NEW 1-Click GPT-5 AI Agents are INSANE! 🤯

Today we are going to be building out some AI agents using GPT5. Right? So this API it literally just came out and you can build quite easily NA10 AI agents and I'm going to show you exactly how to do that today. Right? So what

we're going to do first of all is we're going to go to A10. You can just grab the instructions from the AI profit boardroom if you want. Basically from here what we could do is click on create workflow. Now, at this point, you might be wondering, okay, how do you build a AI agent, especially if you've never done this before, etc. It's really simple inside NA10. It's probably one of the fastest and easiest ways that I know to do this. So, what you can do is you can create a AI agent like you can see over here. You just add a new module. So, add node, type in AI agent, and then you can start getting this set up with Chat BT5 really quickly. And at this point as well, you might be wondering, okay, what's different? Why is Chat be better for AI agents versus other benchmarks? Number one, it's got pretty high benchmarks. For example, avoiding hallucinations. It's also got multimodal reasoning. It's good at coding and it's very fast. Plus, it has a bunch of different models that you can select between depending on what you want

right? So, for example, you could use mini for lighter and faster, cheaper jobs. You could use nano for ultra fast and ultra cheap jobs. But it's pretty powerful either way that you use it. And it's really good for NAM workflows because it has a 400K token context window which is higher than many other APIs. It's also fast, cheap, and also it's really good. It's built for aic stuff, right? So if you want to get started with this, what you need to do from here inside N is you would go to your AI agent. Then you're going to select chat model over here. You're going to type in open. And at this point, if you run through here, what we can see is we've got GPT5 on the list, right? So you if you type in five over here, we can select list. Now, if you

haven't already connected your Open AI account, let me show you how to do that for scratch. Don't worry, I can get it set up for you pretty quickly. So what you're going to do over here is you're going to grab an API key. All right, so key, what you're going to do is you're going to go over to platform. openai. com. All right, platform. openai. com link inside the AI profit board if you just want to learn where to get this stuff and how to set it up, etc. But from here, you can go to the developer platform and you just need to grab an API key. All right. So, what you're going to do is go to your dashboard over here. Then you're going to scroll down to API keys. create a new secret key. And once you get that key, all you're going to do is paste in the API key over here. Simple as that. Really simple stuff. You can leave everything else the same. So the base URL is this. And then once you've got this set up, it's going to say connection tested successfully. All right. So we can retry that. Make sure it's working. Boom. It is great stuff.

Then from here, you're going to see the model list. And again, you just type in five. All right. Now, you've got a bunch of different options here. For example, you got 5 2025, the 8th August, chat, latest, mini, nano, etc. Nano. And if you're wondering, okay, like what are all the differences between these models. So, let me pull this up. You can actually compare the models over onto if you want to see some examples. So, let's pull these up. Now, nano and mini are more lightweight versions of chat GPT. Right now you can see they all actually have a 400k context window and what that means is it could just handle a lot more context in the chat. Right? So if you compare that to something like Claude, Claude has a smaller context window. One of the complaints I see from people inside the AR profit board all the time is that people they don't get enough tokens in a conversation and then they have to start a new conversation to start using it again. Does that make sense? So basically if you want a longer conversation and more context then you would use something like GT5 instead of claude and they're pretty comparable in terms of how they code right now if we have a look over here what you're going to see is that this is a full-blown model right so it's 1. 25 to 5 million input tokens, $10 per output tokens. Now, if you compare that to Open GPT5 mini, that's way cheaper to use this model, right? It's going to save you a lot of money. If you use Nano, even cheaper, mate, right? So, you're going to save the most money with nano. And if you're not doing anything too complex, then that's one of the best ways to use this, right? So, what we can do is type in five here. Let's go with nano just to make it easy and simple. All right. And then we've got that set up. So, we've got the Open AI chat model that's going to run when we run the chat. Inside the AI agent, what we're going to do is we're going to select system message. And then from here, you can basically tell your agent whatever you want to do. Now, you might be wondering, okay, but where does it get the instructions on what to do next? So, what you can do over here is select a prompt, use a message, and inside this section, we've got the chat input. By the way, if you have any agents that you want to see me build today whilst we're doing this live stream, just post inside the comments. Happy to help you. Shane says, "Sup, Goldfinger. Good to see you here. " And Bassive says, "Hello as well. Good to see you here as well, mate. " All right. Andrew says, "Hey there. Thank you for doing this. Unfortunately, I won't be able to stay on the whole thing. Will this be available as a rebroadcast for me to watch later? " Absolutely. So, if you actually go to my YouTube channel and then you click in the live tab, right? So, you can watch this back. Plus, we create like a edited version to save people time on our normal videos as well. All right. So, what we're going to do from here is we're going to get back to this workflow. We're going to stay productive. I'm just going to select you're a helpful system. All right. So, we're going to open up the chat just to make sure this works and say, "Hey, mate. " All right. We just make sure that actually works. So, we're using the Nana model. The Nana model is great for chat because it's fast and it's cheap. All right. So, if you're going back and forth quite a lot, that's going to save a lot of time. So, inside here, it says, "Hey, good to chat. What can I help you with today? Answers, writing code, planning, just a quick chat, etc. All right. Now, if you post another message here, it's actually going to forget what you said because it needs a memory. All right. So, what

you're going to do over here is you're going to click on the plus sign and select me. Now, this is really easy to set up cuz all you do is you click on simple memory. All right? And then this shows you how many past interactions you want the model to use as context, right? So, if it's only five on the window length, then that means it can only remember five previous messages you've sent before it forgets again. All right? Now, if you want to extend that, simple. You just type in 20. All right. So, if we put 20 here and let's say, hey, what did I just say? Now, it's going to use the simple memory feature and it will remember previous examples. All right. So, it's used the simple memory section here as you can see. All right, it's running through the chat and you can see it's using the simple memory to do that. So, if you want to clear this chat, just click on refresh here. If you want to deploy this chat, you got your GPT5

one-click AI agent ready to go. What you can do over here is you can actually make this publicly available. Right? If you make it publicly available, what that's going to do is it's going to create this chat URL that you can share with people. So, we can put inside here, hey there, I'm G5. Have a cheeky chat with me. All right. And then you can add other stuff as well. You can even allow file uploads and all that sort of thing when you deploy this. But I just want to show you the fastest, easiest way to get this bad boy deployed. Okay. So if we hit save, make this active, and I'm just going to deactivate some my other active workflows. One second. So let's deactivate these other ones. Or you can just upgrade your plan. And also, you might be wondering, okay, but can you get like can you get NA10 for free? We actually have a tutorial inside the AI profit boardroom that shows you how to build this stuff locally for free, right? So, if you want to build this locally for free with NA10 instead of paying for NA10, then you can get the local guide inside here. And it shows you exactly how to set this up, right? See, it shows you how to set up NAN locally right there. All right. So, let's get back to this. And from here, we're going to deploy this. So, let's make it active. Boom. Shakalaka. That was easy. All right. Then, we're going to go over here. Chat URL. We're going to open this up in a new incognito. Plug this in. Make sure it works. Here we go. Hi there. I'm GT5. Want a cheeky chat with me? I certainly do, sir. I certainly do. All right. And if we say, "Hey, mate. What you doing? " Here we go. Right. Chat deployed. How fast was that? We literally just created a one-click AI agent in the space of 10 minutes as promised. All right. So, from here

we're going to go back to the canvas. And now, we're going to create something more interesting. Now, in the meantime, if you want to get asked to this, I'm going to download that JSON file. It's important, so you can just steal it from me along with the cheat sheet and all the relevant links from today. We also have like tons of NASA workflows inside here. So, let's add a resource file. We'll upload that. We'll call this basic GP5 agent. Super basic one because we want to start with the basics. Just show you what you can do and then expand it from there. If you actually go inside the classroom here, then you're going to go to NAM templates. You can see all this other cool stuff like video generators, social media posting machines, email analyzers. We even got like workflows for like SEO optimized WordPress blogs, etc. So, there's some really cool stuff in there. And from here, what we're going to do, linking inside the comments description. From here, what we're going to do is start building out something a bit more interesting, a bit more fun. All right. So, what we're going to do is I'm going to go over to one of my best recipes for creating SEO content. We'll use that to generate content inside NA10 with GPT5. All right. So, I'm going to take this prompt and I'll show you how simple and easy it is. So, we'll grab that. We'll delete that. We'll grab that. You can see how this is all going to be customized for me, my business, etc. Going to grab that prompt. Then we go back over here and then we shall go to the AI agent inside here system message. We're going to take the system message like and I'm going to say this is how you create SEO optimized articles and the keyword equals the keyword I specify to you. Then we got context. So you can just replace this with information about you, your business, etc. If you pull this up full screen, let me show you how this works. All right, so it's going to insert my funnel links. It's going to write some nice content about me, who I am. It's going to make sure that it writes it in the right way because we don't want any trash. And then from here, we're going to go back, escape, and then boom, we've got a SEO agent ready to go. All right. So, Dino says, "How do you create your AI videos? " So, if you want to create AI videos like me, just go to the AI profit boardroom, go inside the crash course, and there's a section on AI avatar videos down here and here. All right. So, if you want to know exactly how to do it, go to the AR profit boardroom crash course right there. So, let's go back here now. link inside the comments description by the way for that stuff. And then from here, what we're going to do is we shall go over here, AI agent, and we're just going to test this out. So, I'm going say my keyword equals SEO training Japan, right? It's using that memory function we were talking about earlier. It's creating the content now. We can pull this up full screen. And the good thing about using this like an SEO tool is that number one, you can host NA10 locally for free. Number two, you can use the latest APIs whenever you need to. you don't need to wait for whatever tool you're paying for to upgrade it. Number three, you can actually customize this to your business so that when you're creating content, this will customize you, how you want the content, etc. And number four, it writes the content much better. Right? So, you got the content right here as an example. And that's a pretty short article, and I think that's because we're using Nano. All right. So, what I'm going to do over here inside the OpenAI section is I'm going to switch over and I'm going to use the real McCoy, which is the actual full version of GP5, the full powered version. Right. So, let's run over here. We'll switch that over. We're going to refresh the chat and put keyword equals SEO training Japan. Make sure the article is 1,000 words or more, and we'll get it to start creating that. All right. cheap. It's going to be a bit slower than nano, of course, and it's going to be a bit more expensive, but if you get better outputs, it's 100% worth it. Someone else is asking, would you be able to create an AI agent that can evaluate the performance of LLM models based on criteria like accuracy and latency? You go into something like chat GPT and you say, "Give me some instructions for my AI agent/customgpt that analyzes the performance of LLM plus researches which models are the best. " Right now, if you do that, obviously if you're using something like G5, what you'd have to do is add in a tool and you use something called Plexity, right? Perplexity's tool, plug in the API and everything else. Plexi's tool can actually go off on the web and start searching. The other one that you can use is firecrawl. Firecrawl is pretty cool as well, but yeah, you want to make sure that it's connected to the internet. So, if you use GT5's API alone without adding that tool in, the biggest issue with that is it's not going to be connected to the web and so it's not going to have the latest benchmarks or data unless you upload it inside the chat. Right? So, that's the main thing to note here. Now, again, this is pretty slow. Other thing to note here as well is that probably a lot of people are rinsing the APIs right now and the servers are getting overloaded. But yeah, there you go. And Danny says, "What do you think is better for coding development right now, Claude or GT5? " Honestly, from what I've seen, I did a test on it yesterday. You can watch the video back. Where is it? This one right here. If you watch that video back right here, you'll see me compare the outputs. And to be honest, GP5 actually failed on some tests that Claude Opus performed really well. When you watch that video, you'll see. So, I would honestly say that Opus does the job. And if you want to create something really good, Claude code is very powerful. So, I'd recommend that step. So, we've got the outputs back now. We got all the content back. That's written the content as you can see. And there we go. Right. Then, it's customized all the content to ourselves. We've got the content here. All right. So for example, it's written all the content here step by step the SEO content and then what you can actually do is you can take that content and send it over to WordPress. All right. So if you connect this to WordPress, create a post, you can now create an SEO AI agent in the space of a few minutes that is customized to you. Your business is using GT5 remembers everything that you said and then sends that content over to WordPress and publishes it or drafts it. Right? Really simple and easy. We actually have loads of automations and this sort of stuff inside the AI profit boardroom, but that's just a little teaser to be honest. When I actually look at the

content itself, I still prefer Claude, right? I still think that Claude writes better content. So, for example, if I go inside Claude and I would recommend using Claude Sonet for this, you can change that inside the API settings of NA10. But if you take that content, you say right keyword equals train Japan, plug that in, the content itself is going to read much nicer. All right? So, it just feels a lot more human. It sentient. is more interesting to read. Whereas the content from chapter 55 was a little bit robotic honestly. But there you go. If you want to switch it around test new things, you can. You can easily delete this and then you can change that to anthropic. The reason that you would change it to anthropic is because that's going to be connected to claude for sonic. So whichever way you want to do it, test out, have a little go and there

you go. And then if you want to, let's say, for example, you want to import like one of the NA10 workflows from the end profit boardroom. You just go to the template section over here. And let's say for example, you know, we were talking about that perplexity scraper bot before or what else we got here down the list. Yeah, we'll go with that one. All right, let's take this one for example. We can just download the perplexity bot. Go to NA10. We'll delete this. Then we're going to import from file. Get the JSON file. And boom, it's all set in. Right now, obviously, you need to connect your Plexi account, but that's good to go once you set up the credentials. And then you would switch this over to five. All right, GT5. So, if we go down here, we can then select whichever one we want. So, let's connect this to GT5, for example. And now, basically, the difference with this when you have a look at this one is that it's connected to the internet cuz Plexi Sona API can actually go off on the internet. It's one of the very few APIs that can actually connect to the internet, do live research, etc., which is perfect if you're trying to build stuff that can go off, do your research. I know someone was talking about comparing benchmarks and LMS, etc. So, there you go. All

right, so that's pretty much it. Thanks so much for watching. If you want to get access to everything that I've talked about today, feel free to get it inside the AI profit boardroom. We have tons of NAN templates inside here. You see all this cool stuff that we've got here. If you want to automate, for example, viral reels, what else we got here? But if you want to host NA10 locally for free, we've got a whole process on that right there. Additionally, we've got other cool stuff as well, like a thousand NA10 templates linked inside there. We also have an NA10 sales agent that can just automate outbound emails for you. Even like video clippers, ebook generators, whatever you want. You can just plug it all inside and it does it for you. All right. Now, this also comes with daily coaching calls. You can jump inside here and get all these coaching calls and learn whenever you want. We do NA10 master classes every Friday that you can jump on. If you can't watch them or you can't jump on the live calls, you can watch the coaching calls here. We record all the Q& A too. If you have any questions in between those calls, you can post inside the community. Very active community. Everyone sharing, learning, and growing together. Additionally, inside here, what we also have is a six week AI masterass. You can follow the homework step by step. Learn exactly how to build AI agents from scratch if you're a beginner. We have an agency course for helping you land clients with all the automations and all the processes that I use to grow and scale my agency. And then also we have a YouTube AI road map that shows you how to build a YouTube channel from scratch using AI and all the processes that work for me. Everything that is inside here I've already tested and it's proven to work. So thanks very much for watching. Appreciate it. And if you're just like Julian I want you to go off and build this stuff for me. Then feel free to book in a AI automation session. It's completely free. On that call, we're going to look at your business. We're going to audit your time. We're going to figure out, okay, what automations do you need to build to save you time? And then how can you do that? And you can book in that call completely for free. And if it saves you hundreds of hours, 100% worth it, right? So, thanks so much for watching. Appreciate it. I will see you on the next one. Cheers.