GPT-5 FULL COURSE 1 HOUR (Build & Automate Anything)

Open AAI's new GPT5 full course 1 hour build and automate anything. Today I'm going to show you everything about GPT5. Open AAI just dropped their biggest model ever and it's changing everything. I tested it 20 different ways and what it can do is absolutely insane. You can build entire apps with one prompt. Create AI agents in minutes and there's even a $200 pro version that's blowing people's minds. Hey, if we haven't met already, I'm the digital avatar of Julian Goldie, CEO of SEO agency Goldie Agency. Whilst he's helping clients get more leads and customers, I'm here to help you get the latest AI updates. Today, I'm going to show you how to build and automate anything with Chat GPT5. We're actually going to run through 10 different ways to use it and build anything you want based on what you want to do, right? So, for example, you could use chat5 for building a basic website. I'll show you exactly how to do that. But if you want to code more interesting projects, I also show you how to do that, too. And I'll give away the full step-by-step processes for every single method that we run through today. So, let's get straight into it. So, the first thing that we're going to do is we're going to go over to chat GP5. This is actually, I would say, the best way to get personalized recommendations, right? So, if you want to use chat GPT in a way where you're journaling, for example, then this is one of the best ways to do it. You can also for example use the canvas method which can build stuff as well. I'll show you exactly how to delete that in a minute. Right? So if we switch to canvas over here and we make sure we're using chat GP5 then from here we can start coding away. Right? So if we just say something basic okay knowing what you know about me and my SEO agency build out a beautiful landing page right something like that. So, as long as you've got canvas enabled down here, then you can actually use chat GBT and based on what it knows about you because it remembers every single conversation. You can create something really personalized to you. And you can see it's now creating the code. And what it's going to do in a minute is it's going to ask you to allow access. And then from there, we can run the code in a second. And we can actually get the code on a canvas, preview it before we build it, etc. Right? And you can share that with people as well, which I'll come on to in a second. I'll show you exactly how to do it. So, let's wait for that to load. And that is one of the first methods. Again, if you want like the full step-by-step SP for all this stuff inside the AR profit boardroom link in the comments in the description, and we'll just wait for this to load. Now, in the meantime, whilst we're waiting for that, one of the other ways you can use this is to build your own AI agents. And you can use NAM for this, right? So, if we go over to NA10, whilst waiting for that to load, we can sign in here. And NA10 you can actually host locally if you just want to use this for free, which is pretty cool as well. But I'm going to use the version online just to make it nice and easy. Xiao says, "Hello from Portugal, Lisbon. Thanks for sharing. Happy to help make. " And what we're going to do from here, this is super easy and simple. Let me show you how easy and simple this is. If you've never built out AI agents before, we actually have a course on how to do it in less than 5 minutes inside the AR profit boarding. But essentially, what we're going to do from here is we're going to add the first step and we're going to just type in AI agent. All right. And pretty simple and easy. Then from here, we're going to add a system message. So, for example, your helpful assistant. Let's put you're a helpful SEO assistant for keyword research just to actually create something useful and valuable with cheap GPT5, right? And then from here we're going to go down to the chat mode and we shall select open it. Then we're going to select five from the list. All right. So there's many different models of GPT, but you want to use five. Now if you don't have your OpenAI account connected, you would just go over here and get a API key from platform. openai. com, right? And you would plug it in there. So from here then we're going to select chaki 5. I'm just going to go with let's see what we got. I'm going to go with nano because it's super fast and easy and it's also quite cheap as well. So if you're watching this you want to save money that's probably one of the best ways to do it. All right. And then if we pull up the chat here at the bottom what we can do is we can just go back and forth with this. Right. So let's say for example we want to get keywords for my SEO training program. Something like that. The AI agent is going to run with GP5. It's nano. In the meantime we've got the landing page ready to go in the background. But over here we've got the AI agent ready to go. And now we've got the keywords down here. Right? So you've just created your own keyword agent inside NA10. You just plug in your keywords. So you say keywords for SEO training program. It gives you a bunch of ideas and you got a bunch of easy keywords that you know you can easily rank with, right? So a bunch of good ideas related to your niche and that would work for any niche, any industry if you do an SEO and that sort of thing. So once you've done that, you can actually deploy it, right? So if you click on that you can deploy this and then you can get a publicly available URL once you've deployed it so that you can share that with your team and that sort of thing. Also the other thing you can do here is you can download the template share that with your team. So for example if I go back to the AR profit boardroom and I wanted to share that with you which I do then I'm going to go to resource file over here. We're going to plug in the JSON file and I'm going to say okay basic AI SEO keyword agent right with cheap5. You can just download that, import that into NA10, and you don't even have to create it yourself now. You can just steal my template. So, pretty simple and easy.

What else we got here? Charles says, "Hey, my guy. Sorry I got cut off last time. Laptop wasn't plugged in. Hope you're enjoying GPT5. " It's pretty good. Is it as good as something like Claude? I don't know, honestly. I think there's been a lot of underwhelm compared to what Sam was saying, but I know that a lot of people learn how to build it, how to use it, etc. Is a big step up from GPT4, etc. Asab says, "Why use AI instead of a website builder powered by hosting general systems? " Because you get more customization, right? Building a website is just it can be nasty. It can be draining. It can take a lot of time. And if you don't have a lot of time, if you're a business owner, then of course AI is going to help you build something custom. And Aaron says, "Everything I've vibe coded is broken. " All right, let's test this out. So, this was a vibe coded landing page that we just started building a second ago. Let's run the code, see what we get. Maybe it's broken. Let's check it out. Santiago says, "How can I use MCP inside NAN? " One sec. I'll come on to that in a second. But here's a page that we vibe coded out with Chat GBT. So, this is all based on what it knows about me. For example, we've helped websites go from like zero to 145,000 visitors. I've been doing link building personally for 6 years now. We have 70 experts on the team. That is true. And it's even, this is pretty crazy. It's even linked out to my funnel. I didn't give it the funnel link, but because chat GPT and especially GPT5 knows about me and has a lot of data on me, it knows that this is my landing page and also it knows that I like to add a UTM to track where stuff came from. So, boom shakalaka and that works really well. That is not broken. It actually works. Obviously, the content is blocked inside chat GPT, but we tested out that link a second ago and we were good to go. Right now, if we want to run it again or stop the code or whatever, we can also share this with our team. So if we click on the share mode, we can share that with a team or we can just download the HTML and then give it to them and they can use it wherever they want to be. All right, coming back to this, if you want to connect chat GPT5 with MCP, we actually have a module inside the AI profit boardroom on NA10 MCP agents, right? So if you want to learn how to build your own MCP agents with chat GP5, we have a module inside the AI agents and workflow section inside the AI profit boardroom and then you can just learn how to build them yourself. All right, you just follow the steps step by step. Also, if you ever get stuck, you can jump on one of live calls. We have live calls every single day, pretty much five times a week. So, if you want to jump on those live calls, ask questions, etc., you can inside the AR profit boardroom. And then if you ever can't attend, then you can watch back the call recordings. Charles says, "I'm digging your work, sir. Happy to help you. " Yay says, "What does SEO agent do? " Exactly. Whatever you want it to do. For example, I created a keyword research agent a second ago. Black Mask Media says, "Chat cheap doesn't write as well as 4. 0. " I think one of the things that you have to do is adjust the prompts, right? So, you can get really good outputs from chat GPT, but it takes a little bit more work. I think you actually have to simplify the prompts. So, that's one thing I would do. So, if I say do your magic for SEO link building, it's going to use its knowledge on this custom GBT. And these pretty nice, right? This one tiny SEO trick feels illegal. It feel like your competitors are waving page one whilst you're driving drowning on page two. Yeah, we've all been there. Blah blah, right? It creates like a really nicely written ad that's actually quite interesting, quite entertaining, etc. Has a nice CTA and this converts. I know it converts because we test it on the AI success lab and we create a lot of copy with chat 5 and post in here, right? You just have to know the right processes, the right prompts, that sort of thing. Ask it how many strawberries are in a I don't get it, but okay. So, just to be just to clarify, right? And SAP says which is better, NASA or make. So when you're building with GPT5 right you got a choice and I'll come on to make now because we seem to have come to that conclusion. So what you can do inside make is you can build AI agents as well using chat GP5. Let me show you how. So what you can do over here is we just log in on make. com. This is another way to build out AI agents, right? So you got NA10 and NA10 is I would say it's a lot more technical and also less linear, right? Like you can build out some crazy stuff inside NA10. If you've seen some of the stuff we give away on YouTube, for example, or on Twitter, you'll see some of the crazy stuff that we build. But for example, if we go down here, you can build like web scrapers. You can build some really complex stuff inside NAM. Let me show you some example templates. Right? So, if we go back to the air profit boardroom, then we're going to go down to NA10 templates. If you want to build like something less linear, NA10 just gives you really good options for that, right? So, let me show you this social media posting machine for example. like you're never going to be able to build this inside mate. com. So if you want something really complex or you want something nonlinear then it turns amazing. If you want something really simple and very linear then I'd recommend using something like maid. com. So for example here if we go down here and we're like okay I want to automate uh social media blog posting. What you can do inside here for example delete the WordPress. You can link this to WordPress and that sort of thing. But just for the sake of simplicity, I'm going to delete that module and then we're going to link Google Sheets to OpenAI to Google Sheets, right? So this is for example an AI agent that you can

build. So let me go back here. We can just create a new scenario. We learn make and then we can say okay take a spreadsheet and the data from my spreadsheet and then use that to create content using chat GP5. What you can see here is it's taking a spreadsheet that I have withmate. com and then with open router we can switch between APIs. Now the good thing about this is every time there's a new release or there's a new model that you want to test you can use them all inside GPT5. Right? So if we type in five down here we've got OpenAI GPT 5 or we've got mini. Right? I'm just going to go with GPT5 over here. Right? So we just switch out the APIs that we're using every time there's a new model. For example, if we want to create SEO content and then publish that straight to WordPress. We can do this like so. I'm going to choose where to start this automation. So, let's click on choose where to start. Choose manually. Let's have a look through the list. Let's go with new SEO just as a random keyword example. We hit run once. And we just need to update the API key, I think, inside here. So, I'm just going to click on this, click add, open router, and then I need to grab an API key. So, I'll just do that on the side. Right. So, if you want to grab an API key from Open Router, you can go over here. Then you can go to keys and then you can create an API key over here. Let me just check if one of these works. I might have a new updated one. Let's scroll down. Yeah, I think that API key is working. We'll wait for that to load. It does take a while. Terry says, "Hi, Julian Avatar. Not today, Sunshine. Not today. It's a real McCoy. " Jacob, do I invest in business? No, I only focus on my own businesses. Got stay focused. But if you join the a profit boardroom, there's loads of people in there who are looking for like joint ventures and that sort of thing. So, for example, if we go inside here, you can post inside the community and just ask, is anyone else interested in starting a new project together or working on buying some equity from a certain business that you're running, etc. And YouTube video says, I'm using GT5 now as I watch this live to build a complex WordPress plug-in and refactor some of its functions. What I really like about GT5 is there's no nonsense and it makes the changes. Yeah, I would agree. Someone asks, I'm just going to stop that workflow cuz it's already created the WordPress post. All right, so we've created that. Nice and easy. Let's log into WordPress over here and see if the SEO agent worked. All right, and just to recap, so far I've shown you three different methods to use GP5. Number one is directly inside the chat. You can build like nice landing pages, etc. So, we can run a page directly here. The other method is you can build AI agents inside NA10. And the third method that we've covered so far is make and building AI agents right there. So, let's just check this worked. We're going to go over to posts, make sure this works. Here's the new SEO. We'll preview that bad boy. Let's see what we've got. And that's the page ready to go. Honestly, I would tweak the prompts a little bit because it just doesn't it's not come out as nice, right? So, you want to tweak the prompts on the formatting and that sort of thing. But that's a basic way of how you can do it. And then if you go inside open rout here as well, you can see that you just say write a blog about, but you would say format it in for example HTML or something like that. And then if we go over to WordPress here, let's see what format we've got for WordPress. Yeah. So drafts it down. And there we go. Takes the information from GT5. Again, I would change the prompt here just to make it much nicer formatted. So inside the content section, you might say, okay, write that in markdown or write that in HTML, etc., and just make it a lot nicer. But yeah, basically there we go. So we're good to go. And that is number three. All right. Now, if you want all the SAPs from today, we've got it inside the AR profit boardroom and this guides you in a lot more detail. Right? So, for example, we've got a full SP on make. com, how to use it, open router, n10, direct in the chat, etc. Right? Now, one of the other methods that you can use this with is you can go over to something called cursor and inside cursor, you can use GPT5 and I think it's actually free. Right? So, if you want to start using and building with cursor, just open up cursor like so. You can download this for free as well. And then, you know, I'm on a free plan. So, you can see here Not I'm not paying for this. I've got GPT5 enabled here. So, if you click on the models, click on GPT5. We're going to enable AI agent over here. And then, if we take, for example, let's say you want to build a website, right? What you can do is you can grab all the content that you have on that topic, go over to the cursor, plug that in, and just say, okay, build a beautiful website for this business. And we're basically just taking the context of our business and then plugging it into cursor to build out that stuff. Now you can see it's planning it, scanning through and just beginning to implement it. And again, it's pretty amazing that you can do this for free. I think you get a certain limit. It might be like 300 conversations per month or something like that. But I think that for the average Jack Johnson just testing out GP5 like this is more than enough. Fancy Cloud says for GPT5 tests are using the GT5 high because that's the only fair test. I'm not testing out today. I'm just showing you how to build with it. Right? So like this, we're not going for fair tests or anything like that. We just here's how you use cursor. Here's how use make. com, etc. All right. So cursor will take a little while. So we'll wait for that to load in the background. But that is method number four. Another way that you can use this is you can go over to Manis, right? Manis, let's have a look here. Manus is like a AI super agent

right? So you can build a lot of cool stuff with this, but you can use GT5 directly inside here, right? So they actually implemented GT5 directly inside Manis right now. Manis is quite interesting because it's connected to the internet and it's really good for like research tasks and that sort of thing. So for example, you can you've got all these different use cases that you can build with. And if you want to see some of the stuff that we've built with it, let me show you some examples here. So we actually we built quite a lot of stuff with Manis. And the cool thing about it is he's very dynamic, but also it can load stuff and host stuff online, right? So you see how this is hosted on a subdomain and we built out this 3JS runner game where you can just go around in a castle that sort of stuff and manice actually coded it out but now you can use GT5 directly inside there right the same for example for this SAS tool so we built out this AICO content writer literally what you do is you just plug in your API key and then from here you can generate content on demand here's another one and this is a directory website that we actually built out for SEO using Manis this was a research report they created so it's really good at research. This was a nicer designed SEO agency website. And then you can also build out of games as well. So this like manice version of Mario Bros. So let's go back to cursor now. See where we're at. Seems to have built and it's setting up the local server. We'll run that. That should be available to check out. And there you go. There's your website built with GT5. All right. So you can see it's taken all the information from my website that we pasted in and then created it and hosted it on a local subdomain with a nice like contact form, information about our business, who we are, etc. the about me information. These links do actually work like you can see and it's creating a nice website. Now obviously you would go back and forth vibe code out inside cursor but again I'm on the free plan. It was super easy to build out really easy and it didn't take a long time at all. Now, if we go back to chat GPT, the other thing you can do here is you can switch between thinking and also GPT5 Pro. Now, if you're using G5 Pro, it's going to take a long time to come up with an answer. So, this is better for more complex tasks. If you were I think one of the best ways to use is like you go into GT5 Pro and you're like, okay, knowing what you know about me over the last week, for example, what are some ways you think I can improve or how do you think I'm wasting time or what don't I see that I should know? Where are my blind spots? Right? Because it sees you. It sees all your work. it knows what you're typing in and working on every day. So, that's one of the best ways to use GT5 Pro from my own experience. It's not obviously not good for quick answers and that sort of thing. You can use this inside Manis. And then also, GenSpark is another good way to use GT5, right? So, if you want to combine it with the internet, pre-built agents essentially, then you can do that inside here. For example, I've even built out with GenSpark like these videos, right? So, let me mute this. I'll show you what I mean. — It's the first step. So this was a video built with Gen Spark and Bayo3. So you can combine chat 5 with other APIs like Bay3, not just for completing tasks and coding stuff out, also for even for creating videos and that sort of thing. Genpark actually announced recently that it's free on Genpark and free users now have access to GT5 for free right directly inside there. So you can use this inside GenSpark and then build stuff out with it as well. If you want to know, okay, what can you build with GenSpark? Like what the what sort of stuff can you do with it here? Let me show you some examples. I actually honestly I prefer GenSpark's outputs to Manis in general. I tend to find like it's a lot faster as well. But if you want to see some examples of what we built out with GenSpark, let me show you some here. So this is a SEO game that we built out. We also created a SAS tool right here. This is a full website that it created. Literally just went off on the internet research stuff and that sort of thing. And then we have AI growth calculator so you can calculate your growth. Fancy Cloud says, "Why is your Chrome, Google, YouTube all darker? " Cuz I'm in dark mode and I think you're in day mode. That's why if you want to learn how to switch that over, just Google it. But yeah, you can switch between dark mode and light mode. What else we got here? This is a quiz that I actually used to train my team so they can like answer questions inside the quiz. We have this keyword runner game that we built with Gen Spark. I even translated my website into French and then deployed that. And this is another runner game that we built with GenSpark. All right. And you can do this with site with a chat cheap now as well because it's directly inside there. And black mass media says, "Does your A profit boardroom have instruction videos different from your channel? " Yeah, we have so much in here that you won't find online. So, for example, inside the AR profit boardroom, we have a six week AI automation master class that you won't find anywhere else. And literally, it gives you homework and it's right here's what you do week 1, week 2, week three, etc. So, it shows you exactly what to do. So, for example, in week one, you learn how to build an AI agent in under five minutes. And then also all these NA10 templates are inside the AI profit boardroom. You won't find these for free anywhere else. On top of that, we have a crash course with all the automations I use inside my business. And these are videos not on YouTube. You won't find those anywhere else. On top of that, you also get my six week agency course on how to get more clients. This is an AI automation agency. And we have the YouTube AI section here as well. So, this is a six

week program that shows you exactly how to get more leads, traffic, and customers using YouTube and AI. Top of that, you get access to the community where you can post and ask any questions. You won't find that anywhere else. And additionally, inside the calendar here, you get five weekly live coaching calls. You can ask any questions live on a call, get training on calls, and again, yeah, you won't find that for free anywhere else. So, let's keep going. Now, we've talked about N10, Open Router, we've talked about May. com. Another cool way to use this is you can actually build stuff directly inside something called Bolt DIY. Now, if you want to run BoltDIY, pretty simple and easy. You just clone this inside your terminal. Basically, what this is like a app builder that you can host locally. So, let's grab this and you can just copy and paste the instructions from the SAP like I'm showing you. I'm going to npm run devlab. That's going to give us a local host. All right. And then what we're going to do from here is we're going to select open router. We'll go with GP5. Let's find it on the list. There we go. Now, we have to get a AP. So, I'm going to get that over here. I'll just get that in the background. So, I want to show my API key on a live stream. And we'll just plug that in. So, I've put that into BoltDIY over here. As you can see, we'll hit save. And then we'll say, okay, code our finess calculator. Just totally random example to show you what you can do with this. And there you go. Blackmass media says nice. I'm joining. Awesome. Good. It'll be good to see you in there and connect with there with you there. The air profit boardroom is the only place that I connect with people personally, right? So if you want to connect with me, get help from me, coaching, etc. Ask me a few questions, then join link in the comments and description. From here, we can start coding out, right? The other way you can use this is if you go to lovable, I think they've just implemented chat 5 inside lovable. So you can see here GPT5 meets lovable and essentially you can code with this. So I'm just going to log in here and once you've logged in, you can use GP5 as you can see. So if we click on try GPT5 now we've got that selected as a model. So you can click that on and off. We'll click it on and then from here you can start building stuff out. Right. So let's say for example, okay, build out an awesome dopamine inducing Space Invaders game. Something like that. So I'm obviously I'm just doing this live on a video like this. This is not the sort of stuff you would normally build out, but I just want to show you some quick examples of what's possible. And then yeah, you can see so you can use GT5 directly here with the agent. So that'll run in the background. In the meantime, we have Bolt coding out with GPT5 over here, too. Avocado Juicer says, "I love you. Really love your emotions, your actions, yourself. I appreciate that. That's super kind. " We got some good people on today. Thank you very much, sir. So, you can see Bolt is coding out now. We've got Dopamine Blitz Wars coding out Unlovable. And there's some other cool stuff as well. So, we actually have an SP on how to set up browser agent web UI. Essentially what you can do with this and we have a full video tutorial on it here, but essentially what you can do with this is you can actually control your browser using GD5, right? So you go inside here, you set up the API key, then you run the agent and it can control your browser, control your browser, etc. I can't set this up on a live stream simply because it's going to shut down all of my Chrome instances. So avoid that. But if you're testing this offline, then you can use browser use web UI and that can actually control your laptop with GP5 as well. Also something to bear in mind here is if you're running Bolt locally, try not to have too many programs open. So for example, for me, I'm live streaming right now, which is already taking up a lot of memory. And then if I code with Bolt local as well at the same time, Bolt DIY, then it can get quite messy and slow down your laptop and that sort of thing. But yeah, you can see an example here. So SEO calculator, you just paste in your HTML and then it gives you an SEO summary. So it counts like H1's, description length, title length, etc. analyzes the HTML in terms of SEO and we coded that out using GP5. So, it worked out perfectly first time. Lovable is still coding out the example right here. But yeah, we've shown so many different ways to use this, right? If you want to get an SP on lovable, let me show you exactly how to do that. So, what we can do and I'll just shut down I'll shut down bolt local now and also shut down cursor as well. So, we've already shown you what you can do with that. If you want to use Lovable, I've got a full recipe right there if you want to steal the step-by-step instructions. So, that's still coding. That's going to take a little while, I think. Usually, loveable is a little bit slow. What I'm going to do is just put that in the background and I'll come back to it in a second. And then there's a couple other ways you can use this and host this locally. This is probably going to slow down the live stream, which I'm dreading a little bit to be honest with you. But what you can do over here is you can go to something called Visual Studio Code as you can see. And then you can go to extensions. And inside the extensions here, you can choose between client or root code. And these can both use GPT5 as well. So if we go to the settings, open router, type in GPT. And then scroll down, we can see GPT over here. And this supports browser use as well. So you can use your browser. We'll hit done. And then if we say, okay, right, let's build something out. Let's, I don't know, build out a Tetris style game. We've got make sure you've got G5 selected as the API at the bottom. And then that will code out in the background. And now you can see it's

creating the file. So it's creating the HTML, the CSS, etc. And this is all using GT. All right. So that's coding out now. Let's see what we got here. Mr. Zeno says, "I had a few AI development, a full stack app, and I'm building it in VS Code and it's co-pilot. First time trying this. Back end is 8% ready. Nice work. " And then Cusa says, "Your avatar. " The operator says, "Hey Charles, what do you have? " And Cusa says, "What is it tried to go deep with? " Okay. What's the best to go deep with? I think something like Visual Studio Code is good because you can build, you can go quite deep with it because you're building locally, right? You're creating something locally. So, you save all your progress. You can come back to the project sometime, etc. And there we go. So, now we've got Tetris built out, ready to go. We can move that around. We can flip that around, right? And we just built Tetris with GPT5 in 2 minutes. Let's see if that's actually works. It's taking me back to my childhood. There we go. Boom. Shakalaka. This man is a pro at Tetris. There we go. All right. So, that was how to build it out locally using Visual Studio Code as well. And I'm doing this all live whilst talking to you, right? Obviously, it'd be a lot easier if I was just concentrated and focused, but I want to show you all the cool stuff you can do with this and how you can do it and everything like that. Cusa says, "But Manus looks crazy from your last vid. " Yeah, Manus is amazing. It's just a little bit slow. That's the only thing that I find a little bit frustrating with it, but is really cool. And again, like you can do this inside recode as well. So, if we go inside settings here, then we're going to choose open rout. And then from here, we just type in GPT. And then you can use like chat, mini, or nano. Honestly, I think if you're coding something out that's going to be semidecent, then you probably want to use like the main versions of GPT5, right? So chat or GPT5 directly here. If you use like mini or nano, you're going to lack getting the outputs to be honest. Yeah. And then that's basically it. That's how we build anything. So we've talked about using GPT5. And I just need to add the manuscript inside here as well. Peeps, don't let me forget. and Gen Spark as well. Gen Spark, they also have a browser which is pretty cool. So, you can actually use their brow online as well. It's one of the only AI powered browsers I've seen on the web. So, if you want to use the Manis SAP, let me plug that in there. And then if you want to use the Gen Spark SP, let me pop that in there for you there as well. All right. So, that's an insane amount of to use GPT5 and build basically anything that you want. We've talked about games, landing pages, tools. I've shown you how to even create videos with GT5 and V3 automations inside GenSpark. Pretty much everything you can think of is inside there, right? So we talked about direct in the chat, NASA, open router, bold, client and make. com, the browser use, web UI agent, cursor, rico, lovable, madness, and genspot. 12 different ways to build anything you want with GT5. So thanks so much for watching. If you want to get all the SPS inside the AI profit boardroom, this also comes with my six week AI automation masterass if you're just beginning with this. Also, it comes with an agency course, all my best automations that have grown my business personally. And additionally, we have a YouTube road map here. So, if you want to learn how to build out a YouTube channel with AI, feel free to get that. And we have tons of AI SEO automations along with daily coaching calls and Q& As. And you can watch those back on the recordings if you can't get access inside the community is absolutely popping off. Very active community. For example, this post alone, what 450 comments on there. Additionally, you see all the cool stuff that's going on right here. Loads of lots of good posts. If you ever get stuck or anything like that, you can ask questions. And inside the calendar here, you can see all the calls here. So we actually have an NA10 automation masterass, a weekly Q& A, a call with Dr. Jeff, who is a PhD scientist specialized in AI, and on top of that, we have a Friday learn sort of thing. Now, if you want to join, bear in mind we only have 35 slots left at the current price. So make sure you click on the link in the comments description and join now before the price goes up again. And really appreciate you watching. If you're like Julian, I just want you to go off and build this stuff for me. then feel free to book in an AI automation session link in the comments in description. From there you can book in a call. We'll look at your business and obviously this is about becoming a client, right? So if you book in a call, this is about you becoming a client and hiring us for AI automation. You can just book in a call and we'll show you exactly what you need to build to automate and save time and save hundreds of hours per month. We have tons of good testimonials like you can see right here. A lot of clients happy with our agency, Goldie Agency, and we'd be happy to help you too. What else we got here? Cusa says, "Good job, sir. hopping in once got spare lolly and then Michael says is this live or avatar if this was an avatar it would be absolutely insane but it is the real Julian goldie here all right so appreciate everyone who's watching shout out to all the people who commented and I will see you on the next one cheers by official GPT5 has been released I'm going to be showing you how to access it today if you don't currently have it inside chat GPT no problem I'll show you some other ways to access it. And this is the biggest release of the year when it comes to AI. So you can see on OpenAI's official website here, they've said, "Introducing GPT5, our smartest, fastest, most useful model yet with built in thinking that puts expert level intelligence in everyone's hands. " One of the

interesting things about this is Sam Orman the founder of OpenAI Jack GPT says that this is basically like a SAS ondemand AI model and also you don't need to switch between different models. It will just figure out which one is the best. So you can see here they've said we're introducing GP5 our best AI system yet. GP5 is a significant leap in intelligence. This is better than all of our previous models featuring state-of-the-art performance across coding, maths, writing, health, visual perception, and more. All right. And it is a unified model. Now, what that means is essentially if you're using Jack GPT, you can switch between these different models like thinking or you've got quick coding analysis, reasoning models, etc. advanced reasoning. It's all a little bit messy. Whereas inside GPT5, you'll be able to access this in one single unified model and it will just pick out which one is the best one for you. All right. Now if we actually have a look at this as well, we have access to GPT5 inside open router. So you can see there are many different models. You've got for example GPT5 nano, GPT5 mini, open GP5 and then GPT5 chat as well. You can also start coding with it inside playground AI. So you can go to the chat here, start using GPT5 directly here and you can code with the API key as well directly. Now, if you want all the notes from today, feel free to get it inside the AI profit boardroom link in the comments in description. Just go to the SP section and all the notes from today will be inside there along with loads of stuff including daily live coaching and all my best courses. GT5 not only outperforms other previous models and benchmarks and answers questions more quickly, but more importantly, it's more useful for real world queries. All right, so it significantly reduces hallucinations, which is a great move in the right direction. Interestingly, they talk a lot about health here. When I'm looking through the page, writing code inspe health is a new sort of description of the model that I've not really seen before. So, they've obviously made some advancements. It's going to be interesting to see how that's used for health and that sort of thing in the f. The other interesting thing here is it's good at front end generation, right? So, for example, if we have a look what people are generating with it, people are like oneshotting games. It's pretty crazy. If we have a look at this tweet from Alen, he said, "What's truly impressive about GPT5? One shot in this game is in the graphics. It's the flawless prompt adherence and constraint handling. A fully functional interactable game generated in a single pass. This level of instruction following and code generation is wild, right? " And you can see an example of what that looks like right here. So, you can basically like oneshot games on the front end, that sort of thing. You can see how it performs in terms of numbers. So, if we look at the different versions of GPT on the scale, it's off the charts, isn't it? It's just it's ridiculous compared to other people. Let's keep going through now. See what we got. Sam Wolman is tweeting about it as well. So, he said, you know, when you get access to GPT5, try a message like, use Beatbot to make a sick beat to celebrate GPT5. And then you got like this SAS tool that's just been created. You can see how quick it is. It created that in literally 6 seconds, which is absolutely wild. And the UI is pretty nice as well. So, it can like create games and SAS and that sort of thing on the front end, too, which is pretty exciting. And this literally just came out. I think they literally just did a live stream like 2 hours ago as I'm making this video. Right. You can see here. Yeah, the announcement just came out 1 hour ago. This is brand new. This is fresh off the press. And most of the world has not even seen this yet. So, if you're watching this, you're probably in the top 1% of the world seeing the latest releases from AI. The other thing I was going to say is this has different models. So, we got GT5 Mini, etc. And GT5 is the strongest coding model to date. So, you can see the differences in the charts right here. And this is the other thing as well. So, they've got different personalities inside the chat. So, you can, for example, use synic, robot, listener, or nerd. And then you can customize those in your chat GPT settings. You can also switch between like research text only optin change anytime blah blah and you've got some examples right there. Right. So that's what it's going to look like once you've got access. Now this is rolling out to everyone around the world. So again I don't have access inside chat GPT directly but I do have access inside open router. All right. So if you want to get access directly just go to open routter if you don't have it already released inside chat GBT. Here's another example. So, this was just one single prompt. Basically making it the strongest coding model ever when it comes to building stuff out. So, we've got the jumping ball runner. I'm just going to mute that so it doesn't get too noisy. But yeah, it's built this game. This is actually playable as well. So, it's been embedded directly on Chat GBT's website and then you can build out and oneshot games and that sort of thing which is pretty cool. Pretty nice looking UI right there. That's the prompt that we use. We can actually test that right now. So if we take this prompt like and then we go over to open router. Let's just try what we got here. What we got? So we got nano mini. Let's just try this one instead. So I'm going to go directly inside the chat here. You

can see the price and that sort of thing. We can look at the specs as well in a sec. There's a lot to talk about here. about. Who we got watching? By the way, if you're watching this live, shout out to you. Thank you for watching. Let us know which countries are you watching from. Put a flag in the chat. I'll give you a shout out. So this looks like it's using the reasoning model. if we just go straight into chat GPT. We didn't ask it to, but I think it will automatically choose between the different reasoning models and then we can come back to that in a second. Right. So, I've used exactly the same prompt from the website for the game and we'll see if it actually does one shot it perfectly like we've seen today. In a minute as well, later on in this video, we can compare it against different models. See how it goes as well. We got someone from Algeria. I know it. Norway, shout out to you. So, creative expression and writing T5 is our most capable writing collaborator yet. Able to help you steer and translate rough ideas into compelling resonant writing with literary death blah blah. Let's see what else we got here. So, this is I'm really interested about this. Like, why are they talking about health so much? I know they did have a specific model for health. I didn't think that would be integrated with GPT5 so much, but this is interesting. Compared to previous models, it acts more like an active thought partner proactively flagging potential concerns and asking questions to give more answers blah blah. I wonder if for example some people going to the GP and that sort of thing whether they're just going to turn to chat GPT for the health related stuff. This is interesting right? So for example it's comparing GPT40 versus GPT5 to write short poem and then you can compare the outputs. Right? So you got GPT4 over here and you got the outputs of GT5's poem over here. This is a lot more poetic than this one, right? It's still using those crazy M dashes, though. Those haven't gone for some reason. The M dashes are here to stay. Maybe even in GPT40. All right, that's creating the code now. It's coding out. It's taking a little while, but we'll come back to that in a second. Says, "Maths is 100% insane for me. " We got Comroy from United States. We got some legends from Norway. Plenty of people from Norway here. All right, so let's keep going down. Yeah, it's a lot more advanced, isn't it, in the responses it's given for poetry as well if you just smash it out loads of poems on GPT5. Maybe you aren't. And then we've got the evaluations here, right? So GP5 is much smarter across the board. So for maths, 94%, SWE 74%, 88% on ADA, Polyglot, blah blah. And let's compare them now. So you've got all the different modes. GT5 Pro, that's interesting. I've not seen that model yet. And then if you compare it, 03 was pretty good to be fair, but it was super slow. But if we compare this, GPT5 is absolutely crushing it. Absolutely destroying it. Right? So this is without thinking and this is with thinking if that makes sense. So you got reasoning versus non-reasoning for competition maths. And if we have a look here, look at that. GT40 is all the way down there at 42% versus GT5. Absolutely crushing it on maths. Let's see. Frontier map compare the benchmarks is absolutely destroying other models. Harvard maths tournament PhD level science questions. Yeah. So just across the board GB5 is crushing 03 and crushing 04 as well. Let's see. We got this. We should have this code back now by now surely. Yeah. We got the HTML back. Let's test if that actually works. There's only one way. We can talk about it all day or we can test it, my friends. And I'm a man of action. So let's take this HTML. We'll grab that. We'll go over to live and we'll have a cheeky gander. So here we go. This is a oneshot game. Let's see if it actually works. It doesn't work. Let's look at that. I'm play clicking play. It doesn't work. Let's just try on something else just to make sure we haven't got this wrong. What I can do is just go over to something like claw and say preview this code and it will just turn it into an artifact that we can play. But there you didn't work. What are we doing here? I'm testing the same prompts they've got on the website. It didn't seem to work there. Maybe we need to test it on Let's see what we got here. That is the most powerful model, right? And the most expensive by a long way. It's five times more expensive than the mini version. There you go. We've tested it live. That great is coding as I expected. So let's have a look here. Instruction following and agentic use 5 shows significant gains in benchmarks blah blah. Agentic searching and browsing. I do think that's going to be a big part of it. Right. But if we actually have a look here, it's 54% which is not bad, but I don't know if that's going to be good enough for using this dayto-day. What else we got here? Multimodal reasoning, health. If it can't code out a HTML game, maybe I wouldn't use it for my health. Faster, more efficient thinking. If you're wondering how to access all this or you just want all the links, etc. Feel free to join the AI profit boardroom. All the links are inside the SPS. Just go down to GT5 which is right at the top for you there to make it easy. Link in the comments description to that. What other questions we got? We got people from France, Luxembourg, Italy. Shout out to you legends. How can we use this for SEO? I'll come on to that in a minute. The other thing I've noticed is I've not really seen much about image generation. So, I don't think this has a new image generation model. I think it'll be using the previous one. More benchmarks here for safety. And there we go. All right. And it says on the how to use section, it

says GP5 is a new default in chat GPT. Paid users can still select GPT thinking. But if we go over to chat GPT, it's not there. So it must be rolling out later. It was only announced like an hour ago. Yeah. So it's starting to roll out to all plus pro team and free users with access to for enterprise and edute coming in the next week. All right. I've been saying on my YouTube channel for quite a while it's going to be free. People are saying no it's not going to be free. It is free. I don't I'm not one of those guys who says like I told you. So I'm not going to say that. But yeah, you can see here you can get access for free. The difference is the usage volume, right? So for example, pro users get unlimited access to GPT5 and GPT5 Pro will be interested to see how that performs. Plus can use it comfortably as a default model and then free users will be on like a limited tier. Right? So this is all the stuff about GPT5 coded. Some cool stuff there. All right, so let's have a look because Claude previewed it here. So we got it here. Let's test it out again. And look, it doesn't work when I preview it on Claude either. So this is interesting, right? I bet if I use that exact same prompt inside Claude Opus, it's actually going to work. So let's test that out. Right, if we go over here, let's grab this prompt like so. We'll go over to Claude, run a new chat here. We're going to select Opus 4. 1 and we'll just see, okay, can Opus 4. 1 outperform GP5 with exactly the same prompt that OpenAI has used on their website. That would be interesting to test, right? So, let's see how it goes and we'll see which one is the best for coding. Now, in the meantime, you might be wondering, okay, like how do you what's the best way to use this FCO? Someone asked me before cuz it's better at coding and that sort of thing. So, let's test this out, right? What we're going to do here is I'm going to use one of my favorite content prompts. It's inside the AI profit boardroom. If you want to steal this from me, we actually got a bunch of AI SEO automations inside there. So, if you go to the AI SEO automation section inside the AR profit boardroom link in the comments description, you can get access to all of my best automations like you can see right here for AICO. So, what I'm going to do over here is we shall go to chat GBT. We'll just use a basic model. So, the chat, go inside the chat here and we'll test this out. Now also you can select app inside the chat here. So if you want to get the canvas preview you can select app. We'll do that in a second to test out. But in the meantime what we want to do is just create an article about a keyword. So let's say for example just totally random keyword. We'll plug this in. This got all the information about me etc. who I am. It's very contextual and we'll use that to generate the content and we'll see how it performs as well. All right. So it's planning out the content right there. Now it's writing it and we'll compare that side by side versus chord summit in a second. That's still coding out the game, so we can't compare the outputs before. And Bare Mass says, "Julian, when do you think Google will respond to the GPT5 threat with Gemini 3. 0? " I think Gemini 3. 0 is coming very soon. I think that's going to come out. Usually what they do is they just release like as soon as everyone else does. The same with Claude. I think Claude proactively released Opus 4. 1 because they knew GPT5 was coming out this week. Yeah, I think this is something is coming very soon. Vampy says, "How do I access GT5? I'm not able to access it on the web. " It just goes to open Marita if you want to get access. Otherwise, it'll be released later today to everyone, I think. So, it's just rolling out, right? Rolling out slowly. Some people get access sooner than others. All right. So, this is the output from Claude Opus. To be fair, even like the already looks better than Jupiter 5's output, which is pretty interesting. You can see here we've got the output. Let's see if it actually works. Yes, it does. So, how interesting is that, right? We use exactly the same prompt from GPT5's website. GT5 struggles to code it out, whereas Opus 4. 1 out perfectly and created a really nice game out of it. If you're going to pick one model for coding, as it stands, there's only one that gives me a working output. So, that is that's really interesting. Let's see what else we got here. So, we got the content back from here as well. What I'm going to do is I'm going to compare this output using Claude for Sonnet as well cuz that's probably the most sentient that I've seen so far for writing content if that makes sense. So if we go over to Claude Sonet 4 here, we'll plug in exactly the same prompt and then we'll compare the SEO content side by side and we'll just see which one performs the best, which one creates the best outputs as the only fair way to do it. And we're using GT5 chat here to create this and we'll see which one just feels the most human. MC says, "Thanks for replying. Great work. been following you for months. Appreciate it, too. Happy to help, mate. And Claude is just absolutely smashing it to be honest. Let's see. Do you know what would be interesting as well? Is we take the same prompt cuz I'm interested now. You've got me interested. All right. So, we're going to plug in the same prompt inside Gemini 2. 5 Pro. We'll select the canvas just created directly in here. And we'll see whether Gemini 2. 5 Pro can create a better output than GT5. All right. So, we're going to go inside the chats here. We shall take exactly the same prompt for the jumping ball game that OpenAI

recommend. Let's take that. We'll plug it into Gemini 2. 5 Pro. Plug that in and we'll just see whether that can create a working output as well. In the meantime, we've got the content back from Claude for Sonet and we'll compare which one create the best content. All right. If we actually have a look at the prompt that we gave here, this is interesting because for example, if we have a look here, the keyword was SEO training China. And if we have a look on the outputs, let's have a look first of all at the title. The ultimate guide to dominate in Chinese search markets versus SEO train in China. How to rank, win, and dominate. I would say GT5's title is nicer. Let's have a look at the intro. You're in China. You've heard SEO can work. You spent money on ads. Burn cash on agencies. Still no long-term results. Sound familiar? SEO in China is different. The rules change. Let's have a look at this content. SEO training is not just another digital marketing course. It's your ticket to cracking one of the world's most lucrative. Blah blah. I still prefer the content from here, right from Claude. It just feels a lot more sentient. It does use the keyword as well inside the introduction which is going to help it rank better. Basic stuff, but that's better with SEO. Whereas, if we look at this introduction, it doesn't really mention SEO training China until quite a few lines in which is going to make it harder for search engines to rank it to be honest with you. So, this is the title of the second part of the content. So, why SEO training in China matters more than ever. Now, we all know, we've all seen this AI fluff word right from the beginning, right from chat GPT3, and it is still there today. So, honestly, I prefer the writing from Claude. I think it feels more sentient. It feels more natural. It's nicer to read. It's better optimized for search engines. I'm going to take the content from Claude, honestly, over GT5, which is a shame. I was really, really excited for GT5. Now, let's see how Gemini got on. If we go over to Gemini, yeah, to be fair, Gemini struggled with that. So, we've got an error straight in there. So, if we're putting them in the rankings, I would say Claude Opus 4. 1 number one, then you've got GT5, then you've got Gemini 2. 5 Pro in this specific competition. All right. Some people asking like, "What do I think of generative optimization? " I'm not going to go into that because it's a little bit off topic for today, but if you want to learn about that stuff, just check out the SEO Elite Circle. SEO Elite Circle is a place to be. We've got a very active community that talks about SEO every single day. We've actually got trainings on AI SEO. Loads of cool stuff in here. So, make sure you join that if you want to learn more about SEO and actually get weekly coaching on that, too. All right. So, I want to try Sam Alman's other prompt. Let's pull this. It's in LM Marina as well, and it is number one on the score there, which is interesting. It's apparently beating Claude Opus 4, which is interesting cuz I just don't think it's winning at the minute, right? But I give you the real tests. Nobody's showing you this stuff, right? We're just testing real stuff live. to see what actually works and what doesn't. So, let's keep going. Now, if we go over to X and let's take the prompt from SAML. So, use Beatbot to make a sick beat to celebrate GT5. All right. So, we're going to take that one. And what we'll do now is inside open router, we can compare them both, right? So, we're going to take Opus 4. 1. We'll take GT5. We're going to make sure we use app. So, create an HTML app. And then let's hit enter on that and see what we get back from both of them. Right. is creating the artifacts on both. We can see which one comes back to us the fastest, which one gives us the best output, etc. Very easy to compare them side by side. I keep refreshing my chat GBT just to see if we've got it through, but it's not coming through. Might take a while. This is interesting. It's actually available for free inside Cursor AI. No way. All right, let's check it out. Let's see. Is that GC5 is available with free credits for paying users during the launch week. All right, let's We can test that out in a sec. I'm going to sign up to cursor AI just to show you how it perform. All right, so we got cursor open over here. It's been a while since I used it to be fair. We got GT5 down there and we can use GT5 inside the text. So that's another way to code with it. I actually don't think I'm on a paid plan here, but I can still access GPT5 and then we can switch between agent, ask, and edit. So this is really good for coding out. We'll come back to that in a second. In the meantime, we have the artifacts back. Look at this as well. So this is interesting. E55 is still coding out whereas Opus 4. 1 has finished already. Let's open up the artifact. We can preview this. We've got that back. Boom. Shackle. Look at that. That's looking good. That is looking good, my friend. All right, I'm going to unmute this. Yeah, it's great. It's incredible. We got big bees. We got big beasts. Opus loves to celebrate the launch of GT5. Now, where is where's GT5 gone? There we go. All right, let's open this artifact. So, this is still coding out, right? You can see the three dots are buffering right there. So that might take a little while. So if you want to get access to cursor for free from what I can see, you can just code with it directly inside here. I'm not on the paid plan as far as I know. Yeah, I'm not on the pro plan. I'm on a free plan. So if you want to get free access to GT5 right now, you can just go to cursor. We actually have training on how to use cursor inside the air profit boardroom.

Just type in cursor in the search bar and you can get access to it. If you want to learn how to use this stuff and where to access it and download it, etc. But yeah, you can see we've got GT5 down here. We can switch between GT5 and GT5 fast. We can use it for free as far as I'm aware. Let's see if we can do the same thing. So if we go inside the chat room, look at that 5 is still coding out. We might have to rerun the prompt, but let's take this and that's generating the output here. And there. All right. So that's pretty cool. So there you go. Problem solved. You can get access to it with cursor inside here. accuracy can now it looks like it's stuck inside the search on chat on open router. So I'm just going to X off Opus. We'll try this again. Run the app enter and then we'll go from there. But as far as I'm aware like Opus is still outperforming it on pretty much everything like for speed for the outputs. We have to rerun the prompts for GT5. I mean for content creation called Sonet one there quite clearly. But if you want to use it for free right now and you don't have access inside chat GPT, just go to cursor and then you can use GD5 directly inside here. And it's pretty fast inside here which is cool. The other thing that I'm noticing is cursor is a lot faster than Visual Studio Code. Usually Visual Studio Code if I was live streaming would slow down my whole laptop whereas Cursor seems to do better. Let's test some more stuff now. So if we go over to P 4. 1, let's just let's take something basic like a hyperdopamine pong game. We'll go over to chat GPT GT5 and we'll use here and again we'll switch between Opus and we'll compare the outputs. Right. So let's run that in the meantime. This is rinsing credits but that's the price I will pay for you my friends. That's a sacrifice is finish coding this out. Let's have a look. That's pretty cool to be fair. Wow, that was loud. To be fair, that's a lot more complex than this one. If we go to here, this is the output from Opus. GT5. I would say that's way more complex. We'll stop that. But yeah, that's pretty cool to be fair. I would say that GT5 won on this round. Even though we had to get it to do it twice, the outputs are really cool there. And we can switch between like human eyes, swing, BPM. We can mutate the beat. Like you can see we've got all these different options here. That is a superior output to claude opus, which the UI looks cool, but it's not as good as that. And now you can see we're getting the HTML back. Oh yeah, we're getting this GPT5 party started, my friends. Incredible. Let's take the beat down. Yeah. I would say it's pretty good to be fair. It looks like you get better outputs with open router directly when we test out the artifact like that's a lot more complex. But if you want to create something fun interesting and you want to use it for free then just go inside cursor and just code right there. Right. And if you need some help on that join the AR profit boardroom. So that is it so far. Yeah. If you're wondering when ch is going to be released to everyone inside the app that will come out I would say later today. So give it 24 hours. The API is available. I've tested it today. We've tested all of the different things we can do with it, how we can build it out. Honestly, for content creation, I would still stick to CL. For coding, Opus 4. 1 is definitely on the same level. And there been certain tasks that GP can't do that Opus 4. 1 can. So, don't think that GPT is the best things. Honestly, you're going to get similar or better outputs with Opus. Anyway, we've got trainings on both. So if you want to learn how to use Opus 4. 1, we got trainings inside the profit boardroom. Link in the comments description. Otherwise, you can go over to inside the AI profit boardroom as we also do five coaching calls a week, so you can jump on Q& A. We have 10 master classes here. On Fridays, we do a learning master class and weekly Q& A as well. We also have a PhD scientist who specializ in AI Dr. Jeff. So if you want to learn more about AI, this is the best place to do it. Inside the classroom, you have all these different courses. These are all the stuff that we use to grow our business. So you can see here, for example, we've got a course for agencies if you want to get more clients. We've got all the automations that I use for email content, social media, and videoations. If you just want to learn AI automation from scratch, we have a six week masterass with actionable homework each week to just level up and make sure you make progress. And then if you want to learn how to create a YouTube AI channel, then we have a six week road map right here that shows you exactly how I did it. Plus a bunch of cool AI SEO automations. Plus inside the community here, we just share our wins. We learn, we grow together. We have a great time doing it. success like Borat likes to say, as you can see right here. And it's a very active community, right? We're all just sharing, winning, learning, growing together. And we're just constantly updating and improving things as well. So feel free to join that link in the comments description. We're currently, let's see how many members we're at. We're at 100 1,182 members right now as I'm speaking. The price does go up at 1,200 members. So, make sure you sign up now before you miss out. Otherwise, you're going to pay more later. So, make sure you sign up now. Appreciate you watching and I will see you on the next one, my friends. 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. All 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 can 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 and inside NA10 it's probably one of the fastest and easiest ways that I know to do this. So what you can do please 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 chatbt5 really quickly. And at this point as well you might be wondering okay what's different why is chat BT 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 MA10 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 aentic stuff, right? So if you want to get started with this, what you need to do from here inside NA10 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 the 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 boarding. 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. Then you're going to 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 85 2025, the 8th of 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 can 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 AI profit broom 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 25 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. All 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 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 help for 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. 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 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 oneclick 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 other active workflows. One sagundo. 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 N10 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 NAM workflows inside here. So, let's add a resource file. We'll upload that. We'll call this basic GP5 agent. Super basic one cuz 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. 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 GP5. All right. So, we're 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 see how this is all going to be customized to 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 class 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 to say my keyword equals SEO training Japan. All 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 GPT5, the full powered version. Okay, so we're running over here. We'll switch that over. We're going to refresh the chat and put keyword equals SEO trainer Japan. Make sure the article is 1,000 words or more and we'll get it to start creating that. All right, cheap is 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/custom GPT that analyzes the performance of LLMs 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 tool plug in the API and everything else. Plexi store 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 because 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. The 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, GPT5 actually failed on some tests. The 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, the Claw 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 boarding. 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 training 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 chap 5 was a little bit robotic honestly. But there you go. If you want to switch it around, if you want to 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. Okay. 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. 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 Plexi bot. Go to NAN. 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 because 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 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? 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. Right now, this also comes with daily coaching calls. So, 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. Bye-bye. New Open AAI GPT5 Pro worth $200 per month. Today, I'm going to show you something absolutely mind-blowing. Open AAI just dropped GPT5 yesterday and there's a pro version that costs 200 bucks a month. But here's the crazy part. Even regular GPT5 builds entire apps with one prompt. I tested it seven different ways and what happened next shocked me. Hey, if we haven't met already, I'm the digital avatar of Julian Goldie, CEO of SEO agency Goldie Agency. Whilst he's helping clients get more leads and customers, I'm here to help you get the latest AI updates. Look, everyone's talking about GPT5 right now. It literally just came out yesterday, August 7th. And yeah, there's a pro version at $200 per month. That's 10 times more than chat GPT Plus. Sounds crazy, right? But wait till you see what I tested with just regular GPT5. I didn't just run one test. I ran seven brutal tests. And here's the insane part. I wasn't even using the Pro version, just regular GPT5. And every single one worked on the first try. No debugging, no fixing, no back and forth, just boom, working apps. If regular GPT5 can do this, imagine what Pro can do. Let me show you what's actually happening here. So, open a I dropped this bomb yesterday. They're calling it their smartest model ever. Sam Alman says it's like talking to an expert in any topic. But here's what nobody's talking about, the single prompt power. And get this, I tested regular GPT5, not even the pro version. And what it did blew my mind. See, before GPT5, if you wanted to build something complex, you go back and forth, fix this, change that, debug here, tweak there, hours of work. But check this out. My first test was insane. Using just regular GPT5, I asked it to create something called Treasure Dive Quest. One prompt. I said, "Make a game where you control a diver collecting treasure while avoiding sharks and jellyfish. " I wanted oxygen meters, treasure counts, random enemy patterns, bonus items, the whole thing. Know what happened? It built the entire game. Working parallax ocean layers, animated sea creatures, shiny treasure, even underwater bubbling sounds. The sharks moved, the jellyfish floated, the oxygen depleted. Everything worked. One single prompt. But I wasn't done. I needed to push this harder. Test two. An arctic penguin slide. I asked for physics based sliding, slope variations, fish counters, speed boost from ramps, snowy backgrounds, animated penguin sprites, snow particles. Guess what? It

delivered. The penguin slid down slopes. The physics felt real. The graphics looked great. Snow particles everywhere. Now, I'll be honest. I couldn't figure out exactly how to make the penguin jump and collect the fish at first. But here's the thing. It still built a complete working game. No errors, no broken code, everything rendered perfectly. But here's where it gets really wild. Test three was Candy Match Blast. You know those addictive match three games? I wanted timed gameplay, combo bonuses, power-ups with special effects, high score tracking, bright colors, pop animations, sweet sounds. It built the whole thing. The candies matched, the combos triggered, the timer counted down, the animations popped. It even added a cheerful background tune. Starting to see the pattern here. And remember, this is just regular GPT5, not pro. Just the standard version that everyone gets access to. Test four. Jungle Run Adventure. Infinite procedural terrain. Speed increasing over time. Banana counters. Life systems. Parallax. Scrolling backgrounds. Trees. Vines. Wildlife. Jump sounds. Animal noises. Built it. First try. The character ran. Jumped platforms. Collected bananas. Avoided traps. The speed increased. The background scrolled. Everything just worked. Now, you might be thinking, "Okay, Julian, these are just simple games. What about something more complex? That's exactly what I thought. So, I went harder. Test five, Space Miner 3D. Yeah, 3D using 3JS. I wanted a spaceship flying through asteroid fields, glowing crystals to collect, fuel meters, collision detection, neon sci-fi style holographic HUD lighting effects. Know what's crazy? It wrote the entire 3. js implementation. The 3D objects rendered, the spaceship moved, asteroids spawned, crystals glowed, fuel depleted, collisions detected, the whole 3D environment just existed from one prompt. But games aren't everything, right? What about real business stuff? Test six, a crypto metaverse landing page. I wanted a 3D rotating logo, animated call to action buttons, road map timeline, the works. It created a sleek, professional landing page. The 3D logo rotated smoothly. The buttons animated on hover. The road map looked clean. Everything you'd expect from a professional web developer. Test 7 pushed it even further. A tech gadget landing page with an interactive 3D model viewer. I specifically asked for glTF support. That's complex 3D model loading. I wanted users to rotate a 3D astronaut and damaged helmet plus pricing sections. Purchase buttons. It delivered everything. The 3D models loaded. You could rotate them with your mouse. The pricing section looked professional. The purchase button worked. Seven tests with regular GPT5. Seven wins, zero failures. And I wasn't even using Pro. Now, let's talk about what's really happening here. Open AAI says GPT5 is 80% less likely to hallucinate than their previous models. That means when it writes code, it's not making stuff up. It's writing real working code. They also say it's their best model for coding yet. And after these tests, I believe them. But here's the thing most people miss. It's not just about the code quality. It's about understanding intent. When I said underwater theme with animated bubbles, I didn't have to explain what that meant. It just knew bubbles should float up. Water should look blue and wavy. Fish should swim. The intelligence isn't just in writing code. It's in understanding what you actually want. Want to know something even crazier? By the way, if you want to learn exactly how to use this for your business, we have complete training inside the AI success lab. link in the comments and description. We've got over 14,000 members learning this stuff right now. Plus, you get all the video notes and over 100 use cases. Check it out. So, back to the crazy part. GPT5 comes in different versions. There's regular GPT5. That's what I tested and what free users get limited access to. There's GPT5 Mini for when you hit limits. And then there's GPT5 Pro. The Pro version uses something they call parallel test time compute. Basically, it thinks harder about your problems, takes more time to reason through complex stuff. Think about it. If regular GPT5 can build complete working games and apps in one shot, what can Pro do with its deeper reasoning? For 200 bucks a month, Pro users get unlimited access. No limits, no switching to older models, just pure GPT5 Pro all day long. But here's what's really interesting. Regular Plus users at 20 bucks a month, they get higher limits than free users, but not unlimited. free use open a I also says it excels at front-end coding it beat their previous best model 70% of the time at web development that explains why my landing pages look so good but let's be real for a second not everyone needs this if you're just chatting with AI asking questions getting help with homework stick with the free version or plus you don't need professor but if you're building stuff if you're creating if you're trying to launch products or automate your

business this changes everything here's what else is new. GPT5 can now connect to your Google calendar, your Gmail, your contacts. It knows your schedule. It can help plan your day based on what's actually in your calendar. It's also better at health questions. Open a I says it's their best model ever for health advice. It knows to flag concerns, suggests questions for your doctor, adapts to your knowledge level. The safety improvements matter, too. Less hallucination means more reliable answers. Better instruction following means it does what you actually ask. But here's my favorite part. It's unified. You don't pick models anymore. It automatically roots your prompts to the right version. Simple question, fast response, complex problem, deep reasoning. No more choosing between models. No more wondering which one to use. Now, some benchmarks only show small improvements over previous models. Like in math tests, GPT5 Pro is only slightly better than their 03 model, but remember 03 was already incredible. We're talking about improvements at the top end of what's possible. And in real world use, the difference is huge. Every developer using early access says the same thing. It plans better, adapts to your style, works more like a partner than a tool. GitHub, Jet Brains, big banks like BBVA, they're all reporting faster project delivery, smoother workflows, measurable time savings. Sam Alman said something interesting. He says switching back to GPT4 after using GPT5 felt miserable. That's a strong word from the CEO, but I get it. Once you experience one prompt app building, going back to the old way feels ancient. Think about what this means for the future. We're entering an era of software on demand. Need an app, describe it, need a tool, explain it, need a website, just ask. The barriers are disappearing. You don't need to know JavaScript, don't need to understand CSS, don't need years of coding experience. You need an idea. And honestly, regular GPT5 might be enough for most people. But if you want unlimited access and even deeper reasoning, that's where the 200 bucks a month for Pro comes in. Is that expensive? Sure. But here's the thing. I just showed you what regular GPT5 can do. Pro goes even deeper. More complex reasoning, better at handling massive projects. No usage limits. Compare it to hiring a developer or spending months learning to code or paying for multiple software subscriptions that do less than what you can now build yourself. the future just got a whole lot more interesting. Julian Goldie reads every comment, so make sure you comment below. Tell me what you want to build with this. Share your ideas. Let's see what's possible. And if you're ready to take this seriously, check out my AI profit boardroom. It's the best place to scale your business, get more customers, and save hundreds of hours with AI automation. We currently have 1,000 members crushing it. Want personalized help? Book a free SEO strategy session. Link in the comments and description. And don't forget, we have complete SOPs and processes inside the AI success lab. You'll get access to over 100 use cases, all the video notes, and join 14,000 members who are already using AI to transform their businesses. This is just the beginning. GPT5 dropped yesterday. I got these results with regular GPT5. Imagine what Pro can do. Imagine where we'll be in 6 months. The only question is, will you be building with it or watching others build? The choice is yours. Let's go build something amazing.