LIVE: Vibe Coding Agentic Operating Systems!

Hello. Hello. All right, we're going to be building out the agent OS, coming up some new features, doing a a gentic Q&A in a second as well. So, if you have any questions, feel free to ask. I'm going to get straight to this. Just going to restart, of course, [music] cuz it updates every single day. Getting the steps in as well. I'm playing [music] catchup today. I'm on the Oh my goodness. [music] We're on 13 hours into the day. 87 steps. No bueno. So, we'll we'll have to catch up [music] on that as well. I might have to clean this bad boy up. Pace myself with 10,000 today. And if you [music] got any questions as we go along, feel free to ask as well. Happy to help. >> [music] [music] [music] >> Hey, hey, hey. [music] >> [music] [music] [music] [clears throat] >> at all. Why do you keep ignoring my messages? I actually don't really answer messages on LinkedIn just cuz of the amount of the amount of stuff where it's just not useful and it's it's kind of [music] a waste of time. So, I don't find uh DMs on LinkedIn useful at [music] all. I don't really answer them. Uh, but if you do have questions for me specifically, uh, [music] feel free to DM me inside the AI profit boardroom. That's the only place I really answer DMs [music] personally. So, if you want to connect with me, if you've got questions for me, feel free to post in there. But yeah, on [music] LinkedIn directly, do I answer every DM? No, cuz I get like 10 messages a day of just nonsense. [music] >> [music] [music] [music] >> What [music] else you got here. Leah says [music] hello. Welcome here, Leah. Thanks for joining. Anna says hello as well. Welcome here. Thanks for joining. How are you everywhere? What do you mean? I guess you mean with my marketing, right? [music] Um, I mean, it's just like case of making sure you post across every platform and [music] making sure you post stuff that that people like and react to. [music] >> [music] >> very impressive. Thank you very much. [music] >> [music] >> Uh yeah, you can get it if you just search uh link building mastery or you can get it from [music] the Fine. >> [music] >> Heat up here. [music] >> [music] [music] >> Ah, it's a book. Um, yeah, the early circle is much better, mate. Much better. Hello. Hello. Welcome here, Click Stanker. Good to see you here, mate. Oh, you well? >> [music] [music] [music] [music] [music] >> May OS from but your speed is 10x mine. Uh, how do you do? Well, probably depends on the APIs you use. That's a big thing. Um, but usually when I test it, it's kind of just like a web front, right? So, the website's as fast as your as you can if you if you can load a web page in your browser, then you can load that normally too. So, I don't think there's [music] any issue there. Marker says what you do. Uh, we're just building out the Aentic operating system at all says been trying to get your attention. Um, yeah, it's not something we're interested in there, mate. [music] [music] >> [music] [music] [music] >> Come on. [music] >> [music] [music] [music] >> By the way, if anyone's got questions, feel free to to post them inside the chat about Agentic operating systems. We help you as much as we can. Today we're going to be answering some of the latest questions about Agentic operating systems. Now, if you're not familiar with what this is, this is basically a system where you can have all of your Aentic harnesses, all of your agents, all of your systems plugged into one place where everything is just one click away. So, for example, if we have a look at this system here, this is Hermes Asteros. We scroll down, we can see that it comes up with customized content ideas based on our competitors and our keywords, monitoring everything. And then what it also does is it makes sure that it gives us unique content angles and titles based on that. And we can then just plug this into our SEO system, our video agent system, our notebook for example. Um, we've also got a powerful memory system that everything learns from so that it has one system where it can plug all its memories, all of its learnings inside one place, get automatically updated. And then every time something new comes out, for example, like Jcode just dropped. Super powerful system where it can code way way faster, we've got a terminal, we've got a workspace, we've got the history, all plugged into one place where we can get the most out of this stuff, right? And and look at this stuff, right? You can create amazing uh websites, landing pages, whatever you want using this system, and it's all saved in one place ready to come back to whenever you need to. So, what I do each day is I answer the latest questions inside the AI profit boardroom. So, if you have questions for me, feel free to post inside the community link in the comments and description or just go to the aiprofit.com. I'm going to get straight into some of the latest questions, what people are building with this and what's working right now. So, let's get straight into this. So you can see here Muhammad has actually built out an amazing SEO machine based on our system. So what we actually do is we give people inside the air profit boarding our regentic operating system. It's like a zip file you can get and install and then people create and customize that and build out their systems from there and also they get the latest updates that we build in. So if you have a look at this system that Muhammad has shared like he's created an awesome system um where he's got Vera HQ and then it's got a full SEO machine. So for example as AI workspace a command universe operations automation builder. So he can actually build new automations based on this system over here. Pretty amazing stuff. And [snorts] he shared what he's learned. So, for example, he was saying what's working right now is he has a mission control that gives him one live view of his SEO, an AI workspace that shows all the departments of specialist agents, a command universe that maps out every department, agent, service, automation, life system in one place. So, shout out to Muhammad. Like, this is absolutely amazing. Well done and taking action and actually implementing it. I also really like the fact that he's basically taken the system, made its own uh improve the UI or change UI how he wants to and he's also got it in responsive mode too, which is absolutely amazing. That's one of the best things about the AI profit boardroom is like people share their journey. They share what they're creating. I actually think the command universe is something we could build in. So you can see here it's got the different operating sectors here and the different agents and tools it's using inside this system. Let's have a look at the next question. So, Luca's just posted this, by the way. Look how fast we reply. Luca literally just posted this and we're getting back to him now. So, he says, "I have a technical question. I have many, many chats, like 20 running simultaneously on claw. The problem I face and would like to solve is that they would know and interact what happens in one or the other. call it live sync or um Alisa daily between the chats in a single project as it's a pain for every new or old chat to explain what I did in other chats. How do you solve this issue? So, one of the first things that you can do is just have them all working from the same project. So, if you don't already, you can have them all working from the same place. So, if we create a new conversation inside Claude, we can just make sure they're working inside the same project folder. If you're not already doing that, definitely recommend it. Next up, what you could actually do is just have them put inside one place a daily log of everything they've worked on. So, for example, I use Obsidian for this inside our Gentic operating system. And our agents each time we interact with them, they log what they've done that day with the date. So, you can see, for example, Friday the 7th of August, here's what we're doing, right? And so when we're doing that, the great thing about that is that our agents understand what they've been working on previously across multiple conversations. And that doesn't matter which agent you use or which API use. You can just have them all sync up together. Finally, you can actually just fork the conversation each time you start a new conversation. And that way when you fork the conversation, it's picking up where the other one left off. And just simplify the amount of conversations you have. So for me, for example, I usually have like maximum five different conversations per day with Claude or different conversation threads. And then they're all just forks of each other, which means that they still have context of what they've been working on recently. So that's three different solutions right there. Make sure they're working inside the same project folder. Make sure they're log in a daily note into the Obsidian folder. And make sure that you fork the conversation each time you set up a new conversation and minimize the simply the amount of conversations you have with Claude as well. Great question there, Luca. Got a question from Brian about NAM workflow help. So for example, like this one. Anything you see us post, we just have it inside the NA10 section. So every NA10 workflow is inside the NA10 section. So you can find it inside the classroom for the NA10 folder. We've got another question from Leon which is any tips on getting Hermes agent to make better images and what Leon says is I am struggling with Hermes agent with open eye codeex or off connected to create decent images. I have the image generation tool enabled, but half the time I get these basic diagrams or skills and that sort of thing. So, there's two things that I use to get better images from agents, whether that's Claude or whether that's Hermes or whatever you're using. So, number one is just a templated prompt that I can use where I give it the image and I ask it to iterate the image based on what I know works. And GPT image v2 is the best generation tool. So, if you're definitely using that, I don't think you have any issues there. So, a thumbnail prompt that we often use is this one. Um, whatever agent we use to create the image based on that prompt above, it's very very repeatable. So we will get the same outputs no matter which agent we use as long as we're using the same API for generating images which is normally chat GBT image v2. The other option that you have is that you create a custom skill with Hermes and each time you iterate and give it feedback based on what you want and what you prefer. So for example, if you say, okay, next time make the colors more contrasting, make sure that it updates and saves the skill. So step number one is making sure that you get Hermes to create a skill for generating images. And step number two is to make sure that when you're generating images, it updates the skill every time you give it feedback so that it gets better and better over time. The third option that we actually use is our studio inside the agent OS. So we have an image generation studio inside the agent OS and we do the same with videos and images for Hermes and then it can generate beautiful images and we just type in the prompt that we want and it looks pretty nice each time. So that's another option. We typically generate the images with either Miniax or Grock plugged in to the system and those seem to be the best that work with Hermes when it comes to like an image generation studio. But GPT image 2 could work as well. So three options there. Number one is that you give it a templated prompt. Option number two is that you create a custom skill and update it every time. And option number three is that use the image studio or the thumbnail studio which we've got over here inside the Aentic OS. And that can create beautiful images like you can see right here. We've got another question from Warren, which is, "Do I need open claw if I want to use Hermes?" Absolutely not. You definitely don't need open claw. In fact, I haven't touched it for months simply because Hermes is so good and Hermes basically replaces the fundamental need for openclaw. So if you have Hermes running, you're happy with it, then you definitely do not need to install open claw. In fact, open claw can cost you a lot of time in terms of repairing it, fixing it, making sure it works. And from my own test over the last few months, particularly about a month or two after it launched, it just stopped working and it broke a lot. And you actually don't see many people talking about it. So I think that's why Hermes is is goated right now. We've got one from Teemo who says a question regarding the proactivity and autonomy of Hermes agents and says I've been using the Hermes system for some time to handle various tasks uh for a new project. The focus is marketing, social media, SEO optimization, blah blah blah. But he says, "Nevertheless, compared to Claude, I somehow expected more autonomy and independence from Hermes. Find it very difficult to for Hermes to handle tasks in a truly autonomous manner. For example, if I want 50 contacts research and qualitatively assess each day, it doesn't really work well or reliably. There is a specific skill for this task. Um, and as far as I see, it runs as a crunch job. I'd be interested to know which part of that process is not working on a daily basis. So for example, if we set up a schedule task with Hermes Oracle inside the agent OS, it tends to work pretty nicely and smoothly and it just runs like clockwork every single day. So it will get updated on a daily basis every 24 hours and we get new outputs from it. uh it's not that autonomous in terms of being proactive, but it is autonomous in terms of just making sure that it runs that system each day on a schedule without us. So, if you are struggling to get Hermes to run on a schedule, I'd be interested to know why. If you just want it to be more autonomous and and move uh forward without you, I would actually give it a scheduled task. And bear in mind, this is only if you want to. So only do this if you're comfortable. But what you could do is you could give it a task each day where it's like on a schedule every 24 hours improve all of my automations to schedule tasks with you so that you run more autonomously and proactively without me. You could ask it to do that. Now I don't recommend doing that cuz then it could go off the rails without you. But if you wanted it to be more autonomous, if you wanted it to be more proactive, that's something that you could do. Got a question here from Robert which is how do you update your Aentic operating system? So we're always adding new things, new interesting features. Number one, don't feel obliged to update. Like if you if you feel like you're happy with where it's currently at, you don't need to update. But if you do want to update, you can just get the latest version with the zip file inside the classroom. You don't need to reinstall it or set it all up again. Literally, there's an update.md file in the new zip file. So each time you want to update it, you can use that. Um, we got a question from the legend himself, Christian, who's a a member with us for months inside the community. So, shout out to Christian. And so, here's a question. Those of you running isolated products but wanting centralized orchestration, do you go to MCP server per client or a fully separate control plane? Not 100% sure what you mean, but basically if you're wondering, okay, do we have like separate MCPs for each client or do we use like the same MCP for each each client? Uh typically I would just use uh a separate MCP depending on the tool. So for example, if you need to operate a client's NA10, that's going to be totally different from the MCP that you set up for another client's NA10. And so like there's going to be different MCPS for each client. So that's the way that I would look at it is you will have different MCP servers or the same MCP server but a different connection depending on the client. So like to access one client's MCP server on NA10 is going to be totally different from another client's MCP server because they're like different endpoints and different access points. We got one more question which is you know once you've logged into the AI profit boardroom is there like a implementation guide on the agent OS. So yes so if you go to the classroom here and then you go to the agent OS section we have a full guide here for implementation but also we have a full video tutorial here as well. So, if you want to go really in depth, there's a 1-hour tutorial. If you just want the quick guide, here it is, right? And if you have any questions, you can post inside the community as well. So, you know, however you want the help, we've we've basically set up so it's as easy as possible to understand this stuff and get the most out of it. And then this is all available inside our AI profit board community. So, that's all of the questions from today. If you want me to answer your questions with a video tutorial and help you, you can post a question inside the community here. If you want to get our agent OS system, it's inside the classroom. Go to the new daily updates and you'll find over here. And then we add new daily guides and useful updates based on what just drops. Inside the classroom as well, you can get access to all of our best trainings, all of our best systems, and everything else. And inside the calendar, you can jump on weekly coaching calls, ask questions, get help and support in real time. Inside the map, you can meet people in your local area who are building out with AI agents like you. And this is all available inside the air profit boardroom link in the comments description or go to the air profum.com. Some people as well like they say you know doesn't run an agent operating system use up a lot of tokens. We actually have free models and free AI coders inside here. So for example we have the free AI code over here and we also have the local coding engine over here. Both of them both of them are free and that means you can run this without using up tokens or without costs. Also some people say well isn't this like super technical and difficult to set up? But actually, it's just a quick zip file that your agent sets up for you. So, if you're wondering, okay, can anyone else get the most out of this? Well, you've already seen examples today, but also we've got over 207 pages of wins of testimonials of people crushing it with this stuff. So, if you want to join us, feel free to check it out inside the air profitable volume. And thank you for watching. See you inside there. Can you create a guide on SEO agentic operating systems? based on us call it the SEO agentic OS talk through the system. So for example, the keyword research system, the deployment system for SEO content and also the system for video content too as well as a memory system that helps personalize your content, add information gain, make it unique. Heat. Heat. Heat. [music] Heat. >> [music] [music] >> Heat. Hey, Heat. [music] >> [music] >> Heat. [music] Heat. [music] >> [music] [music] [music] >> Do you register each client MCP into the orchestrator? creator individually. Um, no. So, I would I would be like, okay, here's my client's MCP. Um, and you just give access to that and you would [music] label it and make it very clear to the agent. Okay, client A, this is their MCP. Client B, this is their MCP. And then because something could go wrong quite easily there. Uh what I actually recommend you do is like you make it very clear every time you you speak to it like [music] listen use client B's MCP or use client A's MCP using the details I give you here and just have it ready to copy and paste cuz I think that's that's quite high risk. But I mean honestly for me personally I'm not switching between MCPs that much. Like uh [music] you know for example if I'm running let's say I'm running like SEO campaign for a client quite often like the the let's say the content that you create for SEO. It's going to be like your team that that post that for you. It wouldn't usually be the agent. Um but if you're doing it for your own websites then you'd be like okay well post content for the air prof you just reference the individual website but it depends on the context and the situation FS. What's up, my boy? Welcome here. Hope you're having a good day, mate. >> [music] [music] [music] [music] [music] [music] >> Heat. Heat. two. One >> [music] [music] [music] [music] [music] [music] [music] >> Can you give me a new system inside the Hermes agent OS tab. [music] [music] Oh yeah, Ramshshire, welcome here. Thanks for joining. [music] Any more features you can add to it? Heat. Heat. >> [music] >> Which Claude model do you use? Right now, I'm only using Fable 5. Honestly, Opus 5 is not very good. Fable 5 even is super slow. Like, for example, it's taking I mean, it's already taken like 13 minutes just to create one single guide, which is pretty wild when you think about it. So, it's still quite slow uh compared to where it was previously. I think that the quality of Claw's outputs have dropped a bit over the last couple of weeks. I don't know whether they're planning to build a new model and release it soon, but they should do cuz it could be a lot better. They could do much better. [music] Like 7 minutes just to fix this, which is wild. Heat. Heat. [music] >> [music] [music] [music] [music] >> back in a sec. Power. >> [music] [music] >> Heat. Heat. [music] [music] >> [music] >> Heat. Heat. [music] [music] >> [music] >> Can you do them in parallel though? [music] Oh, this is nice. [music] [music] This looks great. Can you also make sure that you're creating the guide in parallel? Can you also link to our other tools? So for example, if we want to create video content or if we wanted to create SEO content, it links directly [music] to that tool inside our agent OS ri. How do you see AI coding agents changing the future of content and SEO? Will they replace SEO professionals? Um, I think they'll just make it more productive. Like, you you definitely need humans. You definitely need common sense, but the people who learn AI right now are going to have a huge gigantic head start, you know. So, um, if you're using AI for SEO and you're using it in the systems that I'm showing you, you know, you're going to crash. You're going to crash, my friend. >> [music] [music] >> Well, SEO is a great time to be doing SEO because, you know, number one, you have an advantage on people who don't know how to use AI, and number two, it gets unbelievable. you know, like it's I've never seen results like this. And I'll show you some examples in a minute of what we're doing with AI, but it's it's absolutely unbelievable. >> Happy to help. Ra, thank you very much. Great question. Can you rename this to This looks great. Can you also make sure the this applies whenever it's resized as a window. Can you rename it to analyze social media and then come up with great content ideas based on our existing performance. Examples include Hermes Apollo, Hermes Astros, but I've already used those, so don't suggest those, but give me some more names like that. How can freelancers and small businesses start using AI agents? Uh, well, I have a lot of training on that inside the air profit boardroom, but I would recommend that you set up a agent OS. So, like all of the stuff that I cover on this channel, all the tutorials, etc., they're all aimed at people like you who who know how powerful this stuff is, but don't know how to use it. And so the systems that we show for example like you got Hermes Oracle which analyze your competitors gives you content ideas. You got Hermes Apollo which is a a voice powered AI agent. You have for example the memory system. These are all systems you can use that are automatic AI agents to automate anything that you want. So if you want a good system for doing this check out the agent OS inside the airoff warning. Have you started creating the guide? If not, do it now ASAP. I can't see it Yeah. Rim show I'm going to show you an example of a SEO workflow that you're going to love in a second and I'm going to show you proven results behind it as well so you can understand where SEO is going in the next two to three years. Today I'm going to show you the powerful Aentic operating system that has taken our website from zero to 325 clicks per day. This is pretty wild. 325 clicks a day from AI SEO using an automated agentic operating system that I'm going to walk you through in a second. And this is the SEO command center. So let me talk you through how this works. This is basically one system that researches, writes, deploys, and remembers with four connected systems doing the whole job. Live keyword research on your search console data. One-click deployment to five different websites. You could have more if you want to. An AI video pipeline and a memory vault that makes every piece of content you create completely unique and actually rank. And this is something that I've created due to the four tab problem. So picture how most people do AI SEO right now. Tab one keyword tool guessing from third party estimates like for example HS. Then you got tab two which is chat GPT. You're claude writing an article that sounds like everyone else's chat GPT article. Tab number three is a CMS where you paste and publish one poster at a time by hand. And tab number four is like some video app that has never met the other three. problem is with that you got four generic tools with zero connections and it's not very useful. So the system that I'm going to walk you through right now is a powerful system right here where you can have all of this in one place and it all links together. And the great thing about this is that it solves and breaks the cycle for good. So if you're using keyword tools right now, the keyword tool doesn't know what you already rank for. If you use AI for your business, your business doesn't really your AI often doesn't know your business, your numbers or what you worked on last month or your voice or your brand or anything else. And often the publish step doesn't scale past one website and nothing learns. That's the problem that most people have. Now, some people say, "I already use AI for SEO content. Isn't this the same thing?" But using AI to write is the easy 20%. The other 80% is picking the keywords from your real ranking data, deploying at scale, and feeding results back in so content gets more unique over time. And that's the part the other four tabs never do. So, what we have right here, and this is why it's ranking so well. I actually show you multiple different website examples. So we have uh multiple different websites as you can see all popping off in the same trajectory all getting awesome results right one 2 3 4 four different websites popping off like this and it's one loop with five steps and it never forgets. So this whole system is one loop. It looks at your real Google search console data and it finds pages um that are close to ranking. How does it do this? It uses the SEO system over here that's linked to Google Search Console. And this can basically allow you to One sec. pull in your latest keywords, search all of your sites, and then run research as you can see right here. And so the whole system is one loop. It looks at your real Google search console data, finds pages that are close to ranking and it writes new articles using everything it remembers about your business and one click then deploys them to five different websites at once and submits every page to be crawled. So Google reacts, the system measures what moved and then the important part is it writes what happened back into its memory. So next loop starts smarter than this one. So this basically means that every time you use your AI agents and the agent operating system, it researches, it writes five articles, it deploys the five articles, it measures over a 28 window from Google search console data and then it remembers that and writes it to your memory vault. And this is super powerful stuff. So for example, if we have a look here, we have this beautiful memory system that's basically taking in our latest memories here. And so what that means essentially is that it's writing every piece of content, every keyword that you go after, it's taking notes on it automatically inside your memory system so that when you create more content and do more research in the future, the content is more personalized. It's more useful and it is more relevant to you. Also, this helps you rank not just inside Google but also inside AI search engines. Let me show you an example. So if we take a look at this keyword, we are ranking over here and we're also ranking over here. So two times inside the AI as well as multiple times on the first page of Google, right? It's a really powerful system that you can use to get traffic and you can see the traffic that we've had recently for this one single keyword. And so the way this works is like the system pulls your live search console data. And the great thing about that is you're not using like generic uh systems to do this. You're using something that's actually personalized to you. And then it scores every query for striking distance. What does that mean? So what this means essentially is that you know it's finding the keywords from your keyword data that's actually near the first page of Google. How does it do that? Well, when we pull up the research here, we can run the research, right? So it analyzes the data and then we can search by which has no clicks but high impressions, which one is striking distance, which ones had low CTR. And this just gives ideas of like how we can automate the content and how we can optimize it right now. Also, if you're wondering, okay, well, how do I make sure this content is unique to me? Well, it's pulling in from your memory system. And so, the memory system makes sure that you're not posting generic content, right? It's all super personalized to you. The other thing that we do inside this SEO system is that when we create the content, when we generate it, we add in a unique case study into our system. So, we plug in the keyword, we plug in the content we want to create, we deploy that to our website. And if we have a look at an example that we've created recently here, you can see that we have a fully formatted article that takes my existing case study, I plugged it into the system. That means we don't have generic AI slop on our website. We use information gain. use real new content that nobody has ever seen before apart from me because it's my own experience. It's my own case study, it's my own thoughts that go into this article. And so that means every time we create a new article based on that keyword, it's pulling in unique case study data which means that our content is much more likely to rank. Boom. That's what we want. So quick one before we go straight into the rest of it. If you do want this system, it's inside the classroom of our AI profit boardroom community. Link in the comments description or go to a profit.com. You get the full agent OS system here which you will not find anywhere else. So you can't find this system anywhere else. And then also we have unique courses that you can't find publicly because we've posted them only inside the school and also you get weekly coaching uh and four weekly coaching course you can't find anywhere else as well. All right. So all of this is unique and you can't get it anywhere else apart from the AI profit board. So as we keep going through now let's run through the rest of it. So the other thing here as well is like one click just deploys this SEO content in parallel as well. So inside the system when we generate the content we can deploy it to our website and it posts across four or five different websites right and so it's all linked inside one place but it ranks multiple websites at the same time and each article we create is completely unique. So this one and this one totally unique not the same headline not the same content but it does pull in the case study data from our existing ideas that we had. And so if you look at the system, it's a beautiful loop because you got Google search console data here that gets scored. Then you create five drafts across five different websites. It's deployed in one click and it also gets automatically indexed and tracked using Google search console and indexional which is the API we use to get our content indexed quickly as well. And that means we can create content, we can get it indexed and also we can get it ranking very quickly indeed. That's what we want. And so [snorts] there's four different uh systems really inside this whole SEO agent OS that helps you rank. Number one is the keyword research system which I have shown you over here. Number two is the deployment system which you have over here. And then you also have the video agent. Now the video agent is really good because number one >> it number one this content ranks very quickly and number two it's really easy to create uh content like you can see right here. All right. So, this is a beautiful uh video that the AI created for us. So, I didn't even touch it. And you can see that it's made the full video step by step with a voice over uh beautiful animations and everything else completely with AI. Here's another example. So, this one is actually with an AI avatar. So, it's all edited together beautifully. We have the avatar, we have the content, we have the edit together, and we also have the voiceover. And all the research is automated as well with this full video director system. Now, if you're wondering, okay, why would you do video? Well, video is actually more powerful than blog content for SEO. Let me show you an example. So, if we come back to this keyword video ranks way more than the individual article, right? So, if we have a look here, we've got this one, we've got this one, we have, for example, all this content over here, and it's all ranking pretty beautifully for that keyword, right? Our blogs do rank as well, but they rank lower down than our actual video content. Why is that useful? It's useful because you can automate it using this system as well. So that is system number three. We've done the keyword research, the deployment, the video. And then we also have the memory system. Super useful because number one, it avoids you overwriting keywords you've already created because it's all logged inside the system. Number two, it helps you avoid AI slop because the content is personalized to your memory system which has all the information about you, your voice, your brand. And that's just using Obsidian. So it's four jobs, one loop, and the loop remembers and improves every single time you use it, which is super powerful. And then when we generate and deploy the content, it goes across multiple websites and it gets indexed automatically. Some people say well you know if you're creating content across five different websites like won't you get flagged but every piece of content is unique and also this is using information gain which means that we are pulling in unique case studies and ideas into the content so that it has never been seen before which means that it's much more likely to rank. Like Google doesn't care if it's AI content or not. It cares about the quality of the content and the quality of the content is superior to what any human on the planet could write. Right? It just looks way nicer. It's better formatted. It's beautifully created. this um put together in a way that a human never could because it's got like 300 rules when actually creates the content with the skill we use. And that's why our website has performed so well over so many different updates, right? There's been two different spam updates from Google alone this year. Plenty of human sites got hit. Our site just improved every single update. That's what we like. And [snorts] so that is the whole system. And so the vault as well, it pulls in the keywords, the results that we get. It pulls in the videos that we created and also articles as well. And you might say, well, a memory vault, it sounds complicated to create and set up, but actually no, because it's just a folder of notes and markdown files. Like that's all obsidian is. So it's super simple and easy. And so if you look at the old way versus the new way, the old way was like a four tab grind. You know, you had a a keyword tool from HS that was super generic. You could prompt, chat, GBT or claude from a blank page every single time. Super timeconuming. You would get generic fluff and that wouldn't actually be useful. And then also quite often SEOs skip video because they don't know how to do it or they just don't have the time to do it. With this new system with the agent OS, the SEO agent OS, you can uh get research running live on your search console data. Every draft opens up with your memories. You've got five unique articles per keyword with information gain baked into it. And then one click deploys five sites in parallel and submits them for indexing automatically. And the same topic can ship as a video and also a unique piece of blog content too. And then the results right back to the memory so that the content gets better and better over time. So if you want our full SEO agent OS system, you can grab that inside the AI profit boardroom. You could build it yourself, but it would take quite a long time. Spend about 3 to four hours a day improving and building this. So if you just want to get my system, you can get it inside the AI profit boardroom. Just go to the classroom and then go to the new daily update section. You can grab the agent OS here. We just updated it yesterday. you get a video tutorial plus a zip file to install and also I personally answer the questions inside the community every single day. So the beautiful thing about this is what I actually do is I answer your questions that you post which you won't get anywhere else and then I actually link to the tutorial that I've created for you and I break it down if you don't have time to watch this tutorial into a step-by-step guide as well. Right? So you get as much help as you can and support this as you can with this system. You can also jump on weekly coaching calls. You can jump inside the classroom here, but you get the full SEO agent OS system. And also inside the map, you can meet people in your local area who are building out with AI agents just like you are. Also, if you want a free SEO strategy session, you can book that in at goldie. Agency. We'll look at your website. We'll show you how to rank based on what's working for us. Our team will answer any questions you have on the call, and you can book that in at Goldie. Agency. So, thanks for watching, and I'll see you on the next one. see what questions we got here. Kelvin, hey Julian, so does this mean access to the training? Absolutely. Um, but yeah. Yeah. So, you get access to everything I've shown you today. Uh, would you mind giving more context? I think I've done that already today, but let me know if you need anything else. For finding ideas, what's best, Claude or Chat GPT? Uh, honestly, your brain is far superior to either of those for finding uh new ideas. I think that's the one thing that AI is not very good at. But I will show you a system in a second that helps me find ideas. Not not for that. I mean, bear in mind like you don't even need new ideas. You just need to find something that works, right? And if you want the systems for that, you can grab it inside the AI profit boner as well. We've got plenty of systems for helping you kickstart that sort of stuff if you're struggling with it. Yes, is international. We work with many international websites. Uh what would be the token cost for running the whole SEO agent OS? So if you are worried about that sort of stuff in general, we actually have two solutions for you. So you can use the free AI code over here and you can use local models as well. Right? So we have two solutions to make sure that you can run agent OS um for free. Do I need a clean installation for Hermes? Uh number one, welcome titer. Thanks for joining. Number two, for the agent OS, you don't need a clean version. You can use your existing version of Hermes and plug that into the system. And you can also ask Hermes to set up for you as well. That way you don't have to start from scratch and you can just use your existing setup inside the HOS. follow up. Do I need to set up a new folder for Obsidian for Aentic OS? If you already you you just need one single Obsidian folder. So, wherever you store your Obsidian folder, use that. If you don't have it stored, then just create a new folder. But you only need one folder. So you don't need to create a new one just for the agent OS. Um, is there a way for Claude to validate the install? Yeah, you can just say like check through every section, make sure it actually works and show me proof that it actually works. Um, and that way yeah, you force it to check every single section inside the HOS to make sure it's actually working for you. Uh, so you save time. That's what I would recommend. Thanks. Yeah, happy tub. Happy tub. Thanks so much, Shackle. Appreciate it. imagine waking up every morning with personalized ideas ready to go for your content forged from your own content and it's done automatically whilst you slept with every idea looking at your winning content and then giving you more and better ideas with you. Well, that's basically what we've created here inside this system. It's called Hermes Muse, and it basically looks at your existing channels, gives you new content ideas based on your winners. And I'll show you an example of how this works step by step. So, essentially, this is running with Hermes. And what we have over here is a system that automatically looks at my content, looked at what's winning, analyzes it every day on a 24-hour basis, then it actually gives it a score in terms of which um content is performing the best. And [snorts] then from there, it gives us more content ideas that would pop off, right? So you can see, for example, here it's actually looked through my existing ideas and what's worked for me previously and then come up with more ideas based on that. So the beautiful thing is it's like, okay, here's what's working and then here's what you should create next based on what's working so you can create more content that actually pops off. And the reason that I would recommend doing this is because most people are playing a guessing game, right? Imagine, for example, um having a team who never once checks your performance, right? That producer or that system is what most people do because they're too busy, right? So, for example, if you're trying to create content anywhere on social media or just in general, maybe even for your email list, the problem is that you're so busy implementing, you get you stop to look at what's working and come up with more ideas based on that. But the clues are all around us. And so, if we can look at what's working already, well, we have inspiration for the next idea and you pick an idea because it is actually based on data and actually working versus what feels right. Right? And this saves you a lot of time as well because you have an agentic operating system that runs on a 24-hour basis and then it gives you ideas for the winners for what's actually working. Also, what this does is it analyzes and sorts by what got the most attention. So, you can switch between what are the winners and what actually got the most attention and then also what should you create next. And the great thing about this is that it's based on data, right? And this is why we call it Hermes muse because Hermes whispers data, right? And whispers it to you before you wake up. So in the old Greek stories, creators didn't come up with ideas on their own. The muses handed ideas to them. And Hermes was the messenger who carried the word. Now Hermes Muse does the same job with your content. Every morning it's going to read from your existing uh content and then it gives you an understanding of how many views you got or how much attention you got and also how fast that is working right now. Then it blends it into one heat score finds your proven winners and an AI agent which is Hermes uh gives you new content ideas based on what's already working and it gives you for example ideas for your titles, for your hooks, for your formats. So you wake up to one tab as you can see right here with your ideas waiting ranked by which is the hottest right now. And you might say okay like well how many tokens does this cost to use? But you can actually use free APIs. So for example we we have a full system inside the aircraft ward. I mean you can get our full agent OS if you want to but you can use free API. So for example we have a free AI coder built into the system and we also have local models as well. So that means that you can get the most out of Hermes without using up a lot of tokens if you prefer to do it all for free, which is fantastic. And so if you look at the system, it's like, right, okay, here's what's working right now. Here's your dashboard with your analytics. Here's the trending topics that work the best for you recently. And then also, here's what you should create next because it is absolutely popping off, right? And so it's using like pred it's using your data and then giving you predictive ideas for the next piece of content. And the reason that you would do this of course is like if you have better content number one you can move forward faster. And number two you can come up with ideas quicker. You save a lot of time on research. And number three finally with this whole system you're focusing on winners. You're focusing on what's going to work next. So for example if we look at this system these are all ideas that would work really well for me. And I know that because I've tested a lot of these ideas previously. Um, and it's so powerful, right? And also, this is great because it runs on a scheduled crunch job, which means that it's scheduled on a 24-hour basis. And that means like we don't have to manually do this. It's just running um automatically in the background. So, it's coming up with new ideas. It's looking at your winners. It's analyzing your content. It's basically like a social media researcher that never takes weekends off and always delivers before you even wake up. Now, some people going to say, you know, I'm not technical. This sounds like a difficult build, etc. So, actually, inside our AR profit board community, we have over like 3,800 members inside there, right? And we've got over 207 pages of wins and testimonials from people learning and growing with AI automation. And so if I'm non technical and I can do it and if they're non technical and they can do it, then you can definitely get the most out of this too as well. Like look for example at Kurt. Kurt said the agent OS changed everything for me. Larry said just joined and wow. Right. Christine said great AI teaching. So a lot of people getting great results with this system. And if you look at how it loops around, so you don't have to do any prompting for this. When it loops around, it's essentially running on a 24/7 schedule, reading through my existing data, weighing through the attention that my content gets, and also the velocity of that attention, and then from there, it forges new ideas, and we have a board that's ready to go when I wake up and check the results, which is absolutely amazing. And so, we get proven winners without having to think. It just saves us a lot of time. Now also this links directly to our other systems inside the agent OS as well. So for example, when we come up with these new ideas, we can plug that into our video agent. So we have a video agent system over here that can give us new ideas and then create amazing videos as you can see that's fully personalized to me, my systems and who I am. And the same for you. It can create these videos fully personalized to you and all the systems that you have, right? So super powerful stuff. This is a I haven't literally haven't touched this. It's just fully automated using this system that you can see. And the same for example for SEO. If you want to create SEO content based on what's trending and what is working for you right now, you can just plug it into this system with a keyword, some ideas that you have as a case study, and then just click generate articles and it will generate and deploy content across your existing websites. Then we also for example have the memory system. So what this will do is automatically log the ideas that you get from Hermes Muse into your memory system so that when you're using Hermes to create content, it looks at your previous winning ideas and then plugs that into its system so that it can give you better ideas in the future. And so it's super powerful and it all links together as one ecosystem. And it's so much faster and easier than having separate tabs and everything else, right? So you can see what Hermes Muse came up for me uh came up and forged this morning in terms of looking at what content is working and then what we should create in the future which is pretty cool as well. And also you might wonder okay like will this work for me? You know maybe your your audience is smaller. It's all relative to you. So it's a formula based on your audience and and your data. So the great thing about this is that it's fully personalized to you. And so for example, if you get 10 times less views, well, it still works at different scales because it's based on a formula, right? So it looks at the attention you're getting and then reverse engineers. Okay, what is the winning topics based on what you're currently creating? [snorts] Now, the other cool thing about this as well is that we can just click on make the the video or SEO article and it will just create it instantly using this system. So if we click on this, we can just generate that instantly. You can see it's plugged it into this right now. We can click on that and then it will generate the image for social media like instantly. Super powerful stuff. All links together beautifully. And so we go from idea to the video director, the agent cambban for SEO and also the image generator which you can see being created over here. Saves so much time. And so if you look at the old way versus the new way with a system like this, the great thing is that the old way is that you would be checking all your data, squinting at analytics, scrolling through other competitors for inspiration, brainstorming titles in a a Google document. You'd be picking today's winners based on just how you feel instead of the data, writing everything from scratch, repeating the whole ritual tomorrow. That's why content creators get burned out, right? They get tired. They get inconsistent ideas. They waste a lot of time. With this system, it's all automatically done, right? So, the old system would take like 45 minutes. The new system takes zero minutes because it's done automatically for you daily, right? So, it scans your existing content. It gives you a heat score. It gives you new ideas based on what you should create. And then every idea arrives automatically titled, hooked, and scored. Each names the winner that proves its pattern as well. It shows you what it's based on. And additionally, in one single click, you can create a video, an article, or a thumbnail, right? Um, as you can see right here, we've just created this, and it's pretty much ready to go. And so, the result is that you save so much time, but you're also ba basing what you create next on a system that is proven to work because it's based on your data as well. And you might say, well, I prefer to rely on intuition, but if you do that, you you'll lose against people who do pick with data. For me personally, ever since I've used data to help me create content, it saves me so much time because I'm not guessing anymore. I'm basing it on what do people want? What do my audience wants? Right? And the thing to note here is like your audience has already voted. The Hermes Muse is just counting the ballots. That's literally all it's doing. And so it works in five simple steps. It listens every day. It weighs all your content, your data. It whispers to Hermes in terms of what should come next. It hands off everything inside this idea card. So you can just click a button and create whatever you want and then it restokes every 24 hours. It comes up with new fresh stuff every 24 hours. You can see it's generated a bunch of images here um based on that idea. How simple is that? It's a workflow. Really, really easy. And so if you want this full system, it's inside the AR profitable volume link in the comments description or go to the arprof.com and you can get this full system. Just go to the classroom over here and then you can get the new daily updates and you can grab the new agent OS version right here. It comes with a video tutorial. You can see when it was last updated. You get the zip file to install it and then we add new guides and tutorials based on what's just dropped. Inside the community, you can ask questions, get help and support in real time. And then inside the map, you can meet people in your local area who are building out with agents like Hermes and the Agentic OS. So, I've shown you that it's nontechnical. I've shown you that you can run it for free as well, and I've shown you how powerful it is because it's based on your data and it's actually proven to work. So, feel free to get this link in the comments description or go to the aprofitbomb.com. Thanks for watching. Let's see what questions we got here. Kelvin says, "Wow, thank you very much." Um, Tito says, "What are the capabilities it can do? Haven't seen this." Uh, well, I've shown you a lot of the features today, but if you if you just check out the latest Hermes Agent OS video that I published yesterday on my channel, you can check it out there as well. [snorts] Uh, Kelvin says, "I'm entirely new to AI. How much time do you think it would I need to get up to speed?" So, we have a full If you're a complete beginner, you can go from beginner to expert inside this section here. So, you can get a full beginner to expert road map if you want. Click Sanger says, "If you were me starting from scratch, what's the first move uh you'd make?" I'd start a 30-day challenge and just start building from there. By the way, uh Christian, if you want to check out our course on that, we have a full course over here, right? So, you can check out this course and that's based on what's working for me. So, you can get the full system for me over here. Shackle says, "A coder, can we build agents in there?" Absolutely you can, right? But I recommend that you just use Hermes instead. What else we got here? Milad says, "Hey Julian, is Hermes still the best open source AI agent?" Definitely the best open source one. Shackle says you can skip backwards. Yeah, absolutely. How is the setup for Apollo? Um, if you're struggling, Tito, DM me the problem that you're having, the screenshot, and I will personally help you. So, if you have any issues setting it up, DM me personally. I will personally help you. Yes, in school. That is the only place to direct message me. I don't answer DMs on any platform apart from the air profit boarding. Is Fable better than the new uh chat GPT? Absolutely. It is indeed. It's much much better. Way better. All right, I'm going to go in a sec, but I'm just going to do this last tutorial and then I'll head off, my friends. Today I'm going to show you the Hermes Oracle Radise, the trend machine that wakes up before you do. so that every 24 hours this agentic operating system with Hermes Oracle ranks the hottest stories in our industry and actually reads them out loud, finds content ideas and pushes it to our SEO system. So this is the Hermes Oracle system and it's basically analyzing our industry, pulling in the lo latest trending news and then coming up with content ideas for you. And this is based on what I would call the too late problem. So every trend has a golden hour. We've all been there, right? For example, in AI, the leak drops, the thread spikes, the timeline catches fire, you post about it this morning, you write the wave, right? Whereas, for example, you post about something 3 days later and you are the person explaining last week's news. Happens all the time. Happens. It's happened to me many times in the past, right? And so most people trying to get more leads, more customers, more attention for their brand, the the problem is that they're doing it the slow way, right? So they're doom scrolling, hoping the algorithm shows them the right thing at the right time. And often it doesn't. And so you just see what it wants you to see. And often that's quite late. And so the problem is that you miss out on all the new trending topics. And then you're too slow to create content about it. you miss trends and you lose opportunities to your competitors. With this system, the Hermes Oracle Radar, that basically ends this because you have a machine that hunts the fire hose every day before you wake up and hands you the most important stories worth posting about with your angle already written, right? And this actually plugged into Grock. So, we have Grock build plugged into the system. So, it's analyzing the latest news on Grock and then finds us the new trending topics. So for example this morning Hermes uh sorry chat Astra is planned to be released right apparently it's coming out next week and this is what's trending right now. Now you can see that automatically today Hermes Oracle found this information and then we can just draft a post like this for social media using the system or we can actually publish that content to our our website to start ranking for it as well. So we can see that it's automatically drafted the social media content as you can see right here. Um and what we can do is we can for example like if we just want to quickly create social media content we can just quote it like so. We can paste it in like this. Boomshack lacquer. We've just created uh trending topics uh trending content in like one single click based on what's popping off right now. Right? And so with this system, it's looking through the fire hose of information, which is literally like millions, like millions of of posts. And then you've got the Oracle, and it ranks what's trending right now, analyzes the most trending topics, and then gives us the ideas right here. And it can also publish SEO content to our website on that particular topic, or we can draft the social media content, which you've just seen me do a second ago. We can also reddraft that. So if you want to post something different on LinkedIn or you want to post about it later today, we can do that again in one single click. And a lot of people ask me like how are you everywhere? You know, a lot of people see me on uh Instagram or Facebook or LinkedIn or X whatever. Like they ask me like how how do you post everywhere? Or how do you create content everywhere? This is a system that we use, right? Because we can find trending topics, we can get attention quickly and we can draft the content quickly and it's all fully personalized to me, my systems and everything else. Also bear in mind this links to our memory system inside the Aentic OS which means that it basically pulls out the context and my voice and my brand and my projects so that it can create more personalized content for me in the future and that loops round so that when we're creating content either for our website or for social media it works really well. Now you might say okay show me some proof that this actually works. That's a fair question. So let me show you a couple of examples. So, for example, if we have a look at X, yesterday on X, we reached 549,000 people in one day using this system. It's it's pretty wild. And then if we have a look here, this is my website where I create SEO content as you saw a second ago. So, we're creating SEO content with the Hermes Oracle system here. And if we look at our website, that has gone from like uh pretty much zero clicks a day all the way up to 325 clicks a day with SEO, which is like 10,000 clicks a month, right? And so how are we doing this? Well, we're ranking for trending keywords. So let's have an example. So if we look at this system here, we look at this keyword, you can see that we are ranking here and we're also ranking here for this particular topic. And also when we're doing the system, we never miss out on a trend again. We can be super fast on the ideas and the content that we create. And it's very, very automated. It saves so much time. You can see a couple of other examples here. Also, if you're wondering, okay, what does the content look like once you posted it? So, here's an example of the article we've created, and it looks beautiful. actually pulls in the trended news into the article and then it's actually indexed with a tool called indexional so that it ranks on Google as soon as it possibly can do and also it breaks it down with tables with nice formatting with relevant uh keywords and headings and everything else and actually helps our content rank pretty quickly. And [snorts] so the great thing about this is you stop scrolling for trends and you get briefed like an operator with a system that improves every single day. Now if you want this full system it's inside the AI profit boardroom also comes with other systems that we used for this. So for example we have the memory system here we have for example Hermes muse that analyzes the winning content you've put out recently and then gives you ideas for content and also all of this system whether it's Hermes Oracle or Hermes Muse when you're using the system you can just click one button and from there you can create the video or the SEO article or the thumbnail right as you saw a second ago. So if we click on this, it's pulled in the prompt directly into our video system. And then we can click this button. It will actually generate a beautiful video as you can see right here. And so this all links together as one beautiful ecosystem to save you time and get you results in an automated way. And I've shown you proof that actually works. Some people say this doesn't work. I've shown you proof. Uh some people say this uses up a lot of tokens, but actually you can run it with free or local models. So we have the free AI coder over here and we have the local system over here. So those are two free alternatives if you don't want to rely on APIs. Also you might say isn't this time consuming or you know I don't have time to do this blah blah blah. So we actually have over 207 pages of wins and testimonials from busy business owners and entrepreneurs who a lot of them have never used AI before. Then they joined the AI profit boredom community which is where you can get this H and OS and they are crushing it now as you can see right Christine great AI teaching uh Jeremy this was an amazing response Dr. Fazal built an entire agent OS on clawed code. You can see for example Scott I finally found your OS. Sensational work mate. Right. So so many people just getting awesome results with this that I know if they can do it and if I can do it then you can do it too. You don't need to be a genius to run the system. And so if we look at the layers of the Hermes Oracle radar you've got the alarm. So it's a scheduled chron job that runs 24 hours with Hermes agents. Every 24 hours it's pulling in the latest news. Then you've got the eyes. So it uses Gro's live search to find the latest trending news and that's how it finds these new headlines as you can see so quickly. Then we have the judge. So the judge actually looks at the ideas that are plugged into the system and analyzes based on relevance um six different signals, right? So it looks at the signals of the content. It's like, okay, this one is the most important. So you actually see that it's got a score over here and it uses an algorithm to analyze the content idea and then order it by which one is most likely to pop off. So, if I looked at these manually, I would definitely say like the Gemini 3.5 Pro and the Astra headlines are the ones most likely to be trending right now and they are ranked number two and three, right? So, the system usually gets it right. And then also, you have the messengers. So, for example, in one single click, you can create the content for SEO, you can create the social media content, whatever you want. And again, like you could do this manually or you could uh get my system if you want to. But either way, I just want to show you the power of this to inspire you and to show you how powerful it is. And also, when you look at this system, like before it was one hour of doom scrolling and then you're still late coming up with ideas, right? So, a lot of people, especially people who are trying to find new ideas for content, like they wake up, they open X, they scroll, they hope to find useful stuff, but they only see what the algorithm decides to show you. They miss all the interesting stuff because it's all biased. Like quite often algorithms are biased to what they think you want to see, not what not to what's actually trending right now. And then you find the the trend like 3 days later it's too late and you have no record of what happened before. With this system, you have an automated system that finds relevant stories ranked by relevance. Uh it searches by keyword and then also you can customize it to you in your industry and it has history of what's happened previously. So if we go to previous days, we can see what the previous news was for those days and we've got a full history log of everything that's happened and also that gets automatically plugged into our memory system with Obsidian so that our agents understand what's happened in the past too and what's been trending recently as well. So people think like oh you know you need u some sort of crazy trend tool for this. No, you can just use Hermes with a beautiful UI like this and then you plug it into a system where it's ready to go in one single workflow. You might also say, okay, well, uh, usually these sort of tools are not very useful, but I've shown you the results that we've got and I've shown you the headlines that it's generated. So, you've seen proof that actually works. And other people say, well, I'd still have to do a lot of research. All your research is done automatically for you. And you don't even need to create the content cuz you can plug that into our SEO systems or into our social media systems to create the content as well. And so if you want the full Hermes Oracle stack along with Hermes Muse as well, we've also got Hermes Apollo, which is a a powerful voice agent built into Hermes. We've got the memory system that basically makes all of this better and better and loops around every day to make it more personalized to you. And we have all of these different amazing tools that you can get access to. You can get that inside the arrm community link in the comments description or go to the arprofom.com and inside this community you can post questions and I'll personally answer them with video tutorial. If you want to get access to our new agent OS, you can grab it over here inside the agent OS section. And you can see when it was last updated, you get the zip file to install and a full video tutorial if you want to go really in depth with this. And then also we add new daily guides as you can see right here to help you as much as we can. Also, inside the calendar, you can jump a weekly coaching call, ask questions, get help and support in real time. And inside the map, you can meet people in your local area who are building with AI agents like you. So, feel free to get this link in the comments description or just go to the apiprofitborn.com. Thanks for watching. All right, that's pretty much it for me. What we got? Shackles. Uh, is there a way to make clientf facing uh reports for SEO? Yeah, we actually have a full I'm limited on time so I got to go but we have a full system on that inside the SEO elite circle actually. So if you want to create uh SEO client reports automatically full full system on that inside the SEO elite circle. Thanks for watching. Bye-bye. Thanks library jester as well. I appreciate you man. Appreciate you post uh doing that every single day. You are an absolute legend. All right. Thanks everyone. Bye-bye.