Leveraging AI

244 | Custom GPT vs. Projects: The Amazing Automation Tools I Use To Run My Business - And You Can Too with Isar Meitis

• Isar Meitis • Season 1 • Episode 244

Share episode

Learn more about Advance Course (Master the Art of End-to-End AI Automation): https://multiplai.ai/advance-course/

Learn more about AI Business Transformation Course: https://multiplai.ai/ai-course/

Most business leaders are dabbling with ChatGPT and Claude, but very few are leveraging the right tools in the right way. The confusion between Custom GPTs and Projects could be silently costing you time, money, and momentum.

In this solo deep-dive, host Isar Meitis breaks down the exact differences between Custom GPTs and Projects (in both ChatGPT and Claude), and shares real-life automations that have saved him and his clients hours per week — with no coding required.

From sales automation to social media hooks to instant proposal writing, you’ll learn what works, what doesn’t, and how to implement powerful AI tools that actually do the job for you.

In this session, you'll discover:

  • How to choose between Custom GPTs and Projects for your business
  • Real examples of AI automations that cut hours off daily operations
  • A step-by-step walkthrough of building and deploying GPT automations
  • The key differences between ChatGPT Projects and Claude Projects
  • How to organize persistent memory, files, and workflows for smarter AI collaboration
  • When you shouldn’t use Custom GPTs (and what to do instead)
  • Why the newest update to Projects just made them a game-changer

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!

GMT20251124-180014_Recording_avo_1280x720-1:

Hello and welcome to the Leveraging AI Podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business, and advance your career. This Isar Metis, your host, and we have a really interesting episode and. I have a really interesting episode for you today. There is a relatively big confusion between different tools that chat GPT provides to all of us basically right now. And what I mean specifically is the difference between custom GPTs and projects. Now, if you use one. Or the other, or maybe a little bit of both, or definitely if you haven't used any of them, you'll find significant value in this episode and you will learn how to actually implement them effectively. You'll learn how to pick the right one for your project and even how to. Create specific automations that you can use in your business and areas of expertise that you can use in your business in order to make the most out of chat GPT. We're also going to touch a little bit about the differences between that and how to use projects in Claude and some minor differences between this and that. So if you want to understand how to use ChatGPT projects or custom GPT or cloud projects in the most effective way, how to develop them correctly and what the hell are the differences between them? this episode is for you. Before we dive into explaining all the differences and so on, I want you to understand what are the options, like what the hell can you do with these tools? And so I'm going to show you different examples of automations as well as different other ways to use projects. And then you at least have an understanding of what are they good for, and then we can talk about the differences and how to pick the right ones and how to implement them. Let's start with an example of how you can use, in this particular case, a custom GPT to do data analysis across several different files. What I'm going to show you right now is a really interesting automation process that actually takes two separate files. This process was built on a real process that I've done for a client. But using fake data and what this process does is actually extremely helpful. So they sell across multiple different channels. They get an updated levels of inventory from all these different channels and every single day they have to combine all that information and then compare it to the sales data and then based on the new levels of inventory, they need to create a new updated sales brief that goes to their salespeople. So the salespeople know what to sell more, what to sell less, what is inventory they ran out of, and they need to stop selling whatsoever what they have a lot of, and they need to run promotions and so on. This process used to take them several different hours every single day. And then we've built on automation routed using a simple custom GPT. So the inputs to this custom GPT are just two files. One is yesterday's sales briefing, and the other is today's updated inventory information after it was compiled from all the different sources. And what you'll be able to see is that this GPT now will run four or five different steps, all its own, each and every one of them. Highly detailed by comparing columns and rows and cross-referencing data from both files. And it is just going to read the files and then start doing. So say, did step one and now it's going into step two, and it's gonna analyze step two. And you can see in each step exactly what it's going to be doing. So it's gonna pull the material from one file compared to styles in the other file. And then considering all the roles matching to description, it's doing a lot of highly detailed work. And now it's going to step three, each and every one of these steps used to take humans. Multiple minutes and sometimes the combined effort would've taken, as I mentioned, two to three hours. And now here we are and we're done. So you see now I have a download, updated inventory, uh, file that I can click well check it first and then send it to my sales team immediately. So this took about. Three minutes of me talking, meaning I could have done an email or something if this was my actual work, and I've got the file that previously used to take hours to do by cross-referencing two different files in two different formats with different namings and so on, and yet it knows how to do this effectively every single time. Let's look at a completely different example. In this example, I will show you a automation process that writes hooks for my posts. So how does that work? Well, initially, my team has collected multiple hooks from many different sources on the internet. Ones that work and drove a lot of engagements. And now all I have to do is drop a post into it and it knows how to do that, and it knows how to find relevant hooks that I can use and recommend them to me, and I can pick the one that I think makes the most amount of sense. So let's take an example. Let's go to LinkedIn. Let's pick anybody's post. It doesn't really matter. I'm picking out a post and I'm picking it without the hook line from the beginning, and then I'm gonna drop it into. In this particular case, custom GPT. Then I'm gonna click go again, no instructions, no nothing. And then the tool itself will go through multiple different options, uh, of hooks and it will find the ones that probably will work best for this post. So you can see now it gives me, uh, three different options option. Hook template number 14, story category, how I went from X to Y, so this is the template, and then the way it's suggesting to use it is how I went from 12 views on my first LinkedIn post to speaking at a HubSpot event alongside the CEO of a$2.1 billion company. That is not bad. Definitely a hook. I will probably click to see what the rest of it hook. And then it gives you another hook option. Most people think X, but actually Y. So this is the template. And again, the recommendation is most people think your first version needs to be perfect, but actually your worst work is the data that gets you to your best. So I think the previous one is better, and then it give me another one, and I can ask for as many more as I want, and then I can pick the one I want to use. Or at least get ideas and then I can write my own, or I sometimes combine some of them together into one hook. So this is, again, something that just helps me be more creative and follow templates that have been successful for other people. I'll show you one more example that I use all the time, and that saves me hours. Every single week. I get approached regularly, so probably several different calls per week to provide AI workshops to companies. And these always work the same way where I have an initial. Call with usually a senior person, the CEO or the COO or somebody like that, or somebody from l and d that is asking me about my services. And sometimes it's follow up with another call with somebody more senior on another person that can weigh in on how the training should go, and then a few emails go back and forth. And then they're asking for a proposal. So either one call or several. And then I need to write a proposal, and this used to take me writing the proposals about two hours per proposal. And now what I do is I actually have a very simple process where I take the transcriptions of the calls from Fathom, which is a tool I use that listens to all my calls, re regard whether they're on Zoom or Teams or uh, Google Meet. And then I drop that into this custom GPT or project and it writes the proposal for me. So a process again that used to take me about two hours now it takes the AI about five minutes, takes me another 10 minutes to review it, correct what I need to correct, drop it into my header and footer in a regular document and then send it over. So a huge savings of time, especially that I'm doing two to three of those every single week. That gives you an idea of how much time I'm saving just with that one automation. So these are the things you can do with it when it comes to automations, but actually projects can be used for a lot more than that. So now let's take a look at projects for a second and see exactly how that looks like. So where do projects live inside of ChatGPT and how exactly can you use it? Well, it lives on the left side menu, the top thing you all. Every one of you has, it says New G. It says New chat, search, chats, library, and so on. And then underneath that you have projects. And projects can be used in two different ways. One is in similar ways to custom gpt. Again, we'll discuss exactly what that means, but the other way is as a space to have relevant context for a specific task. So what you can see here is you can see that I'm looking right now at a project that is called Sample Client Project. The reason I have it is I don't necessarily wanna share what I'm doing, these demos, how I'm actually working with each and every one of my clients. But how am I actually using it is really important and not necessarily the details of a specific client. In general, all these AI tools are thriving on context. The more context they have, the better results you are going to get. Which means if you want to get great results when you're talking to a specific client, you need to tell ChatGPT or Claude or Gemini or gr. Doesn't matter which tool you use. Everything you know about. The client, the project, the people you're working with, the specific proposal, the everything that you want, which just takes a lot of time and it's obviously not very effective doing this. Every single chat that you have, and this is exactly one of the things projects are very good at. You can provide the chat. With background information, context of the specific client or on the specific project or on the specific topic you are working on regularly. For me, as an example, I do AI courses. I have this podcast, I have a YouTube channel, so each and every one of them has its own. Project. So what is in the project? The project has a combination of two different things. One is files or knowledge base in the language of custom gps. So what could be these files? Well, they could be everything. If I just want to have a. Project about a client that I'm working with. I will have something like this. So I have information about the culture of this client as a document. How do I know that? Well, first of all, I go to their website and I see what they write about themselves, but then I take, uh. Additional stuff that I know about them, and I add it to that document and I upload that as a document. I have different proposals that I've written for them, so you can see a course proposal and a workshop proposal. You also have a consultation agreement that I have with them in here, and people document what's in the people document. I will create a deep research project and I'll ask it to research the top people that I'm working in, the company and the decision makers. Then I will go to LinkedIn and I will pull some additional information from there. And then I have a segment in this document about each interview people that I'm working with as well as hire decision makers in the company if they're not the people that I'm talking to. And I upload that as well. And then about us. So I'm literally taking the about us page from their website combined with deep research about the company, saving it as a document and uploading that as a document about this client. So. What happens now is if I am opening a new conversation here, different than a regular conversation in ChatGPT, this conversation under projects already knows all of that information. And so instead of giving me vanilla answers, it knows everything there is in here, including. Projects, including proposals, including work we've done before, including emails. If they're important, I will include them in here about the company and so on. And hence, the answers that I'm getting are specifically for this company are related to the work we've done with them and so on. So extremely helpful. But in addition to just the files, it also has instructions. So if you go to the, the ellipses, the three dots on the top right corner in projects. You can see that I have a segment. Uh, I have a button called edit instructions. If you click on edit instructions, you can see it has instructions and you can see that this one says Comprehensive AI Strategy Development for client. And then I have different objectives and how to work with it and what are the benefits and what are the pros and cons and how I want it to respond and so on. And so the way it is going to answer is very, very different than the way just a regular chat is going to answer because it's custom tailored for this client and for the kind of work I wanna do with this client and the way I want to communicate with GPT about this client. This is a complete game changer compared to using just a regular conversation with chat GPT Now, because you can create these smaller bubbles of context. Each and every one of them can be specific just to that topic, which again, could be a client, could be a project, could be something that you're working on regularly, et cetera. So this is one way to use projects. But before we dive into the other way to use projects, I wanna show you what our custom GPT is, because that will help you understand how you can use projects as well. So custom GPTs are these mini automations that can do one thing again and again, just like I showed you before, either find a hook or create proposals or anything else that is a repetitive task in your company, whether they live. They live down here on the left menu of chat, GPT, where it says gpt, and underneath that it will say Explore and then it will show you a few of your gpt if you don't see all of them. Then if you click on explore on the top right corner of the screen, you will see my gpt. And when you click on that, you're gonna get a list of all your gpt. I have about a third of them or maybe more so. Let's look at the one that generated the hooks for us before. So if I click on that, uh, if I, on the top left corner, it says post hook generator, and it has a little dropdown menu, and if I click on that, I can click on edit and then we can see the structure of how this works. So in this particular setup, what you see is once we get into a custom GPT, you can see it has a name, which it just tells you what it is. Then it has a description which tells you in more detail what it is, and then it has instructions. And in this case, the instructions are really, really short. You're an expert copyright who specializes in writing hooks for LinkedIn post. I want you to write three hooks for any LinkedIn post that I provide. One, please refer to the hooks from the Resource 750 plus Hooks. Two. Select three hooks, templates that work. Three, please include the Hook template and the number four, use the templates from the resource two, craft a Suitable Hooks. That's it. Really short, but really powerful. So how does it know where to pull the hooks from? Well, down here it has what's called knowledge base. And in the knowledge base you can upload files in one of the files. Up. Up I've uploaded has a document that has over 750 hooks with examples on how to use them. Now the other thing you have is you have. Conversation starters, what are conversation starters? They add buttons on the custom GPT. These buttons can be used as one of two things, either as to give somebody an idea of what they need to do. So in this particular case, you see it says, input your LinkedIn post. So I know what to do. Otherwise there's no way for me to know. So if I'm gonna share this with somebody, they may or may not know what to do with this custom GPD. But the other thing that you can use it for is you can create several of these conversation starters, and then in the instructions refer to each and every one of them separately, which means you can allow the user to. Start with a different kind of data or a different kind of source, or a different kind of starting point that based on the button that they have clicked, which just makes it more versatile. So these are the capabilities inside a custom GPT. And as you've seen. All you have to do is upload something and get the output, because it already has the instructions. You don't need to tell it what you want it to do, and you will do the instructions time and time again. If you wanna dive deeper into how these things work and how to develop them. Uh, there's a separate episode that we've done about it. So if you go back to episode 1 75, it was called Stop Wasting Time, automate Repetitive Tasks with Custom gpt. You'll get a little more information that we're sharing today, even though I'm gonna try to share a lot of it with you today as well, even though today's episode is more about to compare that with projects and how to choose the right solution for you. Now down here on the bottom, you have two more things. Inside the setup of custom gpt, you have the capabilities that you wanted to include, and that includes web search canvas. Image generation and code interpreter in data analysis and just pick the ones you actually need in the custom GPT versus everything. And then on the bottom, on the very bottom, you have create new action. What are actions? Actions are the ability for the custom GPT to actually run code and connect to other things in your tech stack. So. That means if you have other tools or databases and you wanna be able to either query the databases or connect through an API to third party tools, you can do that inside a custom GPT, which makes it even more powerful because now it can query your CRM, your ERP, your email marketing platform and so on, and work with it in tandem to give you the results that you want versus. You having to export data, copy, paste it into the custom GPT and so on. Now, if you don't know how to write code, then there's a little button here that says Get help from action GPT. That uses another. Custom GPT that OpenAI created to write code for you to put it in here, for it to connect with third party tools. Most people, and in most cases, that is not necessary, but it is a huge benefit if it's something that you need or want to do. So these are custom gpt now on a very high level, these two things, projects and custom gpt have very similar concepts, meaning they have a knowledge base of files that you can upload, and they have instructions that they know how to follow in order to deliver specific kind of outcomes. So let's dive a little deeper into what are the differences between projects and custom gpt. That will give you a hint on which one you need to pick for different use cases, and I will give you an idea. As of right now, there's a very clear winner that you should pick probably 95% of the time. So let's start with the purpose. Is there a difference in purpose between custom gpt and projects? And the answer is, it depends. Custom gpt are built to be a repetitive task creator. Basically, if you have a. Single task that you wanna repeat again and again and again, then Custom GPT will do that. Projects can also do that, but in addition, they can be used as a way to have conversations about a specific topic, meaning it's an entire workspace that can use similar kind of information for two different goals. One is to run an automation that has to run exactly the same way. Or to have open-ended conversations about the same background information. Now, to be fair, in most cases I create two different projects for these two different tasks. One of them would be to create very specific instructions that will repeat a task again and again and again and the other type of project will be a. And the other type of project will be just a data source for open-ended conversations with a context about this particular topic. But in general, custom GPTs are a one trick pony. They will repeat the task that you give them, and projects can do that plus allow you to have open-ended conversations. The next topic is knowledge base or files that you can upload that is very similar on both tools, so both on custom GPT and projects. You can upload PDFs, word document, excels images, et cetera, and that is very similar on both sides. The file limit is. Also very much the same. There's slight differences depending on the level of license that you are using. But in general, on the plus level, which most people are using, you get 20 files of five, 112 megabytes. Each with 20 megabytes maximum per images, and as far as the number of files that you're getting in the projects that goes up if you have the higher level plans. But usually the 20 files is more than enough for what you need. Now here is where it gets interesting. The next thing we're going to compare is how can you share them with others? so custom GPS can be shared in several different. The very basic is just you. You are not sharing it, and you're just using the custom GPT that you created. Option two, you can share it with anyone with the link. Option three, you can share it if you have the enterprise level with other people from your company. And option four, you can share it with what's called the GPT store, which means anybody who has access to chat, GPT can use your custom GPT on projects. Until not too long ago, you could not share it at all. Which was the biggest and more or less only disadvantage of using project that changed back in September for people with enterprise level licenses, and it changed for everyone in October. As of last month, now you can share projects just by giving people the link and they can work inside the same projects with you, which is a huge benefit, and again, was the only real serious disadvantage of projects before. So that was a big advantage of custom gpt that is no longer an advantage. And now let's talk about the two biggest advantages of projects over custom GPT. Biggest benefit number one is persistent memory. So custom GPT is every time you run the custom GPT, it runs and it's done. It doesn't know what happened the previous times you run the same custom GPT. However, projects, as I mentioned, were originally built not to do automations, but actually they were built in order to be a context space, a bubble of context for a specific topic, and they have their own memory feature. So just like there is a memory feature for ChatGPT as a whole. There is a memory feature just for the project, so every new chat within that space adds more context to the overall knowledge, experience, and capability to be more precise with the answers of that project, which does not exist in a custom GPT, which means it's a huge benefit and a lot more value. Two projects versus custom gps because it learns from every conversation that you or other people who use the same project are having within the project. So this is huge benefit number one. Benefit number two is the organization of the chats. If you use a custom GPT, every time you use it, it creates a new regular chat. Inside of chat GPT. I will show you an example so you understand what I mean. As an example, you can see here customized proposal as one of the regular chats that I had. It says Your chats and it was done. With the custom GPT, meaning every time I run the custom GPT, it actually creates a completely regular chat as part of the very, very long list of hundreds of thousands of chats that I have done with chat GPT in the last three years. However, if I create the same proposal inside the proposal generation project. You can see that it shows up every single time I ran it inside just this proposal folder, meaning it is a lot easier for me to find conversations that was done, that are relevant to a specific topic that I am looking at right now. So. Both from the perspective of learning from every single chat, as well as from the perspective of having it a lot better organized in one place, running automations, and definitely the other option of just having open conversations because that's something you cannot even do inside a chat. GPT is a added value of a project. Now let's talk about two advantages of custom gpt that do not exist on the project side. Number one, it is the ability to create code that will connect to third party tools such as your C-R-M-E-R-P. Et cetera. And as I mentioned, that exists on the bottom of the custom GPT. It requires writing code that you can use AI to help you write, but it means you need to be a little more technical. And to be fair, I have about 30 plus custom gps that I use and. One or two of them actually is using this capability to write code. That capability does not exist inside of projects. So if you need that, then custom GPEs are your only option. And then the second thing is conversation starters. We talked about this, that you can create these buttons. Inside of a custom GPT that will explain what to do, or that can start at a different starting point. Inside of the custom GPT. This does not exist in projects at least yet. So what does that mean? It means that for the vast majority of use cases. Projects are right now a better option than custom gpt. Meaning if you have old custom gpt, there's no reason to go and convert them because there's no point. However, if you want to create new automations or new workspaces for you and your team to work on a specific topic, either through an automation or as a context baseline for open-ended conversations, just create projects. There's really no reason. To create custom GPEs right now, unless you wanna connect it with code to something else. Now, I want to give you a few more hints on how to create these automations, whether you're creating them in projects. Or in a custom GPTI always start with a regular chat. I don't actually start trying to figure out what needs to be the instructions. I bring it the data. So every time I create an automation, there's really three components, right? There's the input, the process, and the output. So I need to have a clear understanding of what the input is. So I bring in the input, I clean the data in the input. So the data needs to be very well organized. If it's in Excel, then it needs to be set up correctly without any double headers, without any spaces, without any merged cells and stuff like that. So I clean the data, I bring it into the chat, and then in the regular chat, not inside trying to build an automation, I try to get. To define the process in order to get the outcome, and I just iterate. I ask it, oh, I need to do this and that, and then it gives me an opposite. Oh, it's not what I meant. Let's try this. Let's try that. Until I get to the final output, the way I want it, once I get to the required outcome in the format I wanted, in the length I wanted, with the details that I wanted, I ask it to write instructions. For a repetitive custom GPT that will do the entire correct process and avoid the mistakes that we've done in the regular chat. It writes amazing instructions. Way better than I can write, and most likely better than you can write on your own and it will capture all the nuance. You can ask it to ask you questions if there's any open things it's not sure about, and then it will write the instructions for you. You just copy and paste the instructions into the instructions section, either in the custom GPT or in the project. You also tell it what kind of reference material or knowledge base you will give it, and ask it to include that or reference for that in its instructions. And then add those files into the knowledge base inside of the custom GPT or the files inside of the project. So now you have everything you need in order to run these automations. And you can also use it if you created a project, which again would be my recommendation. You can also have open-ended conversations based on the information that is in the files and in the instructions. And as we mentioned, if it is a project, it will also learn over time and get better over time. So now that you know that projects is probably the way to go for most of your use cases, there's a very similar concept in Claude also called projects. So what are projects in Claude and how they are different from projects inside of a custom GPT? Well, not by much actually, projects in Claude was there before projects in custom gpt and OpenAI, more or less copied the concept of projects from Claude. This is why OpenAI currently has two different features that are very, very similar because OpenAI started with custom gpt. Then Claude created projects, which was broader and more capable, and then OpenAI copied it and provided projects inside of Chat GPT, which was not my recommendation until a month ago, where now you can actually share them with other users, making them a lot more powerful and relevant to most people than custom GPTs. But let's talk about what are the differences between cloud projects and chat GPT projects? So I already showed you how ChatGPT projects look like. Let's go to Claude and see that it's more or less identical. So if I'm in Claude over here, there's like a little folder icon on the left, and if I click on that, it takes me to projects and very similar, I can create a new project. But if you click on a project, you will see that it has a memory, that it remembers stuff about you, it has instructions, and it has files In this particular case. Uh, you can see that it has, 10 different files and it has a set of instructions that tell it exactly how to work and same kind of thing. This is a proposal generator and all I have to do is drop in whatever the it is looking for, and you will know how to run this automation. But I can also have open-ended conversations about this. Topic, which is AV proposal generation in this particular case, and it can give me ideas on how to write better proposals and what kind of proposal am I writing and maybe a new different kind of structure, or how should we approach a specific client and so on and so forth. Because it has all the information about previous proposals that I have written. But there are still some differences between cloud projects and chat GPT projects and let's review them quickly. Claude in general is much better as of right now, so Claude 4.5 compared to ChatGPT 5.1, Claude is much better in formatting. The documents that it's generating and the Excels that is generating is significantly better looking and well organized than what ChatGPT does right now, which is a huge benefit, especially if you are also using skills. I'm not going to dive into skills right now. I'm gonna do a complete separate episodes about skills. But skills are these mini capabilities that you can create inside of Claude that knows how to do very specific things. As an example, I have created a Claude scale that creates everything to my brand when I ask it to do. So, it has my color coding, the tone that I like to use, examples of how I write different things. It has my logo, it has my entire brand guidelines and it knows how to apply it very, very well when it is creating new documents. So the combination of that with instructions means I have to do less work afterwards to format it as I need. The disadvantage of that and the advantage of ChatGPT is that in both cases, when you create it in ChatGPT, it creates it in Canvas if you ask it, which means it's an editable work collaboration document together with the ai, meaning, you can create manual changes to the output from ChatGPT versus in Claude it looks better, but you cannot make any edits. Meaning if you wanna make edits, you have to copy this into a Google Doc or a Word document in order to make these changes. And in ChatGPT, you can make edits. On your own, combine it with the work together with ai, that I find a lot more helpful than using artifacts, which is the Claude version. So what does that mean? It means that right now I am using ChatGPT more than I am using Claude because of that particular reason I have. Multiple times taking the output from ChatGPT, dropped it into Claude to get the formatting done much better. And then I have less work in the manual editing afterwards when it comes to just making it look nice. So final summary of all of that custom gpt are really good to create a specific automation that just repeats itself again and again and again. But you can do the same thing in a project, whether a charge GPT project or a Claude project, the. Projects also allow you to have an open ended conversation about the topic that it has in its instructions and knowledge base, which provides another benefit. It has memory that helps it learn from one chat to the other. And it keeps all the conversations of that topic in a single place that they're easier to find. So overall projects right now are winning over custom gpt. I will say one more thing that I've noticed because I'm working in both environments and when you're running projects in a lot more cases and you, when you drop in the input, it will actually gonna ask you questions, clarification questions that it never actually asks me. Custom gpt that is good and bad. It is good because it is verifying information that it is not sure about on how to execute the task. It is bad because sometimes I just wanted to do the task, uh, and. And so that's another small difference, which is a nuance. I think that in most cases, I prefer when it's asking me these questions, when it's running the project, because it helps me clarify things that the AI is not certain about. That is it for today. If you haven't used this functionality, this can change your life. Literally, every single process that I have in my company is run through either projects or these custom GPTs, and it saves me hours and hours and hours every single week between myself and my team. And without it, I probably would not be able to do all the things that I'm doing right now. So if you haven't created those. Go and experiment with them. You can try to do both. See where you're getting better results. In most cases, it'll be very similar if you follow the process that I explained earlier in this episode, and I would love to hear your feedback about this after you tested out. So look me up on LinkedIn, ISAR Metis, and send me a message. Say, Hey, I tried projects and I tried custom gpt and here's what I found. I would really appreciate that. If you are enjoying this podcast, please. Give us a review on Apple Podcast or Spotify, and while you're opening your phone right now to do that and thank you for doing this. Click the share button and share the podcast with a few people that can benefit from this podcast. I'm sure you know a few and I would really appreciate it. They would probably appreciate it as well, so everybody wins. Keep on experimenting with ai, keep on sharing with the world what you are learning, and have an amazing rest of your week.

Head Shot

Isar Meitis

Host