What's popping? Today we're going to be building out some systems into Hermes, testing out some new models, building out the HOS. Let's get this party started. Hey. Hey. Hey. Daddy, daddy, daddy, daddy. Heat. Hey, Heat. Nah. Nah. Hey, hey hey. Pink Daddy daddy. Heat. Heat. Hey, hey hey. Who we got here? Welcome, bro. Gamer. Yo, Jim says, "What kind of treadmill you got?" I just got one of those ones off uh Shopppee. You can get them off Amazon as well. It's just like basic standing treadmill. Um doesn't go too fast, but it just fits under the desk. then have a standing desk. So, it's pretty good. Usually get about right now I think about 15,000 steps a day in which is good if you're working a lot. Would recommend. Good for the mood as well. So, we're setting up a few things. So, we got um we're working on setting up this local model here, making some improvements to the agent OFS. We'll be doing a Q&A in a minute as well, and then working on some SEO stuff, too. Heat. Heat. N. uh link in the comments description or go to the arprofitboard.com to get access. If you're already in the AR profitab community, then it's it's in the start here post right at the top. So, as soon as you land and we also send you a link to the start here post as well as soon as you join. Thank you so much. Right, Jules. Let's Let's show you. So, I assume you're already in the AI profit boardroom and that's why you're asking. So, as soon as you join the AI profit boardroom, it's right there. Right there. Agent OS is right there. Um, no, it's not on GitHub. It's not on GitHub. It's only for AR profit with rewarding community members simply because we just want to help community members. It's kind of like a nice sort of tool that we give away to members just to say thank you, you know, and just to share what I'm working on. Thanks Terrence. Yeah. Well, it's the same thing, right? It's the same thing. So, if you're if you're building that mission control, that's part of the Agent OS. So, you can plug that in. But, thank you so much. I really appreciate that. Super kind. But yeah, you build it out together in the the same zip file. So you can go from there. Heat. Heat. Yeah, there is. So if you go to the the zip file for it on the agent OS is designed for Windows as well. So you can use it on Windows. And then also if we check out Does it f itself? One sec. It has instructions inside there on how to use it inside Windows. So, it's got the Windows install and then the Windows state and memory section. So, you can use it for Windows, too. Just send a screenshot inside the air proper boardroom if you need help. Uh if you're struggling with anything, just send a screenshot inside the air profit board. Okay. Finesse. Right now is uh 7:30. Usually what I do is that if I have any issues, um, I'll go inside Claude or the agent that set it up and just be like, you know, mate, how do we set this up? And then it will go from there. So that's what I recommend for you if you haven't already. And then if you're still struggling, feel free to DM me any screenshots or anything like that. Google AI. Uh, so you would use a c you I think you can ah do you know what I think if you have Google AI pro, you can't use it inside Hermes because they stopped a warf integration. So with Hermes if you if you have for example like Twitter or Miniaax you can or even chat GBT 5.5 you can do images with the OF login but if you've got Gemini I'm pretty sure you can't because they stop people doing that with antigravity and everything. So I don't think you can use OAF with Hermes actually. I don't see a lot of people using Google Gemini with Hermes directly. Yeah, hyperframes is really good for videos. So, for example, if we check out the video agent inside the agent OS, it's creates some amazing videos with hyperframes. Like super powerful tool. Also, this one is pretty cool, too. created some really cool stuff. Did I build an additional system on a different port somewhere where your machine? No, I didn't. I keep that port open. And uh yeah, I mean like you can't build two ports on the same thing, right? So if you have two ports on the local host, not going to work. So you just want one system built on each port if you're running stuff locally. Otherwise, what you can do is set up on a VPS as well. Today we'll be testing out some local models, uh, one's called Quable, building out some more features inside the Agent OS, and then we'll be doing a Agent OS Q&A as well, as well as some SEO stuff in a sec. What do you Think about What do you mean by you want to control them? There's I I have some training about this in inside the AR profit boardroom on a tool that we've used before. So, feel free to DM me in there and we can help. You need a special tool for it. Back in a sec. Close. all the avatar stuff. So, we have the video agent inside the agent OS. That's how we do it. So, if you want our system, it's it's inside there. Um, it's it's a bunch of tools like I put together, but that's basically the system that we use. Nice. Thank you so much. Really appreciate that. On is pretty good. One of the best so far. Working on it. Nice. Hey Randall, good to see you. out. Heat. Heat. Just like Can you open up the first one you built? Also, just build one pig at a time. Awesome. Can you cancel any other local models that are running in the background or in Docker, etc., and then just have this one running and plug it into the agent OS? Heat. Heat. Yeah, we use some repos. So, for example, like Open SEO is inside there. And then we've also got repos like Paperclip inside there as well. That's all included inside the install as well. So, you know, Obsidian, there's a lot of there's a lot of open source stuff that we plugged into the system depending on what was useful and what people are asking for as well. How do I preview what's actually going to be sent in terms of the actual email to the actual person? Yeah, exactly. Exactly. So, I mean there's many things inside there, right? Depends. There's probably more that I've forgotten about to be honest. Even Hermes itself is open source. So there there's so many things that are built into it. But if you want to see like the full setup, um check out any of my tutorials on it or you know feel free to check it out yourself inside the air for Heat. Hey. Hey. Hey. Create a to-do list app. Heat. Heat. That's not something we've done, but I think we could work with someone like that. It's the same process no matter the industry. It's just about like, okay, you know, you follow the fundamentals, keywords, content, backlinks, and then you go from there. And I think no matter the industry, you can help. I still think you'd reverse engineer it. So you'd look at, okay, what are people typing around that industry and then go from there. So that's the way that I look at it. If you want to start, if you want some help like white labeling it as well, we can do that. Feel free to book in a call at Goldie Agency. Is Perplexi worth it? Personally, I don't use it at all. I'd rather have my own system and that way you don't rely on on anyone else and you you build out a system that improves every day. So that's why we create the agent OS. Personally for me, I wouldn't recommend uh using Publexi anymore. I just think it's it's better to have your own system with your custom automations ready to go and you you can't really do that with something like Publix. Heat. Heat. Well, I mean it depends what you want to do. What do you want to do? What do you want to automate? Based on that, I can give you some recommendations. create a guide on this and how you can use this system for link building outreach. create a draft campaign as well inside the system so that I can showcase exactly how that works with examples and a draft email outage campaign for a recent blog on the air profit board. question. Do you type your prompts to AI or do you speak into a mic? And how is the setup? Yeah, so I do a bit of both. Depends what I'm working on. If it's something where it depends on my energy as well to be fair, but if it's something where okay, right, I need to really give a lot of detail, then I'm going to use the mic. And then it depends on the setup. Like sometimes if I'm walking, it's easier just to type because you know you're kind of out of breath a little bit as well. So it depends on the situation. But yeah, I sort of switch between them. To be honest, most of the time, especially if it's something where it requires a lot of thought, I prefer to use Whisper Flow instead. Next one, automate. Okay. Yeah. Yeah. Yeah. Um, so yeah, that makes sense. So, I mean, I would probably use Claude for that. I would use a combination of Claude or do you know what? I would probably use the agent OS because with the agent OS you got the video agent that can generate the avatar videos. You have the system where you could build for example or or quickly create product descriptions and then for posting as well you got browser use. But yeah I mean anything you can do with Plexi you could do with I mean even Hermes agent itself could do most of this right. It could create the videos for you or the PDFs or whatever you want to create. It could write the descriptions for you and it could post them to wherever you need to as well because it's got browser use. So I think Hermes agent could handle all of that. So could Claude and then what you would do is whatever wherever you do it, you would create a separate skill for each part of that workflow. So for example, for coming up with the idea, you'd have a skill. for coming up with the description, you'd have a skill for actual creation of the production of of the product itself, you'd have a separate skill for that as well, right? And you would break it down into separate workflows. Just like for example, if we're creating a a blog post, we'll have a skill for creating the blog post and then we also have a skill for the keyword research. But yeah, you don't need for that. Plus, it's not really something useful, right? Like, for example, game would be more fun or something more interactive like a website, too. A It's a classic. Service was busy. Happens like every day. This I don't think anyone cares Snake game, like go for the interesting stuff. So, for example, like the Dragon Realm game would be great. The 3D racer game, stuff like that, you know, that's what you want to go for. Really, it was an idea that my friend recommended to me for the situation I was in. So, that's why I started doing it. But I mean, wherever you're at, I think you can showcase the journey. Uh, honestly, for me, I wasn't really that keen on it on the idea in the first place. And it really did take like a couple of years to start taking off. At least might be it might have been 3 years to be fair. And then even when I started, I wasn't showing the stuff I was working on, which was the mistake. So, if you're actually building cool stuff, you know, you could start showing that off on uh social media ASAP. And then if you're not building cool stuff, you should start building cool stuff and then you've got something to showcase as well, right? And it's more about like just documenting the journey. Okay. Make sure that you actually Back in a sec. Are you Heat. Heat. No, no. You, as long as you're a member, you get updates. If you ever left, then you still get the, you know, you have the agent OS setup that you've done. Um, but you wouldn't get updates forever. What exactly is your agent operating system and how does it work with open claw claw chat GPT etc. All right, we'll come on to that in a sec. So today I'm going to be running you through our agent operating system for Hermes and how we've basically taken Hermes all the power of it but organized it in a way that makes it 10 times more powerful and I'm going to show you all the best systems that we've plugged in how it works with open claw claw chat GPT and everything else that we built in here. So essentially the agent OS is like a mission control dashboard where you can orchestrate all of your agents together and a big part of it is Hermes agent because that is the most powerful AI agent in the planet especially when it comes to free open- source AI agents. So what we've got here for example this is Hermes uh a voice activated version of it. We can put it in wall mode and we can talk to it here or we can just have it inside the chat here. We can also chat with it or we can speak to it. Right? So there's two different options for using this. Now you can see the whole transcript here in terms of our previous conversations with Hermes Jarvis. And then you can see all of the stuff that we've actually built with it over here too. So if we want to pull up previous builds that we've created and I'll show you how that works in a second. This is all working right here. So how does this work? Well, basically we have a wake word with Hermes and this is just one tiny part of a big system that makes Hermes way more powerful because for example bear in mind like if you were inside Hermes desktop you just wouldn't have this functionality or for example if you were inside the terminal you can't see your previous conversations you can't design it as nicely and the UI is not that nice either and sometimes it'll break like you can see right there so the best way to use this is really to organize it in a beautiful UI where you have herby's agent as a back end but then all of powers that Hermes agent has. All of the tools that Hermes agent has, you plug into one powerful system like you can see right here. So, if we go into Hermes Jarvis and we're like, okay, open up Google and it will open up right there. Right? So, you can control our browser. If we like build a to-do list app, I'd like to build a to-do list app where it's like interesting. in attention grabbing etc. Um, we can also chat with it here as well. So, we don't just have to voice control it. We can say, for example, okay, build that to-do list app. And then you can see here that it actually start building out. Now, once that's completed, once it's done, you'll actually get a live preview of the app that you've created as well. And that's just one tiny little part of this. So, we can come back to that in a second. Now, we can also have this open in multiple tabs. So, the cool thing about this is, for example, you could have one section or or one tab open where you're building with this. And then also if we go over to Hermes Oracle, this will pull in the latest news. So obviously it takes the latest trending news, consults the oracle and then organizes it in terms of like what's the most trending and then we can draft social media content or we can publish a blog about it automatically to our WordPress websites. Now you can see here for example like it's taken the biggest news today in AI which is like Gro 4.5 entering private beta which is trending on X right now. And so what it's doing is basically looking through and scanning through all the relevant headlines to my industry. Automatically does that every 24 hours. And then we can publish content to our blog about those trending topics and get more traffic. So for example, this was a blog we published beautifully formatted, easily set up, fully automated in one click using this system here. And so it's great for social media content, especially where you've got trending topics and that sort of thing. So next up, what we have here is the studio. And you can see that we can generate images, we can generate videos, we can generate voice notes on the go whenever we want. And it's using a combination of miniax or grock. We can switch between them depending on which one you want to use. So if you're already on the Miniax coding plan, you can plug that in. If you prefer to use Grock, if you're subscribed to Twitter, you can use that, right? You need something that can actually generate images or videos. And so those two APIs work really well with Hermes. So just to recap, you have Hermes, the voice activated voice agent over here. You have Hermes Oracle, you have the studio, and then inside the chat here, we set it up slightly different to everyone else. So we have a normal chat where we can go back and forth with our agents. And this is all connected to our memory and that sort of thing. So if you just want to use Hermes agent, kind of like chat GPT, you can inside this section. But also what you can do over here is you can switch between different profiles. So for example, we set up North Mini code, which is a local model with Hermes agent. and we can chat to it anytime there. We also have a live talk section here. So, we can call Hermes agent and have a little conversation with it. And then we have a lead generation section over here. Now, what this means essentially is that we can use this as a SAS tool for outreach. So, inside this section, we just type in whatever type of leads we want to generate and then it automatically finds the email addresses, finds the leads that we want to contact, enriches the leads based on their information. We can delete or remove any from the campaign. And then once we've done that, we can go to the campaign section. We can tell the AI what the campaign is about. It will draft a email based on each of the people that we're going to reach out to from the lead generation section. And then we can get that campaign live. So for example, this campaign right here, we can click on activate and that is ready to go. And what you can see here is this. We can use this for like link building outreach. We could use this for getting clients, whatever we want. So we've got the voice activated version of Hermes. We have homes Oracle for the news. We have the studio. We have the outreach and lead generation tool. And then we also have mixture of experts which is a powerful system where you can essentially get higher than frontier levels of intelligence using a combination of agents working together. So for example, we've got Claude Opus 4.8 and GT 5.5 added to Hermes mixture of agents. We can type anything that we want over here and then run the panel. And what that's going to do is fuse two different models together to get two different answers and then it will actually look through the answers and give us the best possible output. So all this stuff that we've created over here was generated with Hermes mixture of agents. And that's how we can get better outputs using this system instead of relying on you know for example GT 5.6 it might come out or Fable 5 it might come out but there's no guarantees it's going to come back. So if we use this system instead, well, we can actually beat them on benchmarks and we can create better outputs, but we don't need to relay uh wait for anything. We've just got the system ready to go. So really powerful system right here for using Hermes agent. And then we also have a workspace where we've saved everything that we've generated with each of the models. So for example, with Grock build, we've got that over here. And we can look back through like everything that we've created with Grock build, which is pretty nice. Uh or for example, GL 5.2, to it's all segmented by whichever API we have. Uh we can add MCPS over here, but the main point here is like you get 10 times more out of Hermes agent in a way that's not possible for 99% of people because you've basically segmented each of these into its own little SAS store, its own mini app where you can get the most out of it. And then we have the memory galaxy. So we have context for all of our agents that we've built, which means that, you know, whether we're using Hermes or whether we're using Claude, everything gets automatically updated and organized into an obsidian vault. And then we can see all of our memories inside a second brain, visualize them right here. We can search through any of our memories inside this section. And this is like instant context. And the whole point of every single thing you see in here is that it's a system. Each one of these is a mini system that you can compat. And I think that's the whole focus here is like don't worry about the models, don't worry about what's gated, don't worry about Fable 5 or anything like that. Focus on the system because the system is yours, right? If you if you built this, we're running this locally. If you've built this and you can get mine inside the air off boardroom, if you have a system like this, well, that's yours to keep. Doesn't matter what happens. Whereas, for example, if a model gets taken away, like Fable 5, there's nothing you can do about that. You know, you're powerless and then all your workflows are gone. So you got to learn from that situation and build a better system like you can see right here. I mean for example we can build out these cambbans where we orchestrate teams of Hermes agents. They work together. We can have uh videos and blogs automated like so. We can have different Hermes profiles working together to create that content and it's just like okay plug in a quick task here and it all gets automatically done on the taskboard and then anything that I do dayto-day. So for example like generating images like these or for example uh creating music for example videos etc. All of this stuff we have separate systems for plugged into Hermes so that again everything is within one click and it's way faster. So imagine for example if you doing SEO the old way like you'd have to do the keyword research yourself then you'd have to go to another tool to generate the content and then you'd have to subscribe to HS to get like the latest data on it and then from there you might need a rank tracker and after that you might go have you know over to for example Google search console and then after that you have to publish the content to WordPress it's a mess. What we do instead is we set up systems like this where everything is inside one place and we can just come back to it whenever we want to. And I think that's the power of this system is like it's all set up. It's all ready to go whenever we need it and it's all one click away. So that's what the Hermes agent operating system is, why you should use it, how it works, etc. Um, you can plug in chat GPT Oorth into Hermes agent if you want to use Hermes agent with GPT 5.5 or you can use uh codeex as well if you're using Claude. Well, we actually use Claude to build this whole system. And then we have Claude over here ready to go. Um, and yeah, open claw as well. I personally I don't use open claw much at all anymore. I've actually hidden it from the menu, but if you do want to add open claw inside there, you can just unhide it in the settings, click save, and then open core is ready to go. We built out like a full studio for openclaw with like Twitter search, image generation, voice, video generation, and a live chat with it as well as well as like the normal chat here and the workspace. But honestly, do I use open call that much? Not so much. not so much. So I I personally prefer to just use a combination of Claude and Hermes and everything else that we've got inside there. So that's basically it. Now if you want to get the full system from me for anyone watching, feel free to get that inside the AI profit boardroom inside the classroom. You can get access to our latest tutorials on this stuff. We actually got the full agent operating system that you can download and install right here. So you can see that we update it daily. You get a video tutorial. We've got a zip file for installing it. We've got new daily tutorials as new cool stuff comes out with full video guides and step-by-step tutorials. If you're a complete beginner, you can go from beginner to expert inside this section. And you can get all of my best trainings and courses like you can see right here. Inside the community, you can ask questions and I answer them with daily video tutorials and I personally answer them as well as the rest of the community which is great. And there's always people online which means you can get help and support whenever you need it. You can also jump on weekly coaching calls and share your screen, ask questions inside the map. You can meet people in your local area who are building with AI agents. And there's a couple of things about the agent OS you might say. So number one, you might say, well, does this use up a lot of tokens? And the answer is no. Doesn't use up a lot of tokens because you can use free APIs, you can use oorthth, you can use CLIs plugged into Hermes agent, and you can also use local models. So if you're worried about that stuff, well, that's automatically fixed with all the solutions I just gave you. And then you might also say, well, I don't need all this stuff. That's totally fine. So you can just install um and switch off anything that you don't need. If you go to the settings here, you can just hide anything that you want. So for example, if we want if we don't want open call, we can hide that, right? If we don't use anti-gravity, we can hide that. So anything that we don't want inside the system, we can easily delete or remove or hide. And then also the final thing you might say is, well, it isn't this like pretty difficult and hard to set up? And I would say no. So I mean like for example if we check out all of our testimonials we have over 191 pages of testimonials and wins from the air profit boardroom and community members inside here. And so for example if we scroll down you can see that we've got so many wins and so many people using this stuff that it's absolutely amazing. So for example like hockey was saying they installed the agent OS they've explored it the system is amazing. Rick set it up within 30 minutes. You've got, for example, Hobing who said, "This has literally revolutionized how I work with AI agents." You've got Razer who said, "We're the best. Thanks, Raza." And so, you know, there's just so many people getting great results with this. I'm nontechnical. I can't code. I'm not a programmer, but I built this. So many people are using this because it's it's so simple. It's a system. We've tried to make it as non-technical and as easy to use as we can. So, I'll see to you inside the air profit warning. Thanks for watching. Thanks so much. Yeah, sounds good. Mhm. Where's the guide? Can you show examples of how you can use this for lead generation and email inside the guide as well. And then also, can you show examples of the drafted emails too? Have visuals for each section. Okay. So today we're going to be answering some of the latest questions that we have on the agent operating system. how to use it, how to get the most out of it, how to run it on multiple machines, for example, how you can basically automate and build anything with this powerful system that basically gets updated every single day, controls all your agents, orchestrates anything that you want, and has some of the most powerful features I've ever seen with this. So, for example, we can control local agents using this system. We've got Fusion built in. We've got all of the latest updates, and every day something new comes out, and every day we build something into it that just makes a whole system better. We've even got a second brain visualized into a memory galaxy so that we can see and visualize our memories and then also plug in context instantly into any agent that we want. And the thing that I would say here is, you know, if you've seen the situation with Fable 5, if you've seen the situation with GPT 5.6 where you can't even access it yet. Like the models are getting gated. They're less available, but the systems are something that you can build and then you can hold on to and then you can automate anything that you want and it doesn't really matter about models anymore. So, with that, we're going to get straight into this and start answering some of the latest questions inside the AI profit boardroom. This is something I do every single day. So if you want to ask me any questions and you want to see me answer them in a video tutorial like this, feel free to post inside the profit community link in the comments description or go to the air profile.com. So first question from Victor Agent OS multi system where would you install agent OS if you run multiple machines with multiple systems? So for example, let's say you have a Mac studio running open claw. You got MacBook Air running Hermes. You've got for example Microsoft 365 copilot on a work machine. You also got active subscriptions to chat GBT. Right. So one thing that I would recommend is that you do actually install everything in one place locally. It will just avoid everything being fragmented. It'll be much easier and simpler to manage. But if you do really want to like insist on just making sure that everything is in different places and all fragmented all over the place, then what I'd recommend is you use something like tail scale. Tail scale can link everything together. And for example, you could have your agent operating system set up on a VPS as well using tail scale. John Mesa inside the AI Profitable Ball community, he's actually got a full tutorial on it and it works really nicely. So if you if you do have a setup like this where it's super messy, fragmented, all over the place, no problem. I know I I I meet all sorts of people using AI, so I know how it is. Uh for me, I like to keep everything in one place and keep it organized and simple. If you don't want to do that, then you can have like multiple different computers, you can have your laptop, etc. all over the place. And maybe you just can't rely on a local only setup. So what you can do is you can use a VPS, you can secure it and then you can use something like Cloudflare as well. So, Cloudflare uh access or for example tail scale two good options managing this Now, one of the best things about this community is like so many people uh number one winning with agent operating systems. And what they do a lot of the time, for example, and I'll show you a great example in a minute, is that they customize it exactly how they want it to look, right? So, you might see my system. So, you might be like, I don't need this. I want to customize that. I want to change UI on that. And you can do all of that with our systems, right? So, for example, if you look at Sheena, who's an absolute uh legend inside the community, she's always sharing like amazing stories. So, shout out to her. And what she's actually done is turned her agent operating system into a selfunning lead machine, which is absolutely insane when you think about it. So, if you look at this basically, and um she's actually set this up like a full website, and the website looks amazing as you can see. Right. So, what this does essentially is it's an interactive AI demo of her AI agents that she's hosted, right? So, you can get started and see all the concepts and that sort of thing. And then it generates leads to her agency, which is insane. So she's basically showcasing the full power of her agent operating system which is you know built around our sort of ideas and systems but then customized to her. So shout out to her. And then she has basically set up a website where people can explore it and if they're like right I need this for my business or I want to get Sheena to to do this for me well then they can go through the website once they've seen the demo right and so I think that's just an a really really smart way to use this number one not just for yourself but also for your clients even the design of the website like it looks super nice it's clean nice branding etc so amazing work there if you want to see the full breakdown down of how she did it and what she did. She's got a great post and she's got example screenshots over here, too. Pretty wild stuff. Probably one of the best posts I've seen recently inside the air profit boardroom. And I think that is one of the best things about having a community like this is just you can work together. I mean, look at all the people she's tagged and shouted out here. It's like we're all winning. We're all learning to together. A rising tide raises all ships or boats. And when we share stuff together, we all learn and we grow and we we become part of a community where we're all winning together. So, it's fantastic. Great to see. All right. This is actually pretty cool. I I want to come back to this website. So, you can see here it says how it works and then you go to interactive and it shows like the whole demo of all the systems she's built based on the industry and everything. Look at this. And then you can click on this and it's a CTA to start working with it. Amazing. So we got another question from Rick which is about the Hermes lead machine we've built into the agent operating system. So that's inside the outreach section over here and Rick says you know just joined a couple of days ago and he's interested in starting to generate leads. Is this something that's available right now? And like William says, it's inside the lead section of the agent OS install. So just to demo how this works. Basically what you can do here is you can type in exactly the type of leads you want to generate and then from there it's going to start generating the leads as you can see right here. So it breaks down the domain, the company, their details, their status. So it actually validates like is this a real you know email that you can actually reach out to and then also you get the notes here. So this is enriched. So, it has details about the company that you can use for the outreach email. Now, once you've typed in the leads and generated a list like this, you can delete any or remove any that you don't want to reach out to. And then from there, what you can do is you can go over to the campaigns tab and inside the campaigns tab, you can see our live campaigns over here, right? So, how many people are inside the list? Um, how many emails we've sent, etc. Whether it's in draft or published or whether it's canceled and you can tell the AI what the campaign is about. So you can tell the AI okay I have this blog I want to reach out to these companies I want to get back links for this page for example or you can just allow the subject or you can write the subject in the email yourself manually so it's up to you you can get the AI to write it or you can get the or you can manually write it yourself then you get a live preview of the email and then from there you can just click on create campaign right so it's a full lead generation machine. And once you've actually got the campaigns live, you can see how many leads you contacted, how many are sendable. Um, it also skips anything that's too big. So like if the companies are too big to reach out to, no point reaching out to them. And so it actually removes them from the list unless you want them to stay in. So that's basically how the whole system works. But yeah, it's super powerful. We basically built our own SAS tool with that. And it was just because like the amount of people that were reaching out to me and saying, "Listen, Hermes is amazing. How do we use it for lead generation?" And this is how this is the only solution I've seen right now from anyone. You I haven't seen anyone else build something like this. So if you want to get that lead machine, it's inside the Halo S2. So great question from Yaba here and basically Yaba was asking you know if you have multiple businesses can you run them all inside the agent OS or do you need to create multiple dashboards? So we have quite a few running through this for example. So we have for example multiple websites. We have my agency. We have our community. We have all our social media running through this system. So you can use it for multiple different businesses at a time. No problem at all. And the way you can do that is you just have separate workflows for each business that you want to run. So for example, if we go into the SEO section, we can do SEO and this is for our community stuff, right? Whereas for example, if we go to the video agent, we can generate video content and that's more for our social media. And then for example, if we need to generate outputs for our agency, well, no problem. We can go to the Hermes section here and we can automate the outreach for our agency inside this section. So if you have multiple different businesses or different projects going on, no problem. And the same for example inside the Obsidian memory galaxy. So, inside the Obsidian Memory Galaxy, we have many different projects, many different things going on, but they're all organized into separate folders. And so, you can keep everything organized, even if you're working across multiple different projects or businesses or anything. Another question we got was from Bea, which is can the agent operating system be set up with free models using these free models and can you get good outputs with them? Absolutely. So I'll give you a few examples inside Hermes. You can link free models to Hermes. So for example we have north mini which is a free API and also a free local model. So you can get the free API from open router and you you can also get the free local model from Lama and then we have that plugged into our Hermes agent. The same for example if you go to the local section inside there you can build free stuff using local models and that works as well. And then with a combination of free APIs, oorthth. So for example, you could use Hermes with OAR and GPT 5.5 or free local models and free APIs. You don't need to pay for any APIs. You can just use free stuff. So we've got a question from Nova, couple of questions on the Agentic OS. So he was asking or they were asking, you know, I see use hyperframes above reotion. Is there a reason for it? And do all your AI avatars um run via H gen or consider local models? So Sheen has already answered this, which is awesome. So hyperframes is just HTML. Remotion is react and TypeScript. So for a genic pipeline, HTML is well more way more reliable. And then for avatars, she does the same as us, which is default to Hey Gen, and that's pretty powerful for that sort of stuff. So I found better I found better responses with hyperframes 2. I found that Remotion was a bit more slow and didn't look as good. And then for Hey, genen. Yeah, that's what we use and stick to. Next one we got is from Nick. Nick was asking about agent OS and Higsfield, right? currently in the process of creating uh walk through AI videos. He's got the agent OS up and running and he's wondering, you know, how could you use Higsfield with Claude? So, I I think there's a couple of options here. Number one is you could actually install a separate workflow and ask Claude to build it for you inside your agent OS. And basically, you would have a custom workflow just for using uh Higsfield, right? Higsfield. I think they have an API and they have a MCP as well. So just like how we've got the SEO section and the video agent section, you could have a section that says Higsfield and then you build that into your agent operating system. So that's step number one or option number one. And then option number two is that for example with Claude, you could give Claude access to the documentation for the API, the MCP and the API itself for Higsfield and then Claw could actually control Higsfield directly that way. So there's two different options you could use for the agent OS. Either give it to Claude directly or build your own custom workflow. If you want to build your own custom workflow, it's very simple. It's just like you tell the agent that built it for you what you want to create, how you want it to look, you tweak, you iterate it, and then eventually you get something that you like, which is what we did with pretty much every single workflow inside there. Wow, look at this. So, Robert is absolutely crushing it. He said a big thank you to Julian and this group. You know, he started at zero four years ago. Struggle was real, pretty difficult. Had some ups and downs along the way. So, sorry to hear about that. Sounds like a tough journey, but now he's at this point, which is absolutely wild. So, congrats on your success. Like, that's absolutely amazing, inspiring stuff. Fantastic to hear about your story as well. And, you know, credit to you for just taking all the action and working hard and keeping on going down this journey. I really respect it. Thank you. again. Like when I see stuff like this, it blows my mind. It's just, you know, it's inspiring to see stuff like this, right? It's inspiring to see people's journeys. And I think that's the great thing about having a community like the AirPuff Border is it just brings people together where we can all share our stories. It filters out all the noise and it's a way of connecting in a much better way, which I really like and respect. So we got another question from Victor about you know how can you use Hermes kind of like a voice activated agent that you can control and build stuff with. So we actually have that inside the agent OS as well over here. So if you go to the Hermes Javier section you can basically speak to it. You can switch off real time on and off. So you can basically have it listen to you. So you can see it's responding directly here. It does have the voice. I'm not going to have the audio on right now just cuz I don't think it will sound very good. But you can see that it's literally listening to us in real time right here. Right, which is pretty cool. And then if we scroll down, we've got the full conversation and we've got all the builds and the creations we've made. We can put it in wall mode as well. And then we can have a wake word as well. So this means we can have a word here that actually wakes it up. So if we say like Hermes wake up, it will respond to us. As you can see right here, it's it's glow since we gave it the wake word. So it's pretty powerful stuff. So we got a question here as well uh from John about you know how secure is open claw is it safe to use etc. Here's the way that I look at it. I mean number one I don't really use open claw that much because of those issues. Number two I keep everything local so that it's all sandboxed away on one machine. And number three I think if you're not sure don't use it. So, for example, if you're not certain about open claw, then don't use it. You know, I think that's always a good sign as a heads up, you know, intuitively. If you're not sure about using it to all or you're not sure about how secure it is, don't use it in the first place until you are comfortable with it, until you understand the the power of it completely. So, that's the way that I would look at it. And then when it comes to agents, if you want something that's more stable and reliable, then just stick with claud. You know, you can use inside the agent OS, you can use claude CLI or you could use GM 5.2 CLI. And the CLI options are a lot more stable and reliable than relying on something that's open source like open claw. So that's the way that I would look at it. You don't have to rush into doing anything, but I think it's always best to rely on your intuition and it's down to each person. So, for example, someone who has a lot of experience with agents, they're not going to worry about using open claw at all. Someone who's new to this and a beginner would probably have a lot of doubts about using open core and they should listen to that and just stay away from it, you know, until they are comfortable with it. We got another question here from I think it's pronounced J, but I'm not 100% certain. So, sorry for that. I'm building a board game app for friends say uh developing a game. Any tips on how to make good games with AI? So, one thing that we recently used is this open- source GitHub skill. It's called 3JS game skills. This seems pretty good. When we installed this into Claude to build games for us, the quality of our games became a lot better. And I'll show you an example. So, for example, if we go into, let's have a look here. I think probably Hermes mixture of agents would be a good example. So if we go to Hermes mixture of agents, we built out all this different stuff using the 3JS skill. A lot of it looks really cool. I mean like that's really cool as you can see right here. And then also we have this one too. And this one too, right? And so like you can see the quality of this stuff looks pretty cool. Really interesting to play. Definitely helped level up the stuff that we're creating if it's like a 3D generation. So I'd recommend that to you too. Really good skill and it's free and open source to use. If you want to see more of our creations, what we built, we actually got every model and what we built with it on Goldiebench. So, you can see, for example, if we scroll down here, you see all the examples and then if you want to test them out and have a look yourself, you can check them out right here. So Daniel was talking about, you know, GT 5.6. It's in preview. It's not released yet. This is why I'm focusing more on the system than the model. So with the agent OS, we can achieve better levels of intelligence than what's already out there using mixture of agents or sanafugu or fusion because they're all panels of agents working together which means you get better outputs overall. So that's what I'd recommend for anyone watching this is just focus on the systems, not the models. Because the systems yours, but the models can get taken down or removed or blocked at any time. So it's always better to focus on the system instead. and that's basically it. We've answered every single question from the AI profit boredom community. I do this every single day as I mentioned. If you want to get the agent operating system that you saw today, you can get it inside the classroom. Just go to the new daily updates and you'll find the agent OS section over here. We update it daily. You get video tutorial and a guide on how to install it. And then you get the zip file to install it too. And anytime there's something useful that comes out, we create a video tutorial and a step-by-step guide on exactly how to get the most out of it. And also you can post questions inside the community. Also, the cool thing about this is you don't just get help from me, you get it from everyone online. So, for example, there's 3,800 members inside here and there's 113 people online right now, which means 24/7 you can pretty much get the answers that you need to win with AI. Now, inside the calendar, you can jump on a wheel coaching call, share your screen, ask questions in real time. On the map, you can actually meet people in your local area who are building with AI agents like you. And then inside the classroom, you get access to all of our best training. So, that's all inside the AI profitaboom link in the comments description or just go to the AI profitab.com. Thanks for watching. Let's see what questions we've got over here. My agents manage 20 servers over tail scale. I recommend it. Nice. That's pretty cool. Need 101. Uh yeah, I mean you can get a coaching course inside the profit board. It will help you a lot. Has anyone tried to build a harness like Fable 5? Well, I mean the harness would be clawed, right? The model is is Fable 5. So it's that's the way that I look at it is like Fable 5 is just the model, but the harness is is Claude code for example or Hermes agent. Thank you very much, sir. There is a you can go to the AI success lab and we have a free course there. Yeah, we might do that in the future if there's enough demand for it. No, I think we've talked about this many times, Sabre. Like the office visualization number one is not very good and number two it doesn't actually add anything useful. So, like I think I spent about an an hour or two hours trying to set it up. I know we've talked about this many times and I think you've suggested it many times, but it's not that useful. Like it's it's just not going to help anyone uh with the office visualization as nice it is as it is. I mean, for example, you do get that inside Hermes workspace. You get the office visualization, but it doesn't sync properly and it doesn't work properly and it's not that useful. So, I wouldn't recommend it. Another idea, give Javis more MCP and skills. So you can give um you know you can train you whatever you want to customize. So let's say for example you have ideas like this you can build those directly into your system. So like you can customize it however you want. So if you like right we need a office visualization or we need for example a system where we have um Higsfield MCP plugged in. You can build those like there's nothing stopping you. What if we get a main chat section in the agent OS? We already have that. So inside the agent OS here, you can see the agent mastermind and then you can see that we can have our agents working together and orchestrate all the AR models. Yeah, we already have like three orchestration systems right there and look for the best model to handle each thing. Yeah, exactly. So that's what we do. So, for example, if I get an idea from the agent mastermind and I'm like, "Right, we need to build this." And I think that probably Hermes is the best to go off and do that. We just go into Hermes and we build it. That's the way that I look at it. I don't know, maybe this will be useful. Yeah, you can already do that. You know, you have a main chat for everyone already here. So, just go to the agent mastermind section. Is Hermes secure? Well, I mean, if you're asking that question again, like it seems like you might have doubts. And if you have doubts, I wouldn't use it, right? Only use stuff that you're comfortable with. So, if you're not comfortable with it or you're like, not sure if I should use this or I'm not sure if Hermes is uh that secure, don't use it. Right? That's the way that I look at it. Until you're fully confident with using these tools, it's better to stay on the safe side. Do we have to add information inside of the models outside of the agent OS like sole index? So like if you want to add for example the solemn MD file to your agents just go to the manage section inside the agent OS and then you can manage your Hermes agent profiles and the config for each one and that way you can easily for example edit the solemn MD and everything else right so you can edit description you can edit the solemn MD you can manage the skills and tools for each of your agents like you can see right here so you can switch between those inside the agent OS you can also go inside the chat directly and just say, "Hey, change this in your soulm file." And it will change it for you inside the Hermes chat directly here. I mean that you you've answered your own question there, right? So if if you think your Hermes agent is working fine, you don't need to change anything. The only time you change something is if you feel it needs to change. That's the way that I would look at it. You want to keep it as simple as possible really. So today I'm going to be showing you Quable 27B coder which is uh new coding local model and I'm going to show you exactly how it works. Now we actually built some interesting stuff with this far more than what we usually create with local models. So that impressed me in the first place. Here's for example a landing page that we created locally using Quable and it was pretty easy and simple to create. It moves in the background. It looks better than like 99% of those sort of uh local websites that you usually create. I wouldn't say it's anywhere near like Frontier level, but at the same time like it can create some pretty cool stuff better than what some of the things that I've built with other models. And I'll I'll show you some example comparisons in a second as well. and we'll look at how it compares versus other local models I've tested recently. Like for example, Onif or Quifos. And I do think these local models are getting better and better. And this is one of the best ones I've seen recently. So this is a cool little game we built out. Here's another one. The the thing that I will say here is that if you look at this, it kind of feels like last year's Frontier, if that makes sense. So, it's not like going to start competing with Opus 4.8 or Fable 5 tomorrow, but it can build some pretty cool stuff. And this is actually better than I expected it to be when it comes to to building out with these local models. So, how does this work? Well, essentially what we built here is Quable 527B coder. It's open source. is free to run and it just dropped on hugging face. Pretty good so far. Just got updated end of June and it's got a Quen 3.627B base. So that is the base for creating this So, it's free to use, free to use locally, and we actually ran it with Apple MLX, which is a free open-source setup just for using local models. So, we can run LLMs from hugging face using the system. And that's how we ran it. You can't get it through OAMA. And if you're wondering how it performed on the benchmarks here, yeah, it did pretty good, right? I would say in terms of local models as far as they go, it's right at the top of the leaderboard from everything we've tested out recently. So, for example, recently we've tested out Gemma 412B, Quifos 9B, or N 1.0. And I would genuinely say like the quality of stuff that we got from ONIF is nowhere near the same level as the quality of stuff we got from Quable. Loving these names, by the way. So, it's actually my favorite local model so far. I'm on a Mac Studio Apple M4 Max, 36 GB of memory. When I actually run and create stuff with this model, I can definitely feel like the whole setup runs a bit slower, but at the same time, it can run in the background whilst I do other things. So, it's not like going to completely slow down your whole setup. So, we can still, for example, like run claw desktop whilst this was running before. Now also something that we did is we plugged it into our agent operating system so that we can generate live previews whilst we're building with this stuff. So for example if we give it a command well our local engine inside the agent operating system runs with Quable. So we can run this on free models now like Quable 5 and then when we say build something out it will actually preview it so we can see what we've created and then open up the preview and everything that we create is plugged into our workspace. So for example that 3D dragon game that we just talked about that is available to preview inside our workspace right here and then we can come back to everything that we've created which is pretty cool. Also inside the workspace, we can open it up inside a new tab or we can get the code from it directly. But that's basically a really cool way to build with local models, preview what you've created and then run it on free models as well. Now obviously Quable kind of a reference to Fable 5, but that kind of oversells it. So, it's based on Quen 3.627B, which is a strong base model from Alibaba, and it's got a fine tune as well. So, it's basically Quen 3.627B with a flashy quable coder jacket. And then if you're wondering how to run it, so you can't run it from O Lama. You would run it with Apple MLX if you're running it on a Mac. But yeah, the stuff that I built with it was pretty nice. The only problem was that it's a lot slower. So if you were comparing it to, for example, like Quos 9B, Quifos 9B is way way faster than Quable 27B. So that's something to be aware of as well. It's like yes, it builds better stuff, but it's going to slow you down. However, it's top of our leaderboards when it comes to Goldie Bench and the local models we're testing out. And this is something I'm just going to keep building out over time so you can see the comparisons and see how they perform. The cool thing is as well, like you can run your Agent OS now on free local private models. You don't need Wi-Fi to use these as well. And they're just ready to go whenever you need them. Now if we have a look for example at the same task with Gemma 4 Gemma 4 12B coder totally failed on that task. So if we click on this for example this is the same game and it just it just didn't work. It didn't work at all. The same for example with quos quos 9b we tested the same prompt and it just didn't work right it it totally failed. So, out of everything I've tested, this is the one where stuff we've created actually works fulltime. And you can see the prompts here on Goldieb if you want to see how they compare. Even like the landing page itself looks pretty nice, pretty smooth to use, pretty clean. Doesn't look like generic AI slot. And the moving background is quite nice, too. So, is an impressive model from everything I've tested so far. So that's basically it. The thing that I would say with all this is that local AI is moving fast. Models are changing all the time. There's better and better stuff that I'm seeing coming out pretty much every single day. So I feel like it's ramping up right now, especially with open- source models coming out like all these new updates from China, which is pretty cool. So, Quable is one model, but if you want the agent OS, which is the operating system that runs any model local frontier from one dashboard, here's what you get inside. So, you get the local Hermes agent engine which can run free local models. You got agent Cambban in there. You got Goldiebench style testing. We actually have token efficiency playbooks as well. So, if you're using paid APIs, you can make sure that's more efficient and use less tokens. We have every CLI plugged into there, a workspace with every build saved and a memory of your whole business built with Obsidian inside the AI profit boardroom. So if you want to get the full system for us for the agent operating system, you can get that inside our community link in the comments description or just go to the air profit.com. Inside the community, you can ask questions, get help and support. I personally answer every single question every single day with video tutorial. And then inside the classroom, you can get access to all of our new courses and free trainings. as you can see here. So, for example, if you want to go from beginner to expert, you can get that inside this section. If you want to get our agent operating system, you can get that over here. If you want to learn more about the new stuff, we have new videos, tutorials, and guides released every single day. We date them so you know that they're actually new. And then inside the calendar, you can jump on weekly coaching calls, get help and support in real time. Inside the map, you can meet people in your local area who are building with AI agents. That's all available link in the comments description or just go to the arpuff.com. Thanks for watching. So today I want to show you a new powerful system that we're using with Hermes agent to basically automate and build apps in one single click. And the way this works is that we can drop an idea right here. Then we can shape it with our plan. From there we can approve or deny it. So for example, if we look at this plan right here, we can click on approve and build. And then from there, it's going to start building inside the implementation setup. And then we can view everything that we built on this side. And we actually get a live preview with the idea, the classification, the plan that was created. And we can also start or delete stuff that we don't like. Right? So it's pretty cool as a system. And also it means you can go from idea to implementation really, really fast. As you just saw, we went from idea to implementation in like one or two clicks right there. So this is one of the powerful systems we built into our agent operating system which means you have claude, we have Hermes, we have everything else built inside one place and the great thing about that is that it's very easy to orchestrate our agents. Now, here's something else that we actually plugged into the system, which is we can actually ask our AI agents in a group team chat. Okay, give me a great idea for this app that we're building. And then our agents are going to talk among themselves, read our obsidian vault as well. So, read information about us to get the context. And that means that they'll come up with personalized ideas based on me, my goals, what I've worked on recently and all the memories inside my second brain, which then is going to coordinate between Claude, Hermes, Gemini, whichever agency got plugged into the system. And then from here, once we actually get a good idea. So for example, based on the SEO app that we asked for, it says quick SEO gap idea creation, it's going to plug into our pipeline and from there we can shape, implement, build it, right? And the cool thing about this is as well, if any of these ideas are not very good, you can delete them. Right? If you're like, I don't like that, let's delete that. You can, no problem. If you really like the idea, you can actually star it. If you want to check it first, no problem. Cuz what you can actually do over here is you can decide if you want to approve or deny this plan. So, if we have a look at this one, we can see that we can approve and build it or we can deny if we don't like it. Then from there, we can actually implement it. And from there, you actually get the shipped and filled section over here. So that everything that you've created and built out is ready to go and you can come back to it whenever you want, which is pretty amazing itself. Now also what we can also do is click on the gallery section and we can see everything that we've built in one single place. So the amazing thing is that we can build this huge collection of tools and ideas that we've created, open them up whenever we want. And like some of this stuff is super nice. Like check out this website. Like pretty nice. Here's another one. And the way that we've actually done this is we plugged Miniaax into Hermes agent so that we get a good balance between speed and intelligence. And also because it's a a flat rate coding plan with Hermes agent and Miniaax, you don't have to worry about tokens, right? I've never run out of tokens with Miniax. So I can build wherever I want. I can create anything that I need to. I can move really, really quickly. I can use Hermes agent to help me. and then I can build stuff and implement it really quickly. So this is the app builder system and basically you can drop a sentence into the agent OS. So for example it could be like a habit tracker or meditation timer. Agents classify it, draft a plan and after one approval from you, they build a genuinely working single page app with every button wired in, real data, everything plugged in right there. All right. So you capture an idea it the agents plan it you approve it they build it and then it's shipped. So if you look at this section all you have to really do is approve it because even for the idea itself your agents can come up with the idea from the group chat. And the point of this as well is like if you've looked at for example Sakana Fugu or Fusion or Hermes mixture of agents having multiple models work together will pretty much always give you a better level intelligence than you can currently achieve with the best model out there. And I think that's probably a fundamental rule that that might may be true forever. So, it's a great thing to learn. But number two is that you can use that by having a group chat like this where your agents can talk and they can reply. They can riff off each other. They read your Obsidian Ba for context and then from there they plug those ideas automatically into your pipeline so that you can build and automate whatever you want based on their best ideas. Now, you might be wondering, okay, how does a memory system work? So, we have Obsidian, which is a free app. We've built all of our memories into this memory galaxy. It's all visualized, organized, linked together, and very nice. And basically, the way that we've organized that is that our agents automatically update it. So, you can see, for example, 2 minutes ago, 4 minutes ago, 35 minutes ago, like our memories are always been plugged into this system. And then from there, our agents can update it, but they can also pull from it. So, it's a positive feedback loop. loop engine where our agents update and organize the memory galaxy themselves, but they also use that to come up with ideas and build amazing things that are personalized to me so that we have our agents just running on a loop and there's very minimal um human intervention involved, right? Unless you need to. And that's why we do have the human approval section here because we don't just want to build everything that they create. Want to look at the plan, see what it is, see if it's actually good, and then approve it if it's good. If it's not good, let's delete it. And also, you can rebuild anything that you have here, too. So, you can actually click on the rebuild section here. So, if what you created you don't really like, no problem, mate. You can just click on the rebuild section, and then it will actually start rebuilding the whole system right here, which is pretty cool. And the great thing about this is, I don't know about you, but I would have loads of ideas, but no way to implement it. And I just couldn't build all of them at once. I think that that would be that would make an amazing app. But then, you know, for example, you might have to hire a developer. You might get a pretty mockup from a no code tool, but half the buttons do nothing. And the AI ones usually create like a halffinish system that you never come back to. So you get loads of ideas, but they just sit in your in your brain or your memory and you forget about them. So what we did here is we wired them into an app builder inside the agent OS. So now if I type an idea and hit approve once, the agents build the real thing with every control wired in. It loads and tests itself and fixes it own bugs before it shows me. And we can just build loads of apps this way, right? And you can you can build yours the same way as well. And if you're wondering, okay, like is this sort of stuff difficult to build? Well, we've got loads of people using our Asian operating system and everybody's loving it, right? We got so many people winning with AI automation because we try and design our systems as simple as possible. So, we take the power of something like Hermes agent that most people don't know how to really use and then we plug it into like mini systems and tools like this inside our agent operating system. So that if for example we need an app builder, we've got it ready to go. If for example we need to pull in the latest trended news with Hermes, we've got it ready to go. If we want to generate images inside a beautiful app builder like this, we've got it ready to go. Right? So each one of these are like mini systems where you can get the full power of Hermes agent, but you don't need to be technical to use it. So this is how it works step by step. And the great thing is you can go from like one sentence to a shipped app in like five simple moves. So you drop in an idea, then the agent's going to plan it, then you approve it, and it's just one human checkpoint. So you would read the plan and click approve or reject. And that's the only step that really needs you. And then from there, a coder agent actually builds a complete self-contained app. And from there, the the working app lands in your gallery. So you can view whatever you've built directly. And these are a bunch of examples what we've created. So for example, we can actually use this meditation app and it actually works pretty nice. We can switch between the the times and how long it works. We can easily use this for doing our meditations and it's just ready to go whenever we need it. Right. And again, that was just an idea where we went from idea to implementation very very quickly. So what did you learn? Well, you learned how to generate apps in one sentence, how to do it with Hermes agent, how to do it in one click, how to approve everything, why you need to approve it, and also how to make sure that you never lose your ideas again. Now, if you want the full app builder from us, I mean, you could build your own, but if you want ours, you can get it inside the agent operating system. And that way, you don't need to set up like a coder, a planner, a verifier, or anything like that. Inside the agent operating system, we already have it ready to go. And that's in the air prof. So you get the whole pipeline wired in and running on your own coding plans. So you can go from a sentence to a working app in like a couple of minutes as you've seen today, right? And you get the full idea to app pipeline. You get real working apps that you can build straight away. You get four coaching calls a week and 3,800 members inside there who are building alongside you. So if we go inside the community here, this is the profit boardroom. If you want to get the agent OS, you just go to the classroom. And the goal for everyone who joins is really to learn, scale, and grow with AI automation. This stuff is so new that most people know exists, but they don't know how to get the most out of it. And what we build is systems where you can get the most out of this stuff as quickly as possible. So, you get the agent OS system over here. You got the video tutorial, the last update date, you can get the zip file down here, and then we also have new daily tutorials and guides based on what's actually useful, the drops inside the community. You can post questions. We have people available online 24/7 ready to help whenever you need to to. And then inside the community, you can also post questions and I personally answer them along with the rest of the community so you can get as much help as possible. You can also get four weekly coaching calls and get help and support in real time. And then inside the map, you can actually meet people in your local area who are building AI agents just like you. So feel free to get that link in the comments description or just go to the aiprofitborn.com. Thanks for watching. We got Jay in the house. Welcome here, sir. Thanks for joining. Hope you well. So, Jungle was asking, you know, I found your channel last week, been watching it for a good bit. What tools you already have baked into the agent OS or SEO? So when it comes to SEO, I I'm actually uh so we have this SEO section here. Number one, we have the agent OS that finds based on our Google search console data here, we can easily find keywords that we're ranking for and new opportunities. So for example, if I type in Hermes and we look at this website, it will look through my Google Search Console data, score the potential opportunity, show us which pages we're ranking for but not getting any clicks for, and then actually show us the page itself. And so we can use that topic to rewrite or reoptimize the content. So that's step number one is it can look at our Google search console data and then give us ideas for content. Step number two is we've built in open SEO. So we basically got like a free open source rank tracker that we can use for keyword research, for tracking our rankings, for uh checking our back links and everything else and also our AI visibility inside this section. Then we can also generate content. So based on the research inside open SEO and inside the Google search console data, we can plug in a keyword that we want to rank for. Click generate five articles and that will create personalized content based on us and what we do etc. So if you look at this page that we've created, this takes our case studies and our experiments, plugs it into a beautiful blog post and then helps us rank that way. So there's all these different systems plugged in the keyword research based on Google search console, the rank tracker with open SEO, the content creator and deployment where we can see all the content that we've created as well. So, it's a really powerful system for SEO and we've basically customized it as much as we possibly can while still making it actually useful and also super easy. So, even the fact that, you know, if you look at the skill that we use for creating content, which you can see here, it's a very very specific detailed plan telling our agents exactly how to create SEO content and making sure it's quality controlled, which I think is really powerful as well. I like that. Looks like good tools for traditional SEO. Do you have anything in there for local services, people searching? Um, well, I mean, you could use the same process, right? So, for example, if you wanted to create SEO content for a local business, then you could still look through your Google data. You can still use the rank tracking here. you can still generate the content. So you just customize it to your keywords in your industry. So for example, if I'm like an SEO agency trying to rank locally, well then I can still look through my local keyword data. I can still use a rank tracker in terms of AI visibility and everything else. And then if I need to generate content, well, we can plug in a keyword and start ranking locally for that particular keyword. So it could be for example like SEO agencies near me or Birmingham plumbers near me or whatever it is. And you can create service pages that way as well. So whether you're local, whether you're online, no problem. Today I'm going to show you how to automate back links and link building using a powerful system with built with Hermes agent. And essentially what we can do here is we can basically automate and build link building campaigns and generate leads for link building campaigns using this outreach system that's plugged into Hermes agent. So what we can do for example here is we would find leads. So let's say for example I have a blog about link building automation or let's say I have a blog about AI automation. Well, I can type for example AI automation blogs here. Find an MRI and that will basically search for leads related to AI automation and relevant blogs. So you can see it said found eight sites enriched with their details here and then you can see the details of those leads at the top. So we found a couple of example websites that we could reach out to and then it has enriched the lead in terms of what they talk about, what they do. It's found the details of how to reach out to them. And then from here we can either delete them or what we could do from here is we can go to our campaign section and we can automatically generate the email outrage campaign to build links for them. And what I've typically found with link building is that the more websites you reach out to with relevant content asking for a backlink the more back links you get in return. Right? So it's just a case of reaching out to more websites reaching out to relevant websites and having a good email campaign. So what we can do from here is we can plug in the email that we want to reach out to or the leads that we want to reach out to and then you can either write the email yourself with the subjects in the email body or you can tell the AI exactly what the campaign is about and then that will use this to generate the outreach campaign. So let me show you an example of this. If we go to the AR profit boardroom as you can see right here and let's say for example we want to get back links to a page like this. So what we can do here is we can plug in that URL and we can say okay reach out to prospects asking for back links for my blog about Hermes agent and offer a backlink in return to say thanks. Then we can write the email with AI and that's going to begin to write the subject line and the email body for the campaign. So you can see now they say I was just reading through your domain and liked it because of this reason just published this article. Would you be open to linking to it want me to send over the details? Cheers. And here's exactly what the email campaign looks like. Also have the opt out inside the email too. So we can easily automate link building. reach out to these relevant websites that we've contacted. We've got an email address set up for Hermes that can do the outreach for us and I'd recommend that too. And then from here, if we're ready to go on that, then we can click on create campaign, right? We can start building the backlinks. So, for example, we have a link building campaign set up over here. And basically, this means that we can automate our outreach. Now, this also means that you could use this not just for link building, but for email outreach, for getting potential clients, for lead generation, whatever you want to use it for, but it's a really powerful way to basically turn Hermes agent into an outreach SAS tool that does all the work for you. And I think this is one of the things that you're missing out on if you're just using Hermes inside the terminal. So, if you're using Hermes inside the terminal like so, you just don't get that sort of automation. you don't get that sort of setup. You can't see everything that you've done previously. You could train Hermes with a skill inside the terminal to do this, but how would you manage it? How would you visualize everything you created? It' be very difficult, right? Whereas, for example, if we set up this system and we're like, okay, we'll call this link building campaign. We've got the setup over here. We've got the email and then we can click on create campaign. All right. And then we can preview the whole setup here. And our campaign has been added. Now, if we actually want to start sending it, we can click on activate and that will reach out to the prospects inside that campaign. So, we literally go from lead generation to writing the email to doing the outreach and we can manage all of the systems here. So, we can see all the key metrics like the number of leads we reached out to, validated, sendable, etc. And then we skip anyone that's too big because obviously there's no point reaching out to like, you know, if we reached out to like Forbes or something like that, they're not going to reply to us obviously. So, we skip all the stuff that's too big to reach out to. And then also, what's pretty cool about this is we have the sent items. So, we can easily see what was sent here. And then we've got the inbox as well. So, we can see, you know, who's in our email inbox and who have we reached out to. So, this whole system here just automates the I for me personally as someone who's done a lot of link building and uh building backlinks for our agency, I know that it can be super draining, super time consuming. And this is why most people don't do link building. So we built an AI tool with Hermes agent that just automates all the hard stuff I don't want to do. So this is how the whole system works. And you know your AI can basically do the whole email outreach system for you using this. Here's another example of an email draft that I wrote. Pretty simple and easy to set up. And the great thing about this is like you know what a lot of people do is they'll go into something like pitchbox and they have to write the emails themselves or they have to copy and paste from chat GPT or they have to figure out themselves. Especially if you've got a team doing it like that's a lot of work. Whereas with this system you can easily just automate it from start to finish and it's all inside one place. You're not like duct taping multiple different tools together. The way this works is basically we have Hunter API and we have firecrawl as well for enriching the leads and then we have Gmail plugged into this. So we have a Google Workspace API that we can plug into this system and so it finds email, it finds the leads and reaches them, validates them, writes a campaign, you can preview it and then you can send and this runs on a schedule as well. So it runs dayto-day and you can always pause or stop it whenever you want to as well. The other thing that I would say here is like the actual UI is super nice, right? It looks nice, is nice to read, feels good to use, and also because this is basically your own setup. Like we give AR profit boarding members the zip file to install. Because of that, you can customize it however you want. So if you're like, I don't really like this color or I want this layout to be different, etc., you can ask the AI agent that sets up for you to just customize that and change that for you. So everything that you're seeing here is fully flexible and you can change it however you want. So this is basically how it works step by step. Super simple and easy. And then you give it a brief. The air writer does its job and then it customizes each outreach message to the person it's reaching out to. And then also it can follow up with those leads too which is great. And everyone can opt out as well. So it has like an auto, you know, if they reply stop or if they click the button to opt out, no problem at all. So that's basically the whole system, how it works, how you can use it for outreach. You might also say, okay, well, does link building actually work? So the website that we use this for as you can see the arprofitboarding.com it works really well. So the more backlinks we build from relevant authoritative websites the more our rankings increase because in a world where everyone can create content and everyone can easily find keywords using AI. The only thing that really matters now is the human relationships that you build. How do you build human relationships for back links? Well, you just reach out to other websites and say, "Hey, got this blog. Would you link to us? We can help you in return." And that's how it basically works, right? And so for 99% of people, they don't even know that you can build outreach systems like this. So, if you're watching, you're already in the top 1%. And this is a whole system that you can use with AI to automate this whole process. So if you want to get the agent operating system with Hermes outreach built in, the outreach tool I use is one of many tools inside the agent operating system. You can get the Hermes out system, you can get the local Hermes engine, the Claude workspace, free local models. So we have a free local engine inside there, the AI email tool, the lead generator, agent cambans, uh memory vault built in as well. And 3,800 founders are also using this together too. And if you're thinking, okay, this sounds technical to set up or whatever. You can see that we have 191 pages of people winning, learning, and growing with this stuff, right? 192 actually, sorry. So, you can see all these people using the agent OS system. Loads of people getting awesome results. And so, if I'm nontechnical and I can use this and all these people are nontechnical, too. Then we live in a world where we can build tools like this. We can share it. We can learn to together. And if you want to get the whole set from me, that's available inside the arrum community. Link in the comments description or go to a profitable.com. So, if you go to the classroom here, then go to new daily updates, you can find the agent OS system right here. We add new daily updates. You can get the video tutorial on how to use it. We got a full guide and also the zip file to install. We had new daily tutorials like you can see right here. Inside the community, I personally answer all of the questions daily with a video tutorial for everyone. And also, you get the help and support of everyone online, which means that 24/7 there's always someone online to help you. You can also jump on weekly coaching calls. We have four week coaching calls where you get help and support in real time and then inside the map you can meet people in your local area. So feel free to join us inside there. The other thing I would say is if you like SEO but you don't have the time to implement it, we do have an SEO agency that can help you with link building. So you can book that a onetoone SEO strategy session at goldie. And you'll get a free SEO domination plan. Discover the secrets to SEO link building. Answer any questions you have onetoone. You'll learn the best link building strategy for your website and you'll learn how to outrank your competitors with link building based on what's working for us. So feel free to get that at goldie. Agency link in the comments description or just go to the AI profitable uh sorry cordi. Agency let's see what we got here. Thanks for showing. There's some things I want to add. Anything you want to add, you can just customize. You just ask your agent to do it. Right? So for example, if you're like, right, I want to add this API into the agent operating system. just ask it and and your agent can set it up and add that in for you. You really like the outreach campaign interface. Thank you very much. Would this replace needing um a service? So, you can already use the tracking inside the dashboard if you want something super simple, but it's not like a full CRM, right? So, for example, we still use go high level for our main agency CRM. You might use HubSpot, something like that. It's really different. Like if you just want an email outreach and lead generation tool then you can use ours but if you need like a full CRM then you get a full CRM of course like go high level at HubSpot as you keep building does everything you get you add Yeah. Absolutely. Yeah. So that's why we add new daily updates. That's why I'm always building as well cuz I want to keep adding and helping people based on what people want, right? So for example, people are asking me, how do you automate link building? And so that's why we create the system that I just showed you. Other people asking, well, how do you build stuff with Hermes agent? That's why we create the app idea section, right? So we add all the daily updates that we create inside this section. And as long as you're an AI profit board member, you get access to the new updates, too. We also have a updates.md file inside the zip so that if you already have the agent OS but you want to update it, you can just use the updates.md and quickly install the new versions. Thank you so much. Yeah, I really appreciate that. And try and make it as useful as possible. Exactly. That's it. So, you just type in plain English to the agent that help you set it up exactly what you want and then you can build it in. That's what we do. I mean, if you look at when I build this sort of stuff, that's all we're doing. It's just like speaking to Claude. And usually I spend about 3 to four hours a day doing that. Thank you. Yeah. Well, I look forward to seeing you inside there. Good questions today, peeps, by the way. Thanks so much for all the questions. Today I'm going to show you a new free rank tracker that you can easily build out with Claude for AI SEO. So, if we go to the SEO section inside our Agent OS, you can see that we've added Open SEO. And this is a free open-source project that you can use to create your own rank tracker. Now, why would you want to do that? Because then you don't need subscriptions to fancy tools. Also, a lot of rank trackers out there aren't very good for actually tracking your data, and I'll show you a better way to do that in a second. And also, this is all free, right? It's free and open source. You can customize it, change it however you want. That's the other cool thing is like for example if you're using HFS to track your rankings well you won't be able to customize it in the same way that I'll show you how to do in a second. So how does this all work? Well basically we've got open SEO which is a free open source project. It's actually trending on GitHub. Really powerful. And basically what you can do is you can use this for keyword research and also for tracking your visibility both on Google and also on AI. So it's a really powerful SEO tool and it's fully customizable. So for example, if we want to do keyword research, we just type in for example something like this. Then we can hit search and from there we can start getting the data as you can see. Right? How easy was that? And then we get all of the keyword research you want. But if you want to use this for rank tracking, then what we can do is we can add a domain. We can plug in our website. We can track the country, track whether we want to see our rankings on mobile and desktop. And then from there, we can add the search depth. So, how many pages we go deep on that? And also bear in mind, you're going to plug in data for SEO as an API into this, which is still pretty cheap as you can see right here. So, for example, if you're tracking with the bear in mind like the actual tool itself is free, but then you just plug in your own API. So, if you're tracking like 50 keywords, it would only be 50 cents per month, right? And you could do this for all your clients, you could add as many as you want. There's no limitations. That's the other thing as well. for example, you're using tools, I don't want to hate on any tools, so I'm not going to mention any names, but like if you if you add too many domains for SEO audits to some tools, they make you upgrade or they make you pay extra or you can't even do it on the current plan. Whereas with this, you can track as many domains as you want, my friend. Right? So, it's full again, you get a lot more freedom with this sort of stuff. So this runs on data for SEO which is pretty powerful API probably one of the best APIs for for getting SEO data and then for example we can see our rankings over time we can export it we can add keywords we want to actually track so you can add all the keywords here like this and then once you add a keyword it will start getting the rankings for that particular keyword. So you can see that's instantly pulled in our position, where we were previously, the keyword that it is, the URL that we're actually ranking for with that particular keyword directly from our website. And how easy was that, right? We can also see, for example, how much search volume we got, the keyword difficulty of that keyword, and also the SER features, right? So does it have AI? Does it have video on the SER? Uh does it have people also ask questions, etc. And so this is really easy and simple to use and pretty powerful. Now, if you're wondering how to set up, here's how I personally set up. So, I got the GitHub from Open SEO. I went into Claude directly. I created a new conversation called Open SEO and then I plugged in the details here and just asked it to set up for me. And I gave it the data for SEO API. That was it. Simple as that. So, you can easily use Claude to help you set this up. And if you want to add new features into this section, you can, right? You would just ask Claude, okay, add this, change this, change the color on that, etc. And you can customize it as much as you want. The other cool thing that we've done here is we have a research section here which again is pretty good for rank tracking. And this is completely like this is you can make this fully yours. So for example here we can type in Hermes and what it's going to do is look through my existing Google search console data for rank tracking. And then for example it will pull in from Google search console for each of our websites over the last 28 days, 7 days or 90 days for our particular keyword all of the keywords we're ranking for. And then if we want to create new content around that keyword because we don't already have a page about it, we can just click on use that topic, plug in a case study for information gain like for example this, plug in the keyword, hit generate five articles, and then that actually posts the content directly to our website as you can see on this page right here. So we can create the content, track our rankings, do more keyword research, and it's all available in a fully customizable UI like this. How amazing is that, right? You couldn't do this last year. You could you certainly couldn't do this like two years ago with something like chat cheap 3.5. So I think SEO is number one easier than ever but number two it's more fun than ever right like you can create your own tools at this point you can create stuff that's fully customizable and then you can see for example we can also set up AI visibility tracking. So not only can we track our rankings inside Google. Not only can we track our rankings from Google search console data but we can also add AI visibility. So we can do brand lookup here. We can plug in data for SEO. So we just confirm um your optimization access here. We can open up data for SEO like so plug in API and then we can start using that as well. Right? And the way that we do that is we just have to enable inside data for SEO access for AI. Right? So once you've confirmed it once you've turned that on then you can add it inside this section too. You can also add like MCPS. So if you wanted to connect this rank tracking to claude code or codeex or claude desktop or codeex desktop no problem at all. So you have this MCP server URL inside the AI and MCP section of open SEO and then you can go into claw desktop or claw code plug that in. You can also set up SEO for skills. Right? So what this means for example is if you want skills for keyword research, competitive landscape, link prospecting, uh SEO coach, keyword clustering, you can plug all of those skills into Claude Codeex or Hermes agent, whatever you want as well. So it's a really powerful system. So that's basically how you can use this. And then also you got the domain overview here. So this is kind of rank tracking but for competitors too. So we could have julian.com, but then we could have my competitors and we could also have our clients. So you can manage everything inside one simple place. The other thing that I quite like about this whole system is that it's so simple, right? It's very intuitive to work with. And you know, if we go to the rank tracking section here, how easy it is to to just navigate between this. Whereas sometimes with these SEO tools, particularly the AI visibility ones I've seen, personally, they can be a little bit confusing or timeconuming to use. So this is basically it. This is the free rank radar system that we have tested out and it's a it's an engine that works in real time as you can see right here. And so you get the full picture as well because you can plug in AI answers, you can plug in Google rankings, you can also plug in search console so you can get the data from three different places, plug that into your system like we've got it all set up inside our agent OS and then it's ready to go as you can see right here. It also does serve analysis which is super useful and you can export any of the data as well whenever you need it. So, with this new system, we can see where we show up, where we rank on Google, what Google's actually got in terms of data from Google Search Console. This is a free self-hosted tool. Then, you plug in data for SEO as an API, and it's really simple and easy. For actually getting the Google Search Console data, we got a Google Workspace API. Again, Claude can help you set that up. Uh, we have the agent operating system ready to go if you want this full setup like we've got custom made inside the AirPuff. Uh but basically that's it. So if you're thinking okay which APIs do you need? So you want Google workspace for this section here. Then for open SEO you want data for SEO and for generating the content we use a combination of claude CLI plus we use Netlefy for actually publishing the content. So we can get a a personal access token from Netleify and publish the content directly to our website. The other thing that I would say here is if you are using WordPress all you need is a login details and a personal access token for that. And that's pretty easy and simple. So once you give that to the agents they can easily publish content for you and so you get all the signals you got AI visibility you know are you showing up inside the AI answers are you ranking with your website and also what's your Google search console telling you and the reason that we check Google search console is also because we want to spot new opportunities for ranking our website right we want to find okay what we getting impressions for but not clicks for so that we can easily find new keyword opportunities that would actually help us rank so that's basically That is the whole system, my friends. And then we connect it once. Agent OS Pes Google Search Console data. We see what we're ranking for and it goes from there. So if you want to get the full agent operating system for me with the rank trackers, our full systems, for example, for Hermes agent, we have the SEO content machine inside there too. We have uh agent group chat for managing, orchestrating all your agents. We have the Oracle as well, which can also pull in the latest trending data. So for example, it pulled in the you know GR 4.5 is center in private beta that just that is literally trending right now. That's brand brand new news. And then if we want to create SEO content for it, we just click the publish to WordPress section here and it will publish you directly to our websites as you can see. Again, these are these are actually hosted on WordPress. So you can link to WordPress or Netify, whatever you want. And also the cool thing about this is it all links inside our memory galaxy. So if we go to the memory section here, all the SEO content that we create, all the keyword research data that we get, every time we use Hermes agent, etc. is all plugged into this memory system so that it's organized into one second brain. It's automatically logged whenever we use this stuff and then we can come back to it and everyone, which is super powerful in itself. So if you want to get all this, it's inside the AI prof. We also have a full classroom on AI SEO automation to help you as much as we can. And then if you want to get the agent OS just go to the new daily update section here and you can find the agent OS video tutorial when it was last updated the zip file and we update that daily. Also inside the community there's lots of SEOs and you can ask questions whenever you want. So if you ask questions I'll personally answer them with video tutorial each day. And then also there's members online 24/7 that can help you too. So you get answers not just from me but also the whole community. You get all of my best trainings inside the classroom here. We add new daily tutorials and guides as well. And then you can jump on weekly coaching calls, ask questions and get help in real time. Inside the map, you can actually meet people in your local area who are building with AI agents like this. And this is all available inside the AR profit boardroom link in the comments description or just go to the AR profitwarm.com. Thanks for watching. All right, let's see what questions we got here. I have a new brain folder already with a lot of information about me. Yes, you can. So, you can ask Claude, okay, put that into the agent OS and just make sure that you have Obsidian installed. Or you could actually just say, okay, build this as a a second brain for me custom made. But I would recommend that you ask claw to plug that into Obsidian and then your agent OS can connect with Obsidian. Gina says, "Is it finished? It is pretty much yeah almost uh we use AI for that. We got a lot of training on that. So if you go to the classroom here for the avatar videos, you would go to the playbook here and you can find details on the avatar videos and a full SOP step by step. And then also if you're wondering, okay, how do you like automatically do the rest of them? So, we have the YouTube road map here. I actually recorded part of this with Kazer Dash, who's another SEO YouTuber. So, yeah, we have a full road map on that as well. Drop. Yeah, I mean, whatever you want. I've never heard of anyone dropping Hermes agent for that reason, but again, like everything that we do with Hermes is plugged into Obsidian, so we can easily um get access And then also for the avatar videos inside the agent OS, we have a full video section here that can create avatar videos for you. If you want to see an example of what they can create, here's an example. So that's my avatar. All the B-roll, all the research, all the script, etc. was plugged together using this video agent. And the way you can use it is you just go inside here and type what you want. So it's pretty simple and easy. All right, everyone. I've answered the questions, answered every single comment, answered all the questions inside the community. Thanks for watching. I'll see you on the next one. Cheers. Bye-bye.