how to improve it. And then this is where the interaction comes into play. We want our GPT to ask clarifying questions that will allow the GPT to provide an improved user story. So the GPT has the context of the initial user story. Now we're saying, okay, GPT based on what you know, ask some clarifying questions so you can now improve the user story for the user.
Next up, after the user answers the clarifying questions, provide an improved, user story following the correct framework detailed in these instructions based on the user story the user provided. If the user is, if the user story is too large in scope, provide a recommendation on how best to split it up. and that's a key point too. A lot, that's a big issue with user stories. People will make them too large. all So great.
We have our custom instructions here, but I mentioned, follow this correct framework. What is the correct framework? So this is exactly easier. Like you mentioned, let's go to ChatGPT and have it craft this for us. let's go to chat dbt and we'll mention, we'll give it the persona again. So we're going to say you're an expert user story writer with 30 years of experience of the same persona.
Then we're going to say, provide a detailed framework for how a perfect user story should be crafted, including the necessary sections in the user story and the detail that should be. Included in each section. So we're having ChatGPT do the work for us. So I'll add one
thing as we're waiting for chat to write this for us. In this section and later on, you can also attach documents and maybe Matt, I'm stealing your thunder here, but, you can add additional content. So if there's a book or an article you really like, or a best practices used in your.
company that again, not many people actually follow, you can take that PDF document or whatever format you have it in and use it in here as the instructions for the GPT on how to a grade and be a feedback and three now write an updated one that will follow whatever guidelines you want your company to follow. So again, it could be an internal document, but this could be a best practices from a book segment that you really like.
Yeah, no, that's a perfect example. and back to our matrix example, right? that's the detail that we're plugging into the back of this GPT's head, so it knows what to do. And we're actually going to, do that in a way here in a second, again, library leveraging chat, GPT, but great reference. if there's a great. Article on how to write user stories, a book, whatever it may be. Those are great things to add. So let's check out the outputs. It mentions a title. Yes, we need that user role.
Persona, is a very important piece. We want to know what role, that's interacting with this system. What's the role that they're playing. The user story statement, those that are familiar with it will be very familiar with this. A typical user story framework is as a, whatever the user or persona is, I want to achieve some goal so that. Explain what their, the benefit they're going to get from that. So very clear framework there. Acceptance criteria gets forgotten way too many times.
It's what's the definition of done? How do I know if this work is complete? Gets, gets forgotten way too many times, any dependencies or preconditions. Non functional requirements, data requirements, lots of good stuff here. So I'm going to take just the first bits here. I'm going to take down to, let's go down to like dependencies and preconditions. some of this other stuff we'll leave out for the purpose of this exercise. All right. So we'll come back down here.
And we will pop in our details for the framework. Let me just add in this bit of detail. Another thing you can do is you can break things up, using
different things. Again, for those of you who are not watching this, what Matt is doing is he copied the input we got from the regular ChachiPT on what are the best practices and framework to develop a user story into the instruction sections. Of developing the GPT and is creating a visual separation, like with a dotted line or any visual separation that you want to create, because it helps the GPT.
And by the way, same thing with just regular instructions in ChatGPT to understand the different segments of what it is. So the beginning was general instructions, and now he's adding those, the actual framework into it and saying, okay, this is the framework I want you to use.
Yeah, perfect explanation there. so it adds that separation. Now we're getting into the framework. So I've added detail around crafting a perfect user story involves meticulous attention to detail and understanding the project requirements and stakeholders. Here's a comprehensive framework for creating the ideal user story. So I've popped in the key pieces I want there. So now it has a reference for the detail that should be included in the user story.
So the other piece I want to, mention is the knowledge base. And you hit on this. let's give it some context for what a good user story looks like. Again, instead of me coming up with examples and ideas, let's just ask, ChatGPT, right? So we'll say, we'll take the framework down to where we selected. I'm going to say, give me five examples of great user stories. Using the below framework. All right, pop that in. And again,
in ChatGPT itself, for those who are listening, in ChatGPT itself, we're asking ChatGPT to give us examples. Of what it told us to do. So it told us to write a title. Okay, give me five good examples for a user story title. You told me to provide acceptance criteria. Give me three examples of what a good acceptance criteria. And we're going to use these examples in the GPT to give it examples.
And one of the most important things when crafting any prompt, but also instructions for ChatGPT is Examples. And in the professional language, it's the difference between zero shot and few shot prompting. But basically what it means is it means you're going to get much better results. If you give it examples of what is good and what is not so good or what is bad. And you can give examples for both positive and negative things, as long as you explain what they are.
And if you do that, then that helps. ChatGPT. And in this case, this particular GPT to be a lot more concise with its answers, because we'll try to align with what you told it is good or bad. And you can use very long examples for anything. And if I generalize this, let's say you want to write a proposal and you have a proposal framework, you want it to follow. You can actually. Paste in a proposal framework. Let's say you have a script for salespeople.
So take your successful salespeople have a transcription of what they use in the actual calls and use that as an example to create a new Framework for your salespeople, like each and every one of those things that you have something that is successful in your business, you can use as an example. And like I said, you can also use bad examples. Like when we did this, the thing failed, whatever that thing is. So you can also give bad examples.
So don't follow this because this failed every time we tried it. And now ChatGPT can have a much clearer framework, or if you want guardrails to work within.
Yeah, that's perfect explanation and a key point you hit on the whole, notion of garbage in garbage out. Same thing goes with ChatGPT, generic in generic out, right? You have to be very detailed in your prompt and what you're looking for it to do. So what I've done here is I've just copied the five examples it gave me, popped over to a Word doc and, pasted it in there. So now what I'm going to do is file and just download this into a Microsoft Word doc.
I'm going to come over to our knowledge base. So for those that are listening, one of the features is the knowledge base. So you're able to upload files. And the beautiful thing here is you can upload word docs, PDFs, PowerPoint presentations, Excel files, images, HTML files. there's. So many types of files that you can upload into your knowledge base to give it context. And I'm probably forgetting several. I don't know if there's any others you can think of that. Yeah,
I think you touched on the main ones, right? and I think any file you're going to have can be converted to one of these things, right? So even if you have a file in a different format. If it's a database, you can probably convert it to a CSV. If it's a document from a different source, you can probably convert it into a PDF and so on. So really all the major file types you can upload here.
And again, these file types are sources of information for the GPT to do the specific thing we're going to ask it to do. So I gave an example earlier, if you have a internal document that explains how to write user stories in your business, load that document in here. If you have a style guide and you want this thing to create images for your PowerPoint presentations, then load the style guide in here, it's going to use it and so on and so forth. Like whatever.
Use case you have, the more background information you're going to give it, the more accurate the results are going to be.
Yeah, great points. And the one thing I did add again, another line break, I added a note, just giving the GPT reference in my instruction, saying the attached document in the knowledge base includes five example user stories for your reference. So now it knows how to use that document in the knowledge base. Very important. Otherwise, ChatGPT is just going to figure it out on its own.
And 80 percent of the time it'll probably be fine, but 20 percent of the time you may get some weird hallucination. better safe than sorry. I want to
add two things to that. One, if you have more than one document, then name the documents. So document this and that is this and that information. So again, chatGPT knows where, what information to find in each. Another thing that I'm doing in mine, when I use these kinds of things, not this, but even more specific, let's say you want to create a GPT that is your employee guidebook.
So you're going to load all the employee guidebooks that you have in your, Company into ChatGPT, and then people can ask it questions like how long in advance do I need to request a vacation? How many vacation days do I get if I'm just starting in the business? Who do I need to call to get a new employee card like all these things can be in this document what you want to?
Add in the instructions and is say two things one is Only use information in this document to answer the questions If you do not find information in the document, please say, and then put in quotations, whatever you wanted to say. Information not found, because otherwise it will give you an answer. It will make up an answer because you ask it for an answer. So it didn't find it in the document, it's going to still make up an answer.
If you tell it specifically to say information does not exist, or null, or whatever you want the answer to be, It will actually give you that answer when the information doesn't exist. And the third thing that I do in all of those that are very information specific, I ask it for a citation and the name of the document and the page in the document. So I say, when you give me information. Site where you, the specific phrase you took it from.
And if there's several side, all of them, and tell me next to it, which document and which page, and it will do it, it will say, here's the answer for what you ask so you can take, I'll use my example, you can take 20 vacation days in your first two years of working in our company, and it's going to say. The actual statement from the document that's from page three off the employee manual and this makes it very real and allows you to also verify that the information that you're getting is
actually accurate. Yeah, it's such a great point there. And we, what you just talked about, we've created one of those at Hatchworks, our company, we have like hundreds of pages of employee, handbook docs. We've loaded it into there, but that would that point you mentioned though, be very clear on how much leeway. You give your GPT to riff on its own because the example you gave on like vacation days, that's not something you want to get wrong.
Especially when you're like employee handbook, rules and just policies. You want to give it context to be very explicit and use exact information from the knowledge base. Don't just, come up with something that sounds good. it's a really great point there. So the next piece here is your conversation starters. And this is how a user will begin to interact with your custom GPT. And what's interesting here to me is you're starting to get into almost the UX, the user experience of your custom GPT.
And I think this is where a lot of evolution is going to happen in custom GPTs is this, ability and functionality we have to adjust the user experience. Like the way I equate this is when, the mobile phone came out. Texting on a number pad was amazing and snake was the coolest thing out there, right? And we laugh at that nowadays, but it was groundbreaking. Then, you think back to the Internet, you couldn't be on the phone and use the Internet at the same time, but it was still amazing.
We're at this early stage with these. and I think we're going to look back. And I think it's going to take a lot shorter time than those other transformational things. And we're going to laugh at how basic this all was. so for the conversation starters, let's just give it a, a few different things we can say. give me your user story and I will make it perfect. just, you can add whatever kind of starters you want here. You can add more than one.
Maybe somebody's just looking for, what is the proper. Framework or a user story. And we could provide that detail to them as well. So these are different inroads that people can begin to engage with your custom GPT versus just giving them a blank slate. And for those, listening, what's happening is these are buttons that have been added. Above the prompt window in our custom GPT. So you can see those appearing on the preview window as we go. last piece to mention here.
two things, but we'll go deeper into one is the capabilities. There's currently three. And again, I think this is going to grow as time goes on. Web browsing is a good one. I usually leave that one enabled. Dali three is a great image generator. We don't need image generation for this. G a custom GPT. So I'm going to turn it off. And then code interpreter is a really cool one. If you're dealing with anything with code or reading code, enable that one. If you're not though, turn it off.
Like for this one, we're not, we don't need code interpreter. I have seen some weird things where if you have that enabled, it can do some weird stuff where it's just like starts generating code. For no reason. moral of that story is use only the capabilities you need.
one, one small addition on code interpreter, which is funny to me. They went back to the original name. So they came out with code interpreter probably around may and what did code interpreter can do it writes. Code in the background. So you can ask it a lot more sophisticated things like data analysis, OCR of documents, and stuff like that. And he will write its own code in the background in order to do the function that you ask it to do. And does it. Close to real time, right?
You ask the question, it thinks about it, writes its own code and then runs the code and then spits the answer. So if you need any data analysis, and that's what they changed the name to afterwards. So it was Code Interpreter, which is a horrible name. There was Data Analysis, which is a better name, but now they went back to Code Interpreter. But to make a long story short. If you need any kind of data analysis done through the GPT, then you need this turned on.
If you don't, turn it off, because otherwise it may try to do this when it's not necessary, which will make it a cumbersome and B may give you the wrong answers.
Yeah. If you need to do math, any of that kind of stuff. And what's, I think this is a key point too. So many people stop at just using ChatGPT for writing. It can do amazing things with code. So at Hatchworks, the company I work at, we're going deep into this. So we're a near shore software development company with our focus in Latin America and the U S with same time zone. But we've gone deep into this and we've developed our, what we call generative driven development framework.
And like the use cases and tools that we're starting to create are amazing. It's so much, enhanced productivity going on. But if you look at code. It's just another language. That's all it is. Just like English, it's another language. So it makes sense that, generative AI does a really good job. it code debugging, even thinking through like architectural decisions, like really cool stuff. We're starting to find some neat applications for, last piece is the actions.
We're not going to go deep into this, but this is, if you need to connect to an API, you can do that here. there is a GPT called the actions GPT created by open AI. Use that. You do not need to be a developer to figure this out. You basically come over here, get an example schema and feed the action CPT, your documentation for the API. Say, here's the standard schema. I want you to follow, give me the schema for this API I'm trying to connect to and it will do it. and
I want to connect that there was a question from Ted in, in our call that says, do you think there will be an integrations with various CRM packages if we were to use GPT to create content for sales? So I think this kind of relates to that question. If you can contextualize one to the other, I think that's going to be very helpful to Ted.
Yeah. And I think, so this is the really cool part. You can connect to other systems via APIs and for those that, Maybe less familiar with APIs and apologies if this is a more tech savvy crowd. But the example I always go to is it's like going to a restaurant. The API is like the waiter, right? You interface with the waiter to order your food, look at the drinks, all that kind of stuff. You're not having to go in the back of the house and cook your own meal. So think of it that way.
So if I want to integrate with Uber or Spotify or any other kinds of things, You can do that now with your GPT. I think what's going to be really interesting. And I saw the founder of HubSpot, and his name's escaping me right now. but it'll be interesting to see if at some point in the future, you can connect outside things and integrate those to your GPT. So in the reverse way. And I think that's going to be a huge, unlock in the future as well.
And once you put your detail in right down below at the bottom, you can actually test it. Within the platform. So it's testing as you go to make sure it's working properly. Actions is a really cool, feature within your custom.
And by the way, for those who are just getting started, you don't have to use the actions, like you don't have to go into that section at all. It's like for more advanced users really want to connect external capabilities,
into this. Yep, definitely. and I'm going to go ahead and save this now. let's go ahead. We'll make it available to everyone.
as you're doing this, Arturo added an interesting and important point. He said, recommend sample stories. So we gave it in the examples. We gave it examples on what's the right process, but you can definitely add actual user stories. Here's three great user stories that we've used that we really liked that delivered results. You can definitely upload those as well.
Yeah, and I just took the outfit from a ChatGPT on a first pass. So hoping fingers are good. it's interesting right now. I'm getting, it's saying it's like there's something new with the GPT store that just launched around the privacy policy, but just for context, if you want your GPT to be in the GPT store, you need to make sure you select, everyone available to everyone when you say. That will make it public in the GPT store.
looks like there's something new with the privacy policy that changed since this morning. I got to go update. but I'll put this for only me for now. all right, saving. All right, so now we have our GPT store. The one piece I didn't do is create a logo for it. But just for reference, and I'm not going to go in and do it right now, but you can basically upload an image or use Dolly three, and Dolly three will generate an image based on the detail of the user story, which is really cool.
And actually I think I have. Yeah, I created one before this. So this is a little brain with a pen writing user stories. So great. We'll use that. confirm. All right. And let me know how we're doing on time. I was going to actually run through an example. If we're good,
I'll pause you just for one second, just to summarize what we did so far, and then we have probably 10 more minutes to run through the example, and then we'll leave it open for additional questions, but what we did is we started with nothing.
And we created a tool in literally, if we would have done this without explaining everything that we're doing in a few minutes, we created a tool or maybe not a few, but 20 minutes, if you want all the right information in there that now can really in real life, in actual work environment, provide real feedback to product managers to create better user stories, which means. Huge time. Any of you who's in a software company knows this and everyone who knows you will have to take our word for it.
Huge time savings, which means hundreds of thousands of dollars that get saved from, Oh, that's what I thought you meant. And that's why I developed this thing, but it's not really what we needed and not really what our clients expect. And so having the right user story saves a hell of a lot of time and a hell of a lot of money because development time is really expensive.
And so within 20 minutes with zero technical skills, but with understanding of what a good process is, we can create a tool that we can make available just to our company, so we can share it just internally, or to anybody in the world who wants to use it, which then maybe later on will generate some kind of revenue to us. On the side, you can use the same process for literally.
Anything you can imagine, including, as Matt mentioned, graphic design, creating presentations, interviewing new hires, evaluating employee performance based on inputs from other employees, like literally anything you can imagine. You can create a GPT specifically for that, and you can go back and update it over time to make it better and better. as you see the results that it's generating. So this is what we have done so far. and now Matt, I'll let
you go through your example. Yeah, that's perfect. And I think too, if anybody's like struggling, like, where do I get started? don't put a high bar on yourself of having to come up with this amazing novel GPT, take your existing mundane, boring. Repetitive processes and try to make a GPT for those best place to start. Cause you're familiar with it. so what we're going to do now is we're going to start out by saying as a user, I want to enter my time so I can get paid for the work I have done.
in my career in the past, this is one of the tools, systems we built was a, time entry, time tracking system. And this is a horrible user story, but let's put it in and go
through. so just to explain what we're doing, what Matt is doing is running through the GPT we just created, right? So we created the tool. Now we're using the tool we just created to give us actual useful feedback.
Exactly. And you can see it starting to put in the output. So I got a grade of two out of five, not great. So I remember that was part of our GPT we created was give me a grade. and it says, thank you for providing your user story. Let's evaluate it based on the provided framework. So title missing, I didn't even have it, persona. And this is a great point here. And again, like I mentioned, a lot of times you have more junior BAs and folks like that creating user stories.
So instead of them having to go tap the product manager on the shoulder or even worse, let this flow through the whole. Cycle to the developer. They can just interact with this GPT and it never gets tired of answering questions. but for the user role, I said. I implied a general user, but I didn't specifically define it. This is very important for a good user story. give some detail on the statement acceptance criteria dependencies. I did not provide any of those.
So I got a horrible non passing grade, right? and if we come on down here, it gives some instructions for improvement and it asks me some clarifying questions. So can you specify the user's role or job title? So let's say. the user is a contractor, to, through what means or systems should the user be entering time, a web portal, a mobile app, let's say a web portal. So it's just using context from chat, GBT based on my user story to ask interesting questions.
And I've run through this example before or the user aspect. It'll actually prompt me. Based on the context of the user story I provided asking, is this a contractor or an employee? And I didn't give it that context anywhere. It's a great question that it'll sometimes ask a number three. Are there any specific steps in the process involved in time entry that should be captured in a way we could. Now I'm just thinking of this.
We could adjust it in the clarifying questions to give, examples of things, to do here. So that's another way we could optimize this. but let's say, time needs to be approved before payment is processed. So just we'll add some context there for, are there any preexisting systems or conditions that this user story depends on, let's say, needs to integrate with. A, HRS system, something like that. So we can pop that in and now it's providing my improved, user story here.
So it says title contractor, time entry for payment processing. The user role as a contractor, I want to enter my work hours through the web portal so that my time may be approved and I can receive payments for my work. And then it's starting to give different, acceptance criteria. Here as well. and it's interesting. It's starting to think through different things that I didn't even say or interact with the GPT on, the portal allows contractors to submit time for specific dates and projects.
I didn't give it that context, but that's a great acceptance criteria to add, submitted time entries can be, reviewed and approved by designated approver. Once approved time entries are automatically forwarded to the HRS system. Again. I didn't give it that context, but that's great context that gets my mind thinking, Oh, I didn't even think of that aspect of this user story. contractors receive a confirmation notification.
So really interesting how it's starting to think through different pieces here. And again, go back and optimize. If you didn't like a bit of how it interacted or the output it gave, go back and tweak. Like the example. I gave with the clarifying questions here. I should provide some reference and examples to get the user thinking a bit more, I think that would be a nice enhancement. but yeah,
I want to pause you for just one second to say two things and then to ask you a question that came from the audience. But the one thing that I want to say is that. If you don't understand what just happened, it's nothing short of magic because we've created a tool out of thin air in, again, in, in reality, if you didn't have to explain it, probably 20 minutes, maybe less. And now we gave it a user story. That was one line, which is a really shitty user story. I don't know why I give you two.
Should I give you one? It's just
nice. They get the same thing.
Now we have. Using the tool that we just created, we have a user story that is 30, 40 lines long with a lot more detail based on questions it asked us. So now it's being a, if you want a story consultant, because it's asking us questions and then it's created a much more detailed, much more cohesive, much more usable. User story based on the one liner that we created using a tool that we created in 20 minutes. This one thing that we just did would have saved.
two weeks of development that would have been really bad. And so it's absolutely incredible, this capability, and literally it's limited by your imagination. Now, the question that came out is Matthew Bow asked, love the user story concept. I'm a little late to the party here, but I'm wondering, could you have converted it into a Gherkin or other story format? So I will let you answer that.
Yeah, 100%. it could be any framework he wants and that's where in the, the configuration tab, you can adjust it to any. Type of framework you want approach you want, maybe you hate agile and you think it's the worst movement that's ever happened before and you want waterfall requirements and I'm having like flashbacks right now of 100 page requirement documents. Maybe that's what you want. Go for it. And, just for context, if you go back over to the.
Actually, I'll show that in one second, but just for fun, another thing here I did, we didn't prompt this, but I said, give me five more user stories. I should consider for this tool. So now, based on the context it has, it's thinking, okay, you probably need this, you probably need something for mobile access. You probably need something for time entry approval notification. So it's like going even further past what we had talked about. And then I can, feed that into the GPT.
But if you're in the edit GPT, here is where you would provide that detail, the instructions. And the one point I would mention, and I think the individual mentioned they're late to the party, meaning they joined the meeting late, but I think a lot of people feel like they're late to the generative AI party. But you're not like the amount of people that are truly embracing this is still minuscule. and with any major transformation. The beauty is everybody is at the same starting point again.
So I can't stress enough, embrace this, start learning it. this is the next big movement. I think Bill Gates said there's been two major things that really blew him away. It was the GUI. So the graphical user interface and ChatGPT. He skipped mobile. He skipped all these other crazy things, cloud, those two, right? So this may be even bigger than just a transformation shift. This may be. a whole different way in terms of how we interact and use technology. Matt,
this was absolutely mind blowing. I think anybody who has not used it yet, will get a lot of value. And those who have like dabble with it will also get a lot of value from it. So I really appreciate you taking the time and sharing your knowledge and experience with everybody in such a really detailed, structured way, thought after. If people want to. Follow you, work with you, learn from you. What are the best
ways to do that? Yeah. So LinkedIn is a really good way. TikTok as well. I go deep on specifically custom GPTs. Like ever since this came out on November 6th, I've been completely consumed. So that's all I talk about. my company, that I work at is Hatchworks. so we do custom software development and we've completely embraced generative AI. I mentioned our generative driven development framework earlier. If you're like stuck, don't know where to start.
we're doing everything from, training to, prototyping, like a quick kind of two to six week prototyping on these AI use cases. if you're just looking to get started with some experts. Check out Hatchworks, just Google Hatchworks. You'll find this, in generative driven development. You'll find that on our website to get a bit more context there as well. But those are the best. Oh, one of the thing I forgot today, I launched a new course on how to create and sell custom GPTs.
And for your audience, I'm going to give a discount code. For everybody listening, whether you're on the podcast or here live today, but it's 50 percent off. so we'll provide that out via some. Mechanism here. We'll put it
in the show notes. and if you want to share it in the chat right now, if it already exists, you can drop it in the
chat. Yeah, I will. I will do that, but check it out. I go much deeper than what we just went through, today. And, I'm going to keep adding to it too, as things evolve, like when the GPT store continues to evolve, I'll keep updating it as we go. this stuff's just super exciting. Yeah, I have not been this excited about something in a while.
Yeah, it is. It is, like I said, it's really a game changer and this is. Probably just step it's like version 0. 1 off of this capability. And I'm sure we'll see a lot more of it coming out. And it's really exciting, even in its current form. again, I just want to thank you so much. Since you mentioned the course, I'm we're running. So multiply the company I run is offering a broader course. So Matt's course. If you want to learn GPTs, he's definitely the best guy I know. So go sign up.
It's a game changer. You can automate almost everything in your business, by taking the score. So by itself, it's worth doing. the course that we're teaching is very different. It's a much broader introduction to business transformation using AI, how to build systems and processes and mindset, what tools are out there, how to use them. So it's a, it's an eight hour. Course in four sessions of two hours, and the next cohort is starting this Monday.
So those of you listening to the podcast, it's too late. You're gonna wait for the next one. But those of you are here live either on, on the Zoom or on or on LinkedIn. Then Joyce can share the link with you, on how to get that. And the link will be in the chat. And we are running a 24% off just to kick off the year of 2024. I see it's, kickoff 24 is the actual. promo code to get the 24 percent off.
And it's a course we've been running for a while with a lot of business leaders in various levels in multiple industries, and it's been very successful. But Matt, back to you. Thank you so much. You obviously know this very well and have a lot of experience. You're also very good at explaining this. So again, if you're interested in the course, if you want to learn this, Matt is your guy. And again, thank you for doing this and taking the time
Yeah, I really enjoyed it. It was a lot of fun.