Leveraging AI

94 | No Code AI Automation Framework from Concepts to Daily Efficiency with Nancy Bain

Isar Meitis, Nancy Bain Season 1 Episode 94

Unlock the power of custom GPTs and revolutionize your AI strategy! This exclusive webinar, designed for C-Suite executives and entrepreneurs, dives into a strategic framework for building and managing AI projects at scale.

Join AI expert Nancy Bain from Supernova Media as she shares her proven framework for creating custom GPT builds. Discover how to outline goals, manage iterations, and ensure your AI projects deliver tangible results without wasting time or resources.

Nancy Bain brings a wealth of experience in AI and project management. As a seasoned professional, she has successfully implemented custom AI solutions across various industries. Connect with Nancy on LinkedIn to learn more about her expertise and innovative approach.

Don't miss this opportunity to elevate your AI projects. Join us on LinkedIn Live, but if you want to hang out with us (the really cool people) and be able to engage and ask questions, please register to join us on Zoom.

Link to Nancy's Gumroad: https://bit.ly/4ci76sr  

About Leveraging AI

If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!

Isar:

Hello, everyone. Welcome to another live episode of the Leveraging AI podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business, and advance your career. We have an amazing. Show for you today, and I'm going to start at the top off this by saying that many people understand that in theory, they can automate stuff in their business using a I, the people went a little deeper. Understand they can build serious automations using GPT's within ChatgPT in order to achieve that. The vast majority of people don't have a clue how to do that. And from those of the people who actually are doing this and creating their own GPTs, most of us, myself included, are winging it. Meaning I know what I need to do. I've had experience and I'm walking through the process, trying to make it work. However, like anything else in business, the right approach to this is to start with strategy. And then develop a process and then go and do the thing that you're trying to do in this particular case, creating automations that really move the needle and are efficient and driving value in your business, which is exactly what we're going to learn how to do today, step by step. By no other than Nancy Bain, who is an absolute guru and AI and business automation ninja. I'm not going to tell you how many years she's been running her business, helping businesses build efficiencies around different things. but she has been running her consultancy company, a supernova media HQ for 20 years. Despite the fact that she's still 25. So, this is going to be a very detailed thought after step by step process. On how you should approach building automations together with GPTs to really move the needle and get stuff done in your business from a strategic approach process perspective. And we're going to dive at the end into the actual implementation and the outcomes that you can gain. So if you're looking to do anything like this, and if you're in any Anywhere in business, you should, this is going to be a fascinating conversation for you. And hence, I'm really honored and excited to welcome Nancy to the show. Nancy, welcome to Leveraging

Nancy:

It's good to be here Isar and I meet you at the intersection of That person that you, that user that you just described. Absolutely. Today, I'm going to show you that, the shortest, most efficient distance between A and B sometimes involves, a methodical framework and strategy to make happen. And so think short term pain for long term gain. And I don't mind saying, yeah, I don't mind saying how long I've been doing this. I've been a bootstrapped solopreneur for over 20 years. So finding the shortest, most efficient distance between A and B is my absolute jam. And, so today I'm excited to share with you one of the tools in my toolbox, the custom GPTs and, how I manage my builds and the. finished product, and including the limitations thereof, which we'll talk about. So I've got, a bunch of screens to share with you. We're going to start off in my presentation and then we'll move over into, my notion build, the backend of, and the backend of, chat QPT. So how's that sound?

Isar:

Sounds amazing. For those of you who are with us live, either on LinkedIn or on the Zoom call. So first of all, thank you so much for joining us and freeing stuff, time on your busy days to actually be with us, here. I'm monitoring both the comments on LinkedIn and the chat on the Zoom. So if you have any questions that you want to ask, if there's anything you want to, contribute to the conversation, feel Please do that. I will add that into the conversation and try to find a time to ask Nancy, whatever questions that you guys have. For those of you who are listening to this only at the recording as the podcast or the YouTube channel or on LinkedIn or Instagram or wherever you're consuming this, come join us. We do this almost every single Thursday at noon Eastern, where you can come and participate in these really amazing conversations with people like Nancy. Nancy, stage is yours. Take us through your amazing process.

Nancy:

Awesome. I'm just going to share my screen here. So as I mentioned today, we're going to talk about custom GPTs. And first question, what are they? in a nutshell, they are personalized versions of a chat GPT. they are designed to streamline our workflow. I have 21 of them. Everything from a 15 minute meal, helper, to a workout buddy, to a schedule optimizer, long form content. they're designed for a, single, singular person. Task and that's important to keep in mind, with regard to their limitations. So let's talk about, some of the use cases. I've mentioned, some of the ones, some of the ways that I'm utilizing, custom GPTs. Today I'm going to be showing you my Gumroad Guide, Manager. the, this, it helps me manage my Gumroad tutorials. I think I've got close to 40 tutorials over there now. And so this saves me, my Gumroad Guide Manager, GPT, that's mouthful, certainly helps me save a, an enormous amount of time in, in managing that. So what are some of the pros? we've already talked about, time saving and, they boost performance and ROI and our, campaigns and they improve my decision making, I love to screenshot. Or download my analytics from Google analytics, from Gumroad, from beehive, into, ChatGPT and have them help me drive, data, data driven decisions. With the, custom GPT, managing expectations is key. Okay. they're not silver bullets, and they're not, A generalist. And with that in mind, I polled, my LinkedIn community and ask them their experience with, custom GPTs. And you can see that, only 10 percent of people are finding that, they're responding perfectly. please keep that in mind, when you're using them people, I've talked a lot about prompting frameworks and, and, the recipe for the perfect prompt, but really nothing replaces iterative prompting in my experience. and the cons to me, No technology is flawless and, and GPT is going to produce content that isn't accurate. one of the things that I wish was different is that they're designed to solely exist within the chat GPT interface. So you can't download them or add them to your site or host them anywhere. And also, when you're measuring, the success of your GPTs, some of those, KPIs aren't quantifiable. So you need to keep that in mind, as well.

Isar:

I want to pause you for just one second about this particular topic. the. Both the pros and the cons and give like my two cents on this. it's a lot about learning how to do it right. And that's what we're going to spend the session doing. Once you finesse the process, it's actually following instructions. I would say 95 percent of the time, when in the beginning, I probably would have answered like most of your audience saying, sometimes it follows instructions and sometimes it doesn't. And so a lot of it is figuring out how to do this, but now I reuse the same structures, again and again, that have proven to work. So that's how I go around that part of the problem, the other part of the problem, and we mentioned that briefly in our, call before this interview, which is, there is a way to actually build a similar process, meaning that they don't call them GPTs, they call them assistants, but it's the same thing, into the API. And if you do that, then you can have access to them anywhere because they're connected to the API. So now you can, you just need some kind of a front end user interface for them, but then they could be on your website. They could be on a chat. They could be a backend for a. Zapier, like whatever it is that you want to do with this, you can use them in a different way. So just, I don't want to open that topic because we can do another whole episode

Nancy:

about that.

Isar:

I would love to do.

Nancy:

Yes, please do another whole episode because. so done.

Isar:

I'm going to, I'm going to hold you accountable for what you just said. I was hoping you're going to say that, but all I'm saying is, people need to know that there is a way to get those GPTs out of the ChatGPT universe and into the rest of the world. It's a little more technical, a little more complicated. We're not going to cover this today, but there's a way to do that.

Nancy:

Exactly. And that's what we offer at Supernova Media is those custom solutions, and then you can involve your clients in their use so they can start to service your clients and you can streamline all of that. And so that's where it's at. And I said earlier, I've got 21, custom GPT and one hell of a personal assistant that was, that, that was created using the API. the, it's not for singular use case either. So let's see. Absolutely. Thank you for that. So I'll look forward to another show on that. so Custom GPTs, there are AI actions within those, you can connect to Zapier, which further connects to 6, 000, other apps and, you can use them for things like lead generation, post purchase follow up. It can automatically update your Google Sheets with sales data, so lots of automations are possible. Not all of my custom GPTs use automations. In fact, the ones that I have that I'm going to show you today do, but not via the custom GPT interface. this represents my custom GPT framework. And it will make more sense, once we go visit, Notion. And let's talk about Notion because Notion is one of my top three loves and it is where I begin all my builds. I honestly don't know how I ever functioned without Notion. I love it for a structured development process and centralized documentation. It's great for collaboration, but When I built it, I didn't realize the last bonus there that I love the most of all it's portable now. I've got all my files, they're beautiful, all in one place. And I recently purchased a subscription to Gemini. And their equivalent to the playground and the API is the studio, their AI studio. now my files, they're beautiful. I'm gonna show you here right now, and I can take them there and I can work with, another LL. So I highly, I, love it for that. And it is funny because this, quote right here is how you began your. Here, talk today. And that is, did you know that the most successful digital marketers are often the ones who master the art of deployment? And with that in mind, I'm going to go show you, over, show you my notion build, for my Gumroad guide, custom GPT. Now

Isar:

I'm gonna, I'm gonna pause you just for one second. For those of you who don't know emotions, sure. It's a universe that kind of combines task management and documentation with all their history and so on, but you can do this either with parallel tools like Monday or ClickUp or Jira or Asana. Or you can just keep a Google doc history that can achieve similar things. I highly recommend using one of the tools that is like Notion. I personally use ClickUp, but it's very similar in the things that it can do. A lot of people use Monday. It's very similar in the things that it can do, but having something like this when you're planning a project. And I think that's where Nancy's process shines. She literally And I'm going to talk a little bit about how we created a very well documented process that she's going to share with us right now on how to create these DPGPT versus, as I mentioned, just winging them. So with that, let's dive into what you have in notion.

Nancy:

Great. Notion has a great free version. I started in the free version and until I brought the team in, the free version worked great for me. and, if there's all kinds of free resources, if, in fact, if you were to go to Gumroad and type in Notion template, free Notion template, Those are great ways to start using Notion by copying a template to your own Notion and using that as a framework for success. And if I told you that I didn't do that here, I'd be lying. One last

Isar:

thing before you dive in, for those of you who don't know Gumroad, Gumroad is like a, you can create your own storefront or marketplace of digital products that you can sell. These could be courses could be training could be Basically, whatever it is that you want to sell so it creates you this storefront marketplace of digital Stuff that you can sell.

Nancy:

And it's wonderful because and I could do another show just on that quite frankly, because Let's just make it the Nancy

Isar:

Bain series

Nancy:

Okay, so back to Notion and one of my you know, top three loves I Here we let's have a look, and we're just going to have an overview of it today. so we start off with our strategy and use case, and you'll see that we've got a problem statement project overview and GPT requirements. Every one of these is linked to in my Google Drive so that I can easily open them refer to them and iterate them. And so this is what my problem statement looks like. The issue, the solution, and the impact. And Chachibti helped me with each one of these documents. I didn't invent this on my own. I just, I went and discussed my goals, with, chat GPT and they helped me to define these documents, why is it important to, to have these documents? Because having a custom GPT is an. It's like prompting. It's an iterative process because the, you're going to launch your custom GPT today and you're going to change it three times in the next 30 days. And so I love, another reason why I love linking to these files and having these files is for version control. And I recommend that you, develop a good system, for naming your files. here's my Google Drive over here and how I've organized my files. In fact, Google Drive is where I began my build in organizing, my files. And so name your files well, keep version control in mind. Again, I

Isar:

just want to add something about what you just said, people like, why do I need all of this? I'm going to do two GPTs. Like, why do I need to start with all of that? And I think the mindset needs to be that you can start developing these automations for hundreds of things in your business. So if you have two GPTs, yeah, no problem. Like you can be messy and whatever, but if you have, if you're planning to build one for every small use case in your business, which over time. We will, and it may not be GPTs, it may be something else, but having it documented as far as what was the goal, what we're trying to achieve, what data we needed to use, like all these kind of things will allow you to continue with new tools that come out, new capabilities that show up, new platforms, new improvements, because everything Is going to be consistent and everything is going to be aligned with these processes that you put in place. Add that to the fact that most companies that are going to do this are not solopreneurs. So whatever, in your head is awesome, but it may not be known by the next person to you or the next department or the next division. And so having this all documented and sitting in a place that makes sense in a structure that makes sense with naming conventions that make sense. Will allow this to scale in an effective way. So I think what you're doing is brilliant as far as looking at the bigger picture in the long term versus Yeah, I can do a GPT like right now,

Nancy:

you can build a custom GPT in five steps and a hook generator. And it could be a damn good one, too. But this framework ensures that if I get hit by a bus tomorrow Someone can come in and take over right where I left off and just and that's important. Back to the specifications and the instructions. These are actual files that are uploaded into the back end of the custom GPT. So we use, Markdown, formula. structure for any of your files that are uploaded to the database, and I've got a guide on that if you want to reach out how to you. I'm a big Google Workspace user. So the guide is how to use Google Docs, to manage your instruction specification files, with Markdown. here we have the training data. everybody's training data is going to look a little bit differently. the important. and the other thing here is that I follow a consistent format, for each of the documents in the training data. This is also using Markdown because these files will be uploaded into the knowledge base. So these, for me and my Gumroads, these represent the different bundles, that I have, of tutorials over there. I alluded to this early in the game, but, model training and updates. It's a thing. and, one thing I haven't mentioned already, especially in model training and down here in performance and analysis. I've got a lot of tasks and reminders, set up. Again, I'm talking far more about Gemini these days because of Google workspace, but, there's, I've been able to automate, that whole process and connect it to my notion to make sure that I'm reminded it's time to go and test, do a thorough test and, possibly some iterating.

Isar:

can you dive a little deeper about the model training segment and what exactly you mean by that? Because this means different things to different people. And some people think that only if you're Google, you can train models, which is not true. So can you explain a little more what you mean by that?

Nancy:

At the very end, I've got the best practices, for that. And I, and basic, do you want them now? No,

Isar:

it can wait through the end as long as you're going to answer that question. Yeah.

Nancy:

And so is training can be as simple as going to the, on the front end of your custom GPT and asking it to perform the functions that you've trained it to do. and documenting any issues, with that makes sense, but

Isar:

I'll give you the best. I will add to that uploading documents, references for it to use is a part of training a model. there's a lot of steps that would be considered training a model that will help you perform the tasks better.

Nancy:

Yeah, and links sharing links. yeah. so this is specific to my build. and I'm constantly analyzing the performance of my gumroad tutorial. So I've got a weekly content review, monthly competitor analysis, and what these link to are prompts, actually, that they're just ready to go. And again, I get a calendar reminder that it's time to do a review of, my Gumroad performance. And then so I'll go copy this prompt and put it into the GPT. I've got a couple of automations, for the custom GPT, but you'll note when we get it to the back end, they're not facilitated by the actions. I've got two, so this, But they're facilitated by a Zapier, but not connected to the custom GPT. So now anytime a Gumroad subscriber, add Gumroad subscribers to my Beehive mailing list, and then, add them to my Gmail contacts. And here I've got a link to my Zaps. and that makes it convenient. Those are the two zaps. If I need to go edit them, they're right there.

Isar:

So I'm going to pause you for just one second. For those of you who don't know, what is that? What Zapier is, Zapier is the glue that connects any software to any software that you're using. And it's a no code automation build platform that anyone with zero experience in, in coding or creating automations can connect to. And transfer data for one app to the other. In this particular case, somebody becomes a client on Gumroad. It knows how to grab the email, first name, last name, whatever information is captured over there and populated in other places. In this particular case, Nancy's email marketing platform, as well as, or just her Google account. So she has them if she wants to send them emails and so on. So you don't have to do these things manually. You can literally connect almost, let's put it this way. If you haven't heard of Zapier before, you can connect any software, to any other software, because they have 6, 000 different connected applications at this point. And so a lot of this stuff can happen. there's two other tools that are like that. One of them is called make, there's more than two, but the two that I use, one of them is Make, which is a little easier to use as far as user friendliness. But doesn't have as many connections and capabilities. And the other end of the scale is N8N, which is an open source, no code automation tool that is amazing, but it's a lot more technical. So if you have the technical skills, it's a great path to go. So that gives you different options.

Nancy:

Thanks for that. And I want, wanted to add that Zapier was really tough, but now they've got the prompt. so you just type in docs to calendar to Gmail and it will design the zap for you. So it certainly made it a lot more user friendly and I'm

Isar:

so

Nancy:

happy to see that because it was top. Now, let's go over to, chat GPT. And, take a look at it in action. Let's go into the back end here. again, I'll

Isar:

pause it just for just one second. First of all, for those not watching this, we are opening the editor for the GPTs for those who don't know even what it is or where it exists. you go into the regular chat GPT. So chat. openai. com, I think, and then. In there on the top left button on the top left bar, there's a button called explore GPT's. And if you click on that, you can see all the GPT's that people are creating. And also on top of that, we will see all of your GPT's. So you can on the top right, create a new one, or you can click on any one of them and look at how it's actually written or if it's, if you're creating a new one. And within there, there's always two options. you can create one, which is basically writing prompts to explain what you're trying to do, which I don't know about Nancy, but that's not what I recommend doing. The other option is to configure, which allows you to actually build it in a more structured way. Either way, you're going to end up on the configure side. I just think the first step is not very. Helpful. So now that I've seen what we're looking at, this is what we're looking at. And now to you Nancy, to go into the details.

Nancy:

And I'm going to echo that, you, I, because I do not recommend the create mode at all. I'll admit, I'm just going to leave it at that.

Isar:

So we're on the same page. I think everybody now should know that's the right way to go is to start with configure.

Nancy:

I go immediately to, the configure mode. So there's just I'm going to give you an overview here. And if you've been peeking, at the screen, those who've been able to look at the screen, you're going to notice right away, that, In the instructions, I'm saying leverage the knowledge base file, and down here, check it against this file. And where's my scroller here? Refer to the knowledge base. many times in my instructions, I am referring to these knowledge based files. And these are the knowledge based files that we looked at over in Gumroad. And these knowledge based files I'll have a consistent format and they're all using, markdown. so that's my biggest complaint with the custom GPTs is that, by the way, that they don't consistently refer to the knowledge base files. Okay. So if you, Here in, in the conversation starters, these are the first four prompts I call them the leader prompts, and you've noticed I've tailored these I've custom tailored these refer to the writing. So any time that I can save a prompt, by saying, I remember, I do it. even in my conversation starters, I'm reminding the bot to refer to the Knowledge base files. You will get the best results by reminding it here. You will save time by including in your prompts to check the knowledge base files here. I want to pause

Isar:

you for just one second for the people who are not watching this. There are four main components, five actually, but the fifth one, I don't know if we're going to touch today of the instructions that you're going to give or what you're going to build into your GPT. One of them is instructions, and this is basically just a very long prompt of what the GPT needs to do. The second part is called conversation starters, and these are basically. You give it to somebody. If you don't have these conversation starters, people don't really know how to use the GPT. So all these are buttons that show up in your GPT, like a button that you can click. And that's going to be the first prompt that you can use, which kind of gives you an idea of What you can do with this GPT, the next component is reference documents. It's called knowledge, and you can upload files to that. And these could be multiple types of files that you can upload. The interesting thing that Nancy said that I never thought about, but the more structured and consistent you make those, the easier it is for the GPT to understand the reference material that you're giving it. So those of you who don't know what Markdown is, and Nancy mentioned that several times, so I'm going to explain Markdown is basically the code behind documents that tells it what's heading one, what's heading two, what's our numbering, what are bullets, what's the subject. Like all these things are called Markdown and you don't have to know anything about it other than create a well defined reference structured document like tell it. This is the title of the document. This is heading 1. This is a heading 1. 1 1. 2 1. 3 heading 2. And if you use that, you are using markdown. And if you do that when the GPT wants to understand the content, it's a lot easier for it to understand because it knows how to read markdown. And so it understands how the document is structured and when to find different kinds of information, which will increase the chances of you getting the correct information. So that's section three and section four is basically what capabilities it needs to have. Does it need to connect to the internet? Does it need to be able to create graphics with Dali and does it need to do any kind of sophisticated math or code writing, and you want to unselect all the ones you don't need because otherwise it's just overhead. And so these are the different components that Nancy's talking about. so far, you covered the main thing, which is create very well structured knowledge and then refer to it. Every time you can, to make sure that GPT actually does.

Nancy:

absolutely. And I will say you can create, your instructions, copy and paste them into chat, GPT, and tell it to, to convert it to mark down. If you have Google workspace, you can open up a doc and create your, instructions, and there's an extension that will change that to markdown formula. So there's some really easy ways to, to structure your data. speaking of, another Structured data. my experience and those that I've spoken to said that, the knowledge base responds better to doc files as opposed to PDF files. So I encourage you to keep, I encourage you to keep that in mind. And I really liked what you said, under the capabilities here of, I've got all three capabilities, ticked, and I mentioned earlier to you about best practices and troubleshooting. if you're, when you're troubleshooting and, I encourage you to deselect any of these that you're not using. and let's talk about token limits while we're here too, because these files, ChatGPT is referencing those files, so I encourage you to start new chats often. And, I like to, I like to have chat GPT summarize the conversation that we were just having. And then I take that summary into a new chat. let's have a look on the front end and see this puppy in, in action.

Isar:

can we, before, before we do that, can you dive a little bit and read some of your instructions so people understand how instructions are structured properly?

Nancy:

Okay, so probably best to do that from here where it's nice and neat and where my problems state in my instructions. So this file here, doesn't have a markdown applied to it. it's a lot to refer to the knowledge base, quite frankly. I specifically refer to each document and I tell the bot what, what each document is. And then I tell it what I expect it to do. With those documents and see the thing with this custom GPT. Is that I really don't want it to think every time I want it to follow my instructions based on what is in the knowledge base I wanted to check my knowledge base and provide answers based on the files on based on what it knows and has learned in my knowledge base. This is a breakdown of the files and what I expect it to do this file changes a lot, and it's, and it should have. a lot of, So yeah, so going

Isar:

back to a few things that you said that I think are critical, this is where having a Google doc or a reference for a Google doc in Notion or anywhere else is extremely valuable compared to just creating the GPT. Because if you want to update it and because you thought of something else, so you want to add a capability or it's not performing as you thought consistently, knowing what was there before. It's not possible in the GPT itself. Once you hit save, it's gone. there's no way to roll back to the previous version. However, if you have that in a Google document, then there's the history. And if what you changed broke it and now it's not working anymore, and you want to roll back to the previous version, your one way to do this is to try to remember and guess what was there before. And the other is to just go to the very well structured process that Nancy's sharing, which means I can go back to Google doc, go to version Six instead of version seven, see what it was, copy, paste it back, hit save. And I'm back up and running. So this is where you start to connect the dots off the process that Nancy was showing originally, where, how everything is, structured to how things are actually executed that we're now going to see live. And I'll say one more thing as far as reference documents This could be anything right? This could be a chat bot on how to for HR, right? How do I get another PTO? How do I apply for a maternity leave? when do I know when is my salary going to go up next time? Like all these questions that people ask HR all the time could be a simple chatbot. And all you have to do is upload your employee guidebook. And if you have other reference materials, then upload all of those. If there's any industry related specific, you can upload all these documents, and then people can ask these questions. And again, the three, four, five buttons you want to create are the questions that get asked the most. So people literally just click the button and they're going to get the answer. And the only way to do this is to have these documents referenced. And then in the instruction say, only answer based on this document, if this is the kind of question that you're getting.

Nancy:

Exactly. You got it. Exactly. So let's watch it work. So again, I've reminded it refer to my writing style, and I didn't point that out in my Gumroad guide command center there over on that notion that I have established my writing style in the form of a document and it is one of the training documents for the module, for the GPT. so it's asking me to upload the tutorial. I do want to point out that I downsized, I reduced the size of all my tutorials before I upload them. To GPT, I have Adobe Acrobat Pro. I don't know what's out there for a free version of that, but I do encourage you to size your documents before you upload them. And already for me, it's a fail because of unlock the power. but this, but it's done a really good job actually. Because look how the important thing is, look how close that I am, I got to move. Can you see that? Like, all right. It's so annoying. There we go. Yeah, we can see that. So

Isar:

if you'll scroll up just to explain what it's doing, it's taking a PDF and creating a very concise PDF summary of what's in the PDF. So if you want to have a product that you're selling, that is a digital product, you need to have a description on your website. By the way, this doesn't have to be a digital product. This could be anything that you're selling. So there could be a very long description and you want to make it concise. And this thing has a summary and overview objectives. What you're gonna gain, like all these things. Very well done all written by this GPT based on the long PDF that actually explains the whole thing.

Nancy:

So exactly. So what I did was I uploaded one of my tutorials and I don't get chat GPT to help me write my tutorials. that is what I help. They helped me with so many things, when you're, my tutorials are step by step. I don't. I do that by myself. So what I've done is I've uploaded one of my tutorials and I've got my, my optimized prompt, I call it, because this is like a couple of prompts and one and a reminder to check the knowledge base file and a reminder to ask me to upload. So I've saved a few keystrokes I'm sure just by optimizing my prompt. And it has followed my if you were to see the instructions and read them clearly, it has followed it to the letter, unlock the power it that's all I've got to change. I have a personal aversion to phrase phrases like that. But I must say that most of my readers. are not immersed in it like I am. So they're still excited by unlock the power. yeah. so I've asked for it to provide me with a description with a summary and I told it, I wanted bullet points and benefits. Who's this for? It's followed the format. Absolutely. Exactly. And I've even asked it. I've, one of the knowledge based files was a call to action because I get sick of. Typing out my links all the time so I can over in Gumroad. So these are all live and ready to go. And I take a look at this and I, if I spent less than probably five minutes editing that before it's ready to go over on gumroad. So that is, I want to touch

Isar:

on something very important to what you just said, because people who are new to this saying, Oh my God, this is so much work. Like I got to build a thing in Notion. I got to write the documents in Google Docs and keep their history. Then I got to go to GPT. I got to build the GPTs. I got to test the GPTs. I could have just written the damn instructions, which is

Nancy:

25

Isar:

minutes instead of five minutes, but creating all this GPT. It's taking me three hours. Now the reality is that is true the first time. The second time you do this, now you, every time you want to create a new one of those, it takes you five minutes and sometimes 30 seconds if it's perfect the first time out. And if it takes you 30 seconds to five minutes to do a work that usually takes you 25 minutes and it's something you do several times a week, in week three. You're already in positive ROI on investing those three hours of putting this GPT together. So don't build GPTs for something you do once in a blue moon, but if it's something that you do regularly. Either in your personal life or in your professional life, a repetitive, tedious task. You can stop doing it almost completely by creating a GPT that does it for you. This could be summarizing meetings in a specific format. This could be writing a financial summary based on a specific format. This could be Doing your HR reports in a specific, like each and every one of those things that goes across departments, because everybody in business has the tedious stuff that just need to do that takes X amount of time or they're weak. All of that can go away. If you develop a GPT that does it. And if you do it. In a well structured way, you'll be able to continuously improve on it and fix it as things change and improve and move forward in this whole automation universe.

Nancy:

A hundred percent. You nailed it. Yeah, I love my custom GPTs and I just, I looked at my week, my and my month and I, my Trello and my calendar and I know where my time was being spent and then I built a solution. For, each pain point and, Gumroad was one of them. So this is absolutely streamlined, the process for me. And I'll always write my own tutorials. So I'm not going to streamline that process. One, another thing that I do and another one of my, conversation starters is I do upload my guide once I've completed it and ask for feedback. And and yeah, so that is it. Now you have it. The framework for success.

Isar:

This is awesome. I want to, now that we talked about how to start the process, how to build it strategically, how to create it in a way that is scalable and how to create the GPTs and how they work, there's a, there's an interesting question from the audience that came in the beginning, but I'm like, okay, let's start crawling and then walking. And then I can ask the running question. one of the running question is, do you combine GPTs with Zapier in any way? Do you bring GPT into Zapier or do you use a Zapier, API as a schema within, GPT in order to even enhance this?

Nancy:

Yes, and I've done that for the first, GPTI ever built, was called PI Pilot, and it is, it takes you on a guided. Python course. for absolute beginners. And this was a challenging build because it's similar to the Gumroad, guide build, and that I didn't want it to think. I wanted every user to have the exact same experience. I did not want it to deviate from the script. And so that was a challenge in and of itself. And then I used Zapier to collect leads. It was the one and only GPT I published to the store. It got copied six times. On the first day, and I said I'd never publish another one to the GP store ever again. And so I've used it to collect leads from everything. Do you want a more intense course. And I gathered their email address and I even used it to, buy me a coffee link. so there's some lots of clever ways, that you can use Zapier for sure.

Isar:

So how do you do that? What's the practicality process? How do you connect Zapier to a GPT?

Nancy:

just exactly like you said by a API. And, so there's, yeah, I've got a tutorial on that step by step. So

Isar:

I'll explain on a very high level. And those of you who want, so something we'll do for all of the questions, people like, Oh, I would love to have that. I like, can I get this tutorial? All these tutorials are available on Nancy's Gumroad. website. So I will share a link to that in the show notes, both on the YouTube channel, as well as on the, on the podcast show notes. So it's going to be available for you to get all of these instructions. But in general, for those of you who don't know what schema means, APIs are the language in which one software can talk to another software and a schema basically defines the language. How they're going to connect. Now, that sounds really complicated, but the reality is, if you will just Google, I need the schema for Zapier to put into a GPT in order to connect Zapier. To do that, you will get a piece of code that means absolutely nothing to you, but all you need to do is copy, paste it on the very bottom part of the GPTs. There's a section to put in the schema. You hit save. And it's going to magically work. And I do now more and more of that kind of stuff where I would sometimes even take that code that I know exactly. I don't have a clue what it means and I will put it into chat GPT or Claude or Gemini say, Hey, I want to add this to that. Here's the documentation of the API. So I don't know what the documentation means and I don't know what the schema means, but I'm asking it to. On its own, figure out something from the documentation and ask it and add it to the schema. So now the API can do one more thing and it will write a new code. And then you copy that code and you paste it. And 80 percent of the time it works the first time around. And then if it doesn't, you're like, okay, I'm getting this error message. What do I need to change? And then you go, Oh, okay. Here's another piece of code that's going to fix this error. And you just go back and forth two or three times and that's it. Once you have it working. So going back to the Zapier thing, then you can do a lot smarter stuff because you can literally call a zap, a specific zap that's already pre created. You can call it from the GPT. So the GPT, the automation within the chat, GPT universe. Can now connect to any thing that Zapier is connected to. So if you want to update Excel files, you want to update your CRM, you want to grab information from your ERP, you want to get a document, like literally anything you can imagine from your tech stack can now become available to the GPT and then report it back from the GPT back to Zapier to connect to other platforms. So this is a really. And advanced use case, but it's an advanced use case that with I'll go very extreme an hour of watching YouTube videos, you can figure out how to do. And once you know how to do this, you can create really serious magic.

Nancy:

And it's probably not going to work the first time, but it's probably not going to work. And as I mentioned, if it's.

Isar:

No, go ahead. Sorry.

Nancy:

the way that you described it, I could see you building it with your own hands and going through the exact same things that I've gone through. 100%. The same steps. Exactly. I share. I share guides on, again, back to Google Workspace on how to build scripts, to automate key processes for bootstrap solopreneurs that just makes a huge difference in your life and people will say, Oh my gosh, code. code that was a prompt to, to chat GPT that I copied and pasted and, and now look, so don't be afraid anymore when it says code, there's too many solutions out there to help you overcome that.

Isar:

Phenomenal. Nancy, this was fascinating. I think your process is absolutely brilliant. I think it covers. So many very important aspects that even people who are advanced users, myself included, are not thinking of like the whole structure, putting a processing notion or whatever tool you're using, having your whole history of the GPTs within a document that has a history, like all of those things are things I'm not doing, and I'm sure 90% 5 percent of people are creating. These are not doing, and those people are probably less than 1 percent of the entire population of the world today. So if you feel that this was like, Oh my God, this sounds really complicated, but you are still here to listen to it, to figure out how to do this, you are in the top 1 percent in the world. And if you invest a little more. hint, go and get the tutorials from Nancy road's website on how to exactly do each and every one of those things. you'll be able to do it yourself. And then it opens a whole universe of automations that you can create for your business. Nancy, this was awesome. If people want to follow you, work with you, access to your gumroad stuff, what are the best ways to do that?

Nancy:

you can visit my website at supernova media. ca. Or you can find me on LinkedIn. I hang out there on the daily. it's easy to reach me there, as well. and I share lots of good stuff there. if you're there to learn, especially about AI, I rec, I recommend you follow me.

Isar:

Awesome. I recommend that too. Thank you very much for everybody who joined us on LinkedIn, there were a bunch of people, lots of great engagement over there. Thank you for all the people who joined us on the zoom call. I appreciate you, joining us as well. And obviously, thank you so much, Nancy, for prepping all of this. I know this doesn't come out of thin air. You invest a lot of time in creating this. So thank you for much so much for sharing it with us, for sharing it with the entire audience. And I'm sure we'll be in touch. We'll do some more of these diving into additional topics. Thank you. Thank you. Thank you.

People on this episode