Live AI Agent Builds: SEO, Video, and Coding Automation

Captain Stop there. [music] [music] [music] [music] >> [music] [music] >> Yeah, that's me Yeah. [music] Heat. Take the army. [music] go. Yes. [music] Thank you very much, Orange Nomad. You would say that, >> Randall. Good to see you. Yeah, the hat is uh keeps you cool. Keeps you cool. >> [music] >> go. Captain up >> [music] [music] >> Good question from Mark here which is what's the best way to get back links in 2026. So what

I typically do is I'm still running the same strategies that worked you know 5 or 10 years ago and from everything that we've tested it seems to be the most scalable and also the most efficient. So what we do is we typically just do outreach you know and the thing is AI is automated keyword research it's automated technical SEO schema but it hasn't automated link building and so if you're still doing yeah if you're not doing

outreach I would recommend that and just focus on that which means like find websites that have linked to your competitors reach out to them via email or social media ask them for a backlink and follow up and eventually you'll see some backlinks coming in and that's what we still do for all our clients as well. So recommend that strategy Yes and no. Yes and no. So you can automate it, but it's not as good as just

doing it yourself. So you can automate, for example, what you can do, we did this with our agent OS system, is we got Hermes access to a separate email address, and then that can send outreach emails to potential people who would link to us, and we just have to say, right, here's the pages you want back links to. it will just go in a loop and start reaching out to people. Is it as good as just

using normal outreach? I wouldn't say so, but we do have a full tutorial out there. If you Google like Hermes agent backlinks, you'll be able to find it. Hello SA, welcome here. >> [music] [music] >> Hey, [music] [music] hey hey. >> [music] [music] [music] [music] [music] [music] >> So if you want to vibe code for free, I would just use local models inside something like Visual Studio Code or you could plug free local models into Claude

code with O Lama as well. Those are two different ways to do it for free. So yeah, just look at that and then you can build whatever you want with free local models. The other option that you have is you can build [music] with free APIs. So there's a lot of free APIs like N2 on open router. You can plug those into claw code using free claw code or you can plug them into visual studio code

and just build from there. But either way, that's free and easy to do. [music] [music] >> [music] [music] [music] >> What else you got here? Welcome in, Kevin. So, for that, let me share my screen. I'll show you what I usually use. So, I'd recommend inside the classroom for marketing, go to this section. And I would set up the Twitter automation. I would just focus on one per week, but I'd set up the Twitter automation first

and also the avatar video section here. It's just super powerful. This is what we use personally. So, out of everything that we do, these two methods are the most effective. And you know, if you set up those two systems, you've got the 8020 of it. And then you can keep building the rest. But yeah, I focus on the Twitter automation and the avatar section. There's a hat. Yeah, you can do that with any AI, right? So,

if you want to if you use Visual Studio Code like I was talking about or Claude, they can edit your files for you. It was announced that it was going to be like 24 or 48 hours ago and that was on Monday. So, it doesn't look like it's making progress. I've not heard anything good or positive since then on like what's coming out. So, I think it might be a while. I think it might be a

while. for this you can check out this section inside the air profit boardroom. So if you go to the air profit boarding we've got a full system on it link in the comments description or go to the air prof.com go to the classroom over here you go to uh this section and then you can grab our full process there and also what we've done recently this is crazy powerful is inside our video agent on the agent

OS you can that we have built out a full video agent that can generate the video, generate the script, research the topic, generate the avatar, >> Max Studio with local models, put it all together in a beautiful video like this. It's better edited 99% humility. Let's dive in. >> If you want that system, it's inside the agent operating system as well. >> That actually is my new favorite setup. It's it's absolutely amazing what you can do

with this. >> [music] [music] [music] [music] [music] [music] [music] >> Yeah. So for that basically we show you the same strategies that we use to advertise right? So for example, we have our own our own builds that we advertise. For example, like the agent OS system, right? And so the way that we advertise them, [music] we give you the systems for those so that you can use those for your own business. So if you look inside

this setup here, you've got the system that we use for avatar videos. You got the system we use for shorts. Twitter automations, newsletter automations, emails, even how we automate the the screen share process, but everything you need to win with marketing and AI. And bear in mind, like AI is one of the best ways to market your business, we've got everything inside this community. So yeah, if you want to know how to advertise your builds, perfect

place to learn based on what's working for us and we test everything personally. >> [music] [music] >> feel. [music] Hey [music] Thank you so much, Seth. I appreciate that. Looking forward to connecting with you inside there. And yeah, if you have any questions, feel free to DM me. I'm always happy to help. [music] >> [music] >> Oh, [music] love. >> [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] >> Hey, hey, hey. >> [music] >>

recommend anywhere to get good AI skills for front end. So, I'm not seeing really anything good. There are some GitHub skills where you can get like UI trainings for your for your agents, but the thing that I found the most effective so far is basically you give your agents examples of what you like and why. And then they learn from that. And then once you've got that in place, you can save that as a skill cuz

you're like, "Okay, this is what I want everything to look like." So that's what's worked the best for me. I've tried like front end skill installations from GitHub. Not that great, honestly. So, I'd recommend this process instead. Just find great examples. Give Claude those great examples from there. Bear in mind, Claude and all these AI tools are not that great at front end. They they struggle a lot. I have found some good skills for game design

though, for 3D games design. That blew my mind. Let's have a look what's going on here with this error. Might have to change the model here. Yeah. So, open design. A What's going on with Claude today? Look at this. I might have to restart. Let's try again. shout out to Seth for joining the profit boarding. Thank you very much, sir. That's pretty cool. Wow, he implemented that fast. How to update the agent OS. Yeah. So it's

got an update section inside there, right? So we train on the skill of the export. So we have a skill for exporting the zip file, the agent OS. So if you want to update it, you just get the latest version which is inside the app boardroom and update it from there. And then it has specific instructions inside the export of how to update based on the newest version. You can just pull in what you want. You

don't have to pull in all the new features. just like it could just be one or two that you actually like. And there's also a change log inside there so you can see what's happened recently and uh what you've worked on, etc. Hey Ron, thanks for joining. We're just building some stuff out into the agent OS. Working on building some uh longer videos. We got the Substack machine trying to run, but it looks like Claude is

not working today. Opus 4.8 not working at all. Might switch to Opus 4.7 here. Can see here they're having a problem. Yeah, we already have Obsidian plugged into the system. So everything that we do gets logged in there automatically. Look at that. Even Opus 4.7 is not working. This is madness. Anyone else's is anyone else's claw down or is it just mine? Ah, there you go. Yeah, like I said, um, so we with open design, what

you can do is just get claw to control it. Or you could build it out into something like the agent OS system. That would actually be pretty interesting like to plug in open design inside the agent OS. I might add that to the list. What we could do is we could build a new section inside here and we could add open design inside there. I'm going to put that on my list today and we'll build it

out. I think that'll be a great way to get the most out of it. And then if we go to the AI profit boardroom se which class is good for advertising. So again I would just implement one of these systems per week. so you can master it. So you got the Twitter automation here. This is really powerful. Just to put this in perspective, let us show you how many people we reach on on Twitter using the

same automation. So yesterday, for example, we reached 209,000 people in one day. In 4 weeks, we reached a total of 6.2 [snorts] million people from Twitter. So we use the same automation that you're going to learn, and you can get it right there. And then the other one that I'd recommend is the AI avatar videos. So you can do, you know, AI videos. You post those as content, [music] reach more people, show what you've built. That's

how it works. So let's talk about what we're going to build today. As long as Claude starts working. So we're going to have open design. We're going to build out the video agent. Does it improve that? What else can we build here? Let's get Claude working again hopefully. Thank you so much. Yeah, I think you could actually just build it straight in to the agent OS like if it's a open source project, which it is. I

think it's going to be minimum a week, but who knows? You know, when I've never seen that situation before. So, we're at a point now where nobody knows what's going to happen next because it's never been seen before. There's no history. There's no trends or patterns we can look at before. And I think anyone who gives you an answer on that is just guessing. So let's see. But yeah, I would expect a minimum one week. But

at the same time, like everyone was running out of tokens anyway, using it. So, you know, you can still build amazing stuff with Opus 4.8. >> [music] [music] [music] [music] [music] >> Fall love. [music] That's pretty wild. That is wild. I like I like I mean there was some amazing stuff that came out of it. Don't get me wrong. Don't get me wrong. It just be better if there were more tokens we could use with it.

So, about SEO, do we still prioritize SEO? Absolutely. Absolutely. So, I'll show you a couple of websites we set up. Here's one. This is a website that we're using AI SEO for, and it's doing pretty well. You see it went from like zero clicks a day all the way up to 72 clicks a day. And here's another one. So, this website again, it went from like I think it was at one click a day, something like

that before, maybe two clicks a day, and it's grown all the way up to 215 clicks a day. Plus, the trajectory is awesome on that. So, yeah, SEO is super important. And the way that we automate this is we have this agent operating system. We can go down to the SEO section here. We plug in a keyword for what we want to rank for. We plug in a case study of what we want to rank for

as well. And then we just hit generate five articles. And once we've generated those, we can deploy it. And they get deployed to our website. So if we have a look for example at this one, you can see that it generates a beautiful blog post deployed to our website as you can see right here. Let's just check that's actually on Google. Yeah. So you can see it ranking right there. Let's have a look if it's ranking

for that keyword. Yeah. So you can see it's ranking for that keyword as well. So the system works beautifully. Pretty easy to automate with the agent OS and that's exactly how we do it. So yeah, we prioritize it a lot. Yeah. Do you know what? like there's some what you want to do with Claude, something that's worked really well for me is you basically want to give it a a skill for generating 3D games. So, one

thing we did, for example, with GLM 5.2 recently is build like some pretty amazing games, and it's only after we gave it the the skill on how to do uh how to build 3D stuff. So, there's a a good skill on GitHub which you can use to build stuff like this. Here's another example. This is with GLM 5.2 which is a new Chinese CLA. Here's another one. This a full RPG world game. So, you can see

this one too. Um, yeah. See, you can build some amazing stuff with, you know, with Claude as well. But the main thing you want to know is like make sure that you've given it the the skill on how to generate games. Thanks, Randall. Thank you. >> [music] [music] [music] >> Just being 100% honest, that's not what we do at all. We just build stuff like that for fun. And then, you know, the thing is like when

when you create content like that and you share with the world and you're like, "Hey, here's what we've built." Clients will come to you and they'll be like, "Can you build this for us? Can you do this for us?" blah blah blah. And so that's how it works. We we don't really um do it directly like you've mentioned, although you could [music] [music] >> [music] >> Heat. Heat. >> [music] [music] [music] >> Morning Rick. Good to

see you here. Thanks for [music] joining. [music] [music] Heat. Heat. >> [music] >> So check this out, right? This is a video that we just generated with our agent OS system. So we have this video agent. As you can see right here, we can just type in a topic, build what we want to, and then it will brief it, research it, get the avatar, edit it, put it together, etc. So if we go over to this,

this is a fiveminute video, right? So if we play this back, China just dropped a coding model that humiliates GPT 5.5 and it's basically free. GLM 5.2 from ZDA just went open weights under an MIT license. No. And it's like all the research is in, all the B-roll is added, it's edited. Um, looks super nice. Really easy to build this out. So yeah, it's mind-blowing at this point. It's pretty impressive. I'm actually going to test that

later, I think. But yeah, it's a real me, of course. Thank you so much for joining. I appreciate that. That's great to see. And uh yeah, feel free to reach out or drop jump me, you know, drop me any questions, post inside the community. If you need anything, let me know. But welcome. Yeah, that's awesome. Thank you. Let's see what we got here. So, we got open design being built. Ah, Hermes is just so good. So

much cool stuff you can do with it. It's a great one to learn. Yeah, but it's okay because you can use anti-gravity CLI instead. So, they just replaced Gemini CLI with anti-gravity CLI. So, if you're still wanted to use it, you can. No problem. So it's a CLI, right? So you wouldn't use it with Hermes directly. What you would do is just use the CLI directly. So I'll give you an example. So for example, if we

have a look at anti-gravity CLI over here, you can plug it in. It replaces Gemini and then inside here, you can speak to it and use it how you want. It can build stuff out for you. And then also anything that you build you can see over here in this section. But you you wouldn't use it with like Hermes directly. You don't need to. You can just use the CLI. Like Hermes would be unnecessary to use

with anti-gravity directly in my opinion. Yeah, it can if you set that up. Yeah, for sure. But you have to be careful that like I I set it up with 11 Labs and then I shut it down because the thing is if if someone can call your agent and speak to it like you know you got to be careful there and you so that's why we use Hermes open I don't really use anymore. I just use

Hermes and focus on that instead. What's the benefit of using Hermes inside? So there's a lot of good stuff here. Number one, you can customize Hermes a lot more, right? So for example, we've built out Hermes Jarvis, which is a voice activated version of Hermes right here. We can speak to it. We can control it by voice. We can use it whenever we want. And so you can't do that inside Hermes desktop or inside the terminal.

We can see our whole conversation history here. And then we have a preview. Then we can also speak to our Hermes agent real time over here and have a conversation with it. If you're using Hermes desktop, it's super buggy. Like it doesn't seem to sync properly. But this works inside the studio. We can generate images, videos, voice notes, etc. Which, you know, you you won't find a Hermes studio anywhere. You have to build it yourself. And

then also you've got a chat, but the difference is you've got all your agent profiles over here. Now, at the same time, you can orchestrate your agents. So, for example, what you'll see over here is we have paperclip, and we can orchestrate teams of agents together. So you can see that right here with like the organization chat and everything else which you can't do anywhere else. Then you also got the AI group chat. So you can

have for example Hermes speaking to Claude speaking to Gemini whatever. Okay now inside the pipeline you can actually grab the ideas from that group chat. So if we have a look at our agents talking together here you know we said what's a good SEO keyword research tool we could build. Claude came back to us. Hermes work together and then Codeex added an idea to our pipeline. So when we go to our pipeline here, we can just

start creating ideas and start building them. We can go from idea to fully built a app or tool or website in like a couple of clicks. So you can see all the stuff that we've built over here using this system. So it's very quick and easy to orchestrate your agents, have them in one place, have them warmed up, ready to go. And then also we have the agent camban. Now we have uh offline this is a

local agent cambban and then we have a cambban board over here where we can have teams of Hermes agents orchestrated again none of that stuff you can do with a nice UI inside terminal of course you can't do that and then also inside Hermes desktop you can't organize it like this so it's a fully custom build basically based on you know I spoke to to thousands of of members inside the air profit boardroom tried to figure

out what they want and then build everything around it so that's what we set Thanks. Yeah, this is an amazing amazing uh way to use Hermes and everything else. Now, also if we go over to our reviews and testimonials for the AR prof. So, you can see for example, Amanda was saying like Hermes agent is fully wired into my agent OS dashboard and working. It can read my file system. It can search web blah blah blah.

And then she actually created a video breaking it down. So I've just seen so many people who prefer an agent operating system to just having Hermes normally that this is way better. Right? You can have multiple agents working together. Way more powerful. >> [music] [music] [music] [music] [music] [music] [music] [music] >> So, how heavy and time consuming did it take to build out the agent? I mean, this took hours, you know, hours and hours. That's why

so many people sign up to the profitable boardroom just to get my setup because it takes so much time to build this. It's crazy, you know, like I might spend four or five hours today building out the agent OS, customizing it, checking everything works, iterating, improving, waiting for CL to work, you know. So, it's one of those where like it takes a lot of time to keep improving and building it to make it better and better

and better. And I think that's an advantage. Like the earlier you get started with an Asian OS, the better. And then the great thing is that everyone who gets my system inside the air forum, they just start from from, you know, all the hard work that I put in. So they get everything ready to go. They don't need to set it up. They don't need to worry about customization or anything like that and they're good to

go. So building it myself [music] a lot of time, like hundreds of hours. For members who get my setup, they save hundreds of hours because they don't need to start from scratch. Yeah, I would recommend it. It's so much more powerful when you orchestrate your agents and you have them working together. 100%. Awesome. Well, there you go. And thanks for being a member. trying to install Hermes. I mean, it's up to you. Like, I run Hermes

locally, but you know your situation and your context better than me. So, if you feel like, oh, it's a better idea to have it in a separate container, go for it. It's like Claude have got a new artifacts update. I think we got open design built in as well. Now look at that. Beautiful. So, we can connect this with Hermes or Claude, which is pretty awesome. Wow, look at this. He's so good. uh to get it

just go to the AR profit boardroom inside the classroom go to new daily updates and you'll find the agent OS system over here. So this is the full setup. You can grab it. You get the video tutorial for the Agent OS, the last update date, and the zip file right here. So you can get everything inside here. Thanks for joining. Appreciate it. Yeah. So the agent OS system here, we add like new daily updates as well.

Inside here, we've got an amazing community. You can ask questions, get help and support in real time, etc. I personally answer everything inside the community as well. You got the classroom, the calendar, uh with four weekly coaching calls, a map where you can meet people in your local area as well, and the agent OS system inside there. Link in the comments description or just go to the arprofitborn.com. Yeah. G. Uh, so I mean, nonfrontier, GLM 5.2,

to Kimik K27 code. They've been the latest ones that we built. And then also using what else have we done recently? Yeah, local models. But I honestly like local models even on a Mac Studio not very good. I think you need an amazing setup. Like you need a RTX or you need a Nvidia Spark. But yeah, the main thing that I learned from the whole thing is like you want the system, you don't want the model.

So if you've got an agent operating system, it doesn't matter what models come in and what models drop out. That does not matter. What really matters is, you know, what's your system setup like? How's that working? How's that going for you? Because then as soon as Fable gets taken down, no problem. We set up new systems, new CLIs inside here. We've got the local AI engine, we've got Fusion, etc. And that way you can swap everything

in and out. So that's the way I look at it is like you want to build amazing systems and don't worry about the models too much. There you go. There you go. Thanks. Yeah, I think that is the way forward. If you want to run local models properly, that's what you want to use. I really love a good AI UI designer. So what we're using here as you can see is uh we're using open design and

this is pretty interesting. So we're building out we've open design here as you can see and that might be a solution. So we've built it into the agent operating system today. It's looking pretty cool. Are they fast as well when you use them? I mean running Quen 3.6 locally. That is actually amazing to be fair. That's awesome. >> [laughter] >> That's cool. >> [clears throat] >> Heat. Heat. [music] >> [music] [music] [music] >> Heat. Heat. [music]

[music] >> [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] >> Fall. [music] Fall. >> [music] >> Back in one second. [music] [music] >> [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] >> Falling [music] in love. >> [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] >> I feel [music] [music] [music] heat. >> [music] [music] [music] >> Fall. Oh. [music] >> [music] [music]

[music] [music] [music] [music] [music] [music] [music] >> Hey. Hey. Hey. >> [music] [music] [music] [music] >> Hey. [music] Hey. Hey. Heat. Heat. >> [music] >> So, look what we got here. Since I installed Hermes like a month ago, having so much fun with AI. Yeah, it's amazing. It is amazing. Training Hermes to manage and create animations. Yeah, I actually gave Hermes access to hyperframes. It's super powerful as a video agent. would recommend. Um I just went

to the top one on GitHub and then just went from there. But we've already built it into the agent OS. So if you're in the profit boardroom, you'll get it inside there. See open design there. And we'll release a new update later today. [music] Yeah. So, you can ask chat GPT. There's a prompt for that. You can just ask it like, you know, tell me everything you know about me from Claude and Chat GPT. Give it

previous conversations as well. You can download the previous conversations you've had and then just give that to uh Claude. And I would actually recommend that you ask Claude once you gather all that information to organize it into Obsidian Markdown files in a project folder so that it's all nicely set up. We've got the infinite context engine inside there that shows you exactly how to do that. Let me >> [music] [music] [music] >> The big Love take

away [music] nothing. [music] >> [music] >> And I'm [music] the [music] morning. [music] Let me [music] >> [music] [music] [music] [music] [music] >> How do you see next content? Just keep improving, keep learning, and sharing what I'm learning. You know, documenting the journey. That's the main thing. What am I doing right now? Building out the agent operating system. See you later. Thanks for joining. That went fast. Now take [music] the morning to get me down. Thanks

very much. Appreciate that. Good to see you. Good tag. [music] >> [music] >> Heat. Heat. [music] >> [music] >> Heat. Heat. Hey. Hey. Hey. [music] Heat. Heat. N. [music] >> [music] [music] [music] [music] [music] [music] [music] [music] >> looking. Let >> [music] >> nothing. [music] [music] >> [music] [music] >> I know [music] the together. I know [music] [music] [music] [music] >> [music] [music] >> Heat. [music] [music] Heat. Hey hey hey. >> [music] [music] >> Heat. Heat.

[music] >> [music] [music] [music] [music] >> Heat. Heat. [music] [music] >> [music] >> You love me. [music] Love take away. Let me go. [music] [music] >> [music] >> And I'mma take >> [music] >> I know the Starting to get now. [music] [music] >> [music] [music] [music] >> Heat. Heat. [music] [music] >> [music] [music] >> Hey, [music] hey hey. [music] >> [music] >> Heat. Heat. >> [music] [music] [music] >> Love [music] and I'll give Love nothing. >>

[music] [music] [music] >> I know [music] the morning and I will [music] take Let me down. [music] Heat. Heat. [music] [music] [music] [music] >> [music] [music] [music] >> Heat. Heat. >> [music] [music] >> Heat. Heat. [music] >> [music] >> Hey, [music] heat. Hey. Heat. Hey, heat. Hey, heat. >> [music] [music] >> Love everything. [music] Love nothing. [music] [music] >> [music] [music] >> I will take and [music] the morning to get me [music] The majority [music] [music]

[music] Heat. Heat. N. [music] [music] [music] >> [music] >> Heat. Heat. [music] [music] [music] [music] Heat. Heat. Heat. Heat. N. You love me. Love [music] nothing. Yeah. [music] Heat. [music] And I will take [music] that. I know [music] the to get me now. [music] [music] [music] [music] >> [music] >> Hey. [music] Hey. Hey. [music] >> [music] [music] >> Heat. Heat. [music] >> [music] [music] [music] [music] >> Hey. Hey. Hey. >> [music] [music] [music] [music] [music] >>

Hello. Hello, Chad. Good to see you here. Thanks for joining. One sec. [music] >> [music] >> Hallelujah. [music] [music] >> [music] [music] [music] [music] [music] [music] [music] [music] >> Hey. [music] [music] >> [music] [music] [music] >> Hey. Hey. Hey. [music] [music] [music] >> [music] [music] [music] [music] [music] [music] [music] [music] [music] >> Thanks so much. Yeah. So, you know, you're talking about live demo de demos for us in the school group, right? So, what I do

every day is I answer questions from the community and then I usually demo the agent OS around that and then uh post that as a video tutorial. And then also if you go to the classroom here and you go to the new daily updates, every single new feature that we plug in, we do uh live demos right here. So for example, when we added Kim K 2.7 into Agent OS, we have the tutorial, the full guide

inside here. When we added GLM 5.2 into the Agent OS, we created the full guide over here. So like every single feature that we build in, we create a tutorial about it and we plug it inside this section so you can test it out and you know see me using it live etc. Thanks for joining >> [music] [music] [music] [music] >> I got all [music] >> [music] [music] >> I feel [music] >> [music] [music] [music] [music]

[music] >> Fall. Fall. >> [music] [music] >> Heat. Heat. [music] [music] [music] [music] >> [music] [music] >> Heat. [music] [music] [music] Heat. N. [music] >> [music] [music] [music] >> Hey. [music] [music] Hey. Hey. [music] >> [music] [music] [music] >> You can get the agent operating system inside the AR profitable boardroom link in the comments description. If you go to the classroom [music] and go to the new daily updates, you'll find the agent OS system here to

get the video tutorial, the last update date, and then the resources [music] down here as well. >> [music] [music] [music] [music] [music] [music] >> Hey. Hey. Hey. [music] [music] [music] Hallelujah. [music] [music] >> [music] [music] [music] >> So this is a good question right? Um thanks to the great school courses been become a member struggling where to begin. So we have a full section here that helps you figure out exactly where to begin. Right? So if

you go over to the start here section, right, start here and then run through this implement this section here and it will show you and tell you exactly what to implement next. So you can just go with that and then you can build from there. So I would just start with that. It will show you exa if you run through that it's only only takes about 20 minutes. It runs through a whole process with you and

helps you figure out okay what's the number one constraint and then how can you build around that. So if you implement that, you can get it. Um, can I install the Aentic OS without it totally messing up? Yeah, of course. That's what it's designed for, right? So like it's designed for people who are using Hermes and Obsidian already and want to build on top of that into an amazing dashboard. The reason that I created the Agent

OS is because I wanted something more useful than my my setup already. So like if you've got Hermes already set up and you've got Obsidian already set up, beautiful. You can just plug it into this system and they just work together. So, it's ideal for your use case. >> [music] [music] [music] [music] [music] [music] [music] >> Heat. [music] [music] Heat. [music] >> [music] [music] [music] [music] [music] [music] >> I feel [music] [music] >> [music] [music] [music]

>> Are you >> [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] [music] >> Hallelujah. Hallelujah. >> [music] [music] [music] [music] [music] [music] [music] [music] >> to >> [music] [music] >> the >> [music] [music] >> I feel [music] [music] like you don't Heat. Heat. [music] [music] >> [music] >> Fall. [music] Hallelujah. >> [music] [music] [music] >> which you can see over here. And so that's how

I would approach it here. Right? If we take a look, you can basically plug in a keyword, plug in a case study, and then deploy that to whatever websites you want. Now, you could customize that for each of your clients. So you could have a separate tab inside each one of these sections for each client that you have. So, for example, if I'm trying to do, let's say I'm trying to do content for the air profile

boardroom, I could have a separate tab here. And then I could have another tab for this website, right? And then we can have all of our websites plugged into the same system at the same time using this SEO workflow. So, all you need to do to customize any part of this, and this is exactly what we did this morning when we were building in a local AI agent called North Mini code into this system. I just

explain exactly what I want into Claude and then Claude will build and customize the rest of the agent OS. So if you want to add more SEO workflows for each of your clients, I would ask Claude to improve the agent OS and build a separate tab inside the SEO section for each of your clients. From there, you can plug in a keyword, plug in a case study for each one of your clients and generate SEO content

for them. So, it's kind of like the SEO workflow we already have built in there, but you've expanded it now to each of your clients. And you can easily get Claude to build that in by describing what you want. And then once it's done, just test, iterate it, make sure it's actually working how you want. You could even have separate prompts and separate skills for each of your clients. But the great thing is if they're all

inside the real estate industry, then it's easy to generate a similar prompt for each and just make sure the content is unique for each. So this is a question from Ritz which is like when you've got the agent OS system and you're trying to install it or trying to use it inside codeex or GPT 5.5 instead of claude does it work the same and it's literally the same process. So it doesn't matter which agent you install

it with because they're all going to use it the same way. So for example, the instructions that are for clawed run exactly the same with codeex or any other API that you use because they're all coding in the same way and they all understand code using the same fundamentals. So whether you're installing this for claude or Hermes or Codeex, it doesn't matter, you can still use the same system. This is a great question from Greg. So,

you know, when we're using agent operating systems or we're using agents like Hermes in general, how do you install and use a skill from somewhere else safely? You know, because if you look at all the problems that happened with OpenClaw previously, it was down to skills disguise as skills, but actually they had bad intent and then people would install them and it would go off and do crazy stuff. So, how do you avoid that when you're

trying to install stuff? Here's the process that I'd recommend. I'd read the skill MD file yourself. So, that's a markdown file with the details of the skill. That way, you can easily check it and read through it and make sure it's legit. Option number two is you can actually get that skill in that markdown file and give it to Claude and Claude can check for it too. Now once you've checked it and you understand it and

then also Claude checks it and Claude understands it, you don't even need to install that skill that you're getting from GitHub. You can ask Claude to come up with its own skill that's customized to you and what it knows about you. So that's the third step really is just making sure that you build your own skill and then you don't even touch the original skill. So if you want to be safe, that's a three-step process that

I would recommend. This is pretty cool. So Amanda actually built out an SEO blog uh SEO optimized blog running locally with Quen 330B on a Mac Mini M4 Pro which is pretty impressive cuz I have a Mac Studio and running Quen some versions of Quen was super slow. So that's pretty awesome. And basically that's a great example of how you can use this. Now, we've actually built out the system inside here for local AI, right? And

basically what this allows you to do inside the agent operating system and you can build this too if you're watching for inspiration is you can plug in a local model like we have North Mini code that just dropped and then we can build stuff as you can see right here and we can preview it inside the chat. So this is all switched on ready to go whenever I need it. We can ask it to build stuff.

When it actually builds stuff, we can preview it and then we can see everything that we've built inside the workspace as well, which is pretty amazing because then we can come back to it. We can see what we've built. We can uh have a look at everything that we've created. And it's pretty amazing that you can do this with local AI. Bear in mind like you could have this running 24/7, building new things, building useful stuff

or running through a to-do list as well. And then this is free, it's local, it's private, and it can run 24/7 inside your agent operating system. So great example from Amanda of how you can do this. And also bear in mind like you can use something like North Mini code. These local models are getting better all the time and plug that into your agent operating system as well. You don't have to use a API. You don't

have to use like a page CLI either. Another question that we got from Larry here is what's the difference between the original claude uh Hermes desktop and the one from GitHub by Fata. Right. So there's two different versions. There's the official Hermes desktop app that actually dropped later and you can install it here. And then you have the open-source version from here as you can see. So the main difference is the main difference is number one

is that it's a lot smoother to run the official app from Hermes with your Hermes agent and sync it than it is with the GitHub project because the Hermes agent desktop from Loose Research is their official app and so they've built it and custom made it and understand the mechanics behind Hermes and then build that around this new desktop app. So if you want a smoother experience, I'd go with news research. The other thing that I

noticed when I was using Hermes desktop previously, the original which is fataz on GitHub, that one is a lot more complex and has a lot more functionality than the new one from Hermes Agent Desktop. The new one from Hermes agent desktop feels like it's been designed for nontechnical people who have never used Hermes before and just want something quick and easy with a nice UI. So this is Hermes desktop, the original on GitHub. And then if

you want to see the official one from New Research that came out later, you can see that, right? So it's Hermes desktop versus Hermes Desktop. And if you look at them side by side, like this one is a lot simpler. and a lot more simplified. This one is more complex, but also I've seen that it's more buggy, probably because it is more complex, right? So, if you want a smoother experience, just go with the news research

one. If you want something amazing where you can have all your agents working together, I would go with agent OS instead, right? That's that's way more customizable and more powerful. By the way, if you want to ask me questions like this, so for example, Larry asked this question within 3 hours. I've already answered him. If you want to ask me questions like this and I create a video tutorial for you, you can post inside the community

of the AI profitable boardroom and I personally answer these questions on a daily basis. This is a great post from Alex. So, he's talking about basically what he learned from the situation with Fable 5. So Fable 5 was a new version of Claude. It came out then 3 days later it got pulled and you can't use it anymore, right? And so that creates a big problem for so many people that I know because they had their

full systems built around Fable 5 because it was released and we've never seen a model taken off the market before. Right? So here's the way that he's thinking about it, which is just basically making sure you don't have any one single point of failure for a whole system. And that's a fantastic learning point and a really good point for us all to learn from. This is why the agent OS is so powerful because if for example

one agent gets removed or one model goes down or one CLI even gets dropped, no problem. You can add a different one in. So for example, as soon as Fable 5 dropped, we added GLM 5.5 and uh sorry, GLM 5.2 and Kim K27 into that along with local models as well. And that way you don't need to be reliant on one single model and you can be very adaptable. And I think the whole direction that you've

posted right here makes you antifragile. So whatever happens next, it just makes you improve even if it's a difficult situation like the Fable 5 one. I think the learning here as well is like you want to own the system so that you don't have to worry about the model. So, if you have the agent OS system set up, well, you can customize that as much you want and build with it as much you want. And it

doesn't matter about the models or anything outside of your control. So, this is an interesting one from David. So David was posting about you know how for example open router have this fusion model right and with this fusion model you can have five agents working together and then with those five agents working together you tend to get a better answer because one judge will fuse all the answers together right here's an example and that tends to

even outperform Fable 5 on benchmarks according to the research always test it yourself but could you set that up and what we've actually done is we've set the loop system which is called loop engineering with Hermes. So we've created something similar inside the agent OS which is loop engineering and essentially what happens is that you have a builder you state the goal you define what done looks like and that is one single model then you have

a separate model which is the judge inside the agent OS you can choose a totally different model or API and after every round the judge will check if the builder actually completed the task or not and if not they'll critique it give feedback back and it will loop back around until the job is done properly. And I think that's a really good way to quality control, check things, and also improve the outputs of whatever you're building.

Now, if you want to see a full tutorial on that, we've actually got a full system inside the AR profit boardroom on loop engineering. >> [clears throat] >> So, you can see that right here. And this is a full guide on loop engineering with video tutorial full step-by-step process. Another question that we got from Keith is about agent OS, Obsidian, Hermes, and Paperclip. Right? Since Agent OS is using Obsidian Memory Galaxy for Agent OS, Hermes, and

Paperclip, can just one company in Paperclip have a special Obsidian vault. So could for example, if you're wondering what Paperclip is, basically it's where you can have a team of agents like you can see, they can go off and build stuff. They work together as a team and then you can see the builds over here inside the agent OS. Now the way that I would approach this is that you have a separate project for that team

and then in the custom instructions for each agent you can say okay log everything you do into this specific Obsidian folder. And also when you're pulling out context for us and building stuff make sure that you focus only on using that obsidian folder. And this way it's focused on that one folder, that one project folder inside the whole Obsidian setup. And it can use the rest for background information, but it's only going to log and update

that one single folder and it's focused on that. I think that's probably the best way. And you can do that inside the custom instructions of your AI agents. This is a great question. Is NA10 still relevant if you have an agent operating system cler code and everything else? Here's the way that I would look at it. If you're a complete beginner and you've never used AI before, NA10 is fantastic for understanding the fundamentals of AI, how

it works, and how to build workflows. So, if you're a complete beginner, no experience, that is a great way to learn. However, if you want to just skip straight to building agent operating systems because you have experience, because you know what you're doing, because you understand these agents already and you you don't feel like you need to use any, then you can skip straight to setting up the agent OS. So, it depends on your experience and

knowledge already. We got another question about Fable 5 from Alex and he's already posted his thoughts before. I thought his uh ideas before were fantastic. So today we are building a few things. So we're building out well we were answering questions about the agent OS before. We're setting up open design inside agent OS that's already good to go and built in which is pretty nice. It's looking good. We got the workspace here with everything that we

built as well. Looking great. And so this kind of like claude design but it's open design so it does the same sort of thing but for free which is nice. Uh can you also talk through setup versus VPS? Um for me personally I don't use VPS. Right. So I'm just being 100% clear on you here. But if you want to learn more about using a VPS with Agent OS check out this setup right here. Again, the

reason that I don't use a VPS is because I don't have um I I don't think it's secure, right? And I I think I looked at the situation with Oama and everything else and I was just like, you know, better just uh keep it locally instead. Next question, Chris, how do I update my agent OS from the daily updates? So, inside the whole setup, inside the setup, there's instructions on how to update. So if you want

to update the agent OS, you would use the instructions inside the new version on how to update So you'll see there's a update.md file. That's how you update. It's inside the zip file as you can see. I've added an extra guide inside here on explaining how to do that. Is it possible to prompt Hermes for responses within the agent OS? Yeah. Yeah, of course. So if you go to the agent OS system over here and let's

say for example you're trying to prompt Hermes, you can just speak to it inside the chat, right? So for example here we said, you know, every day at 6 a.m. recap my to-do list and then it actually recaps it daily as you can see. So you can speak to your agents directly inside the chat here. You can speak to multiple different profiles. You can have a live conversation with it. You can speak to Hermes Jarvis. You

got the studio here. By the way, this is not Hermes desktop. This is the agent operating system. two totally different things, just to be clear here. Um, and that way you don't need to copy and paste. The whole point is like you stop being in the loop and you just have this set up ready to go whenever you want to use it. Next question from Stan. I'm currently using a Windows PC and it seems like Mac

is the way to go. Which Mac would you recommend getting on a budget? So, for me, I think I've run the agent operating system on uh MacBook Air, MacBook Pro, those are pretty reasonable. And also, one thing I recommend to my team who are using AI a lot is having a Mac Mini. So, if you have like a permanent setup and maybe have an office where you go and build stuff regularly, I would recommend a Mac

Mini is pretty good. Um, but if you need something lightweight, just go with a MacBook Air or MacBook Pro. Cool thing about the agent operating system as well is it's pretty lightweight, so it doesn't matter what you have, you can still run stuff on it. This pretty awesome. So Marlon shares their agent operating system like you can see and they've fully customized theirs exactly how they want it with an amazing um mission control dashboard like you

can see. You can add like your own logo and stuff inside it as well. Looks absolutely amazing. Really like the camb board built out as well. Looks exciting to use. Love the way you customize it. So, the great thing about this is like you can see that people are building their own agent operating systems. And I've seen so many people do this. So, I know that if I can do it, if everyone inside the group can

do it, we can all build this stuff together. And it's it's a lot of fun as well. So Gil was asking about a Mac Mini M4 Hermes setup. So Gil says here, I am currently running Hermes on my Mac Mini using Quinn 3.5 and also Grock, but it seems quite limited. So I want the setup shown in the videos and understand there is a zip file which I believe is below. Um but not this recommended setup

from scratch. Yeah. So the best place to get my setup is here. I've posted the link and then inside this link you can see the video tutorial the last update date and the resources right there. So that's how you can get it. You don't need to just build it with claude. It could be codecs. It could be um for example. Yeah. So it could be codeex, it could be Claude, it could be Hermes, whatever you want

to build with, you can set this up. I think I already answered this one before [gasps] but basically I would focus on one thing at a time. So if you want to set up a to-do list, you can do that inside the chat with Hermes agent or you could ask it to build out an app for you directly for your to-do list you can come back to and store it inside the dashboard. And then each one

of those things, so for example, emails, lead generation, just focus on one automation a week and just work through it. And you can actually just speak to Hermes and say, "Hey, here's my idea. How do I set this up?" And it will guide you through the whole process step by step. So Chris asking about like how do you update the agent OS? So to upgrade it from the daily update, you just use the update.md file inside

the zip. So there's a zip file here. It's got an update MD file in it daily and you can just use that. By the way, look how fast we answer these questions. [laughter] Chris asked this 11 minutes ago. We've already answered him. Pretty wild. All right, thanks so much for watching. So, if you want to get my full agent operating system, you can get that inside the AI profitable boardroom. Link in the comments description or go

to the aiprofit.com. This is my AI automation community. It's helping you save time, grow, and scale with AI automation. Inside the classroom, you can go to the new daily update section and you'll get access to the agent OS system with a video tutorial, the last update date, and also the zip file for installing this. And we also add new daily tutorials based on the new cool stuff that we've added inside there. So you can learn and

grow from every single tutorial we build if you want to stay updated with it. Inside the community, you can ask questions, get help and support. And I personally answer them like you've seen today. So you can ask questions inside here and I personally answer every single one of these. Plus the whole community helps you out too. And there's always people online. You see right now there's 116 people online. So 247 there's people online who you can

ask questions to, get help and support from in real time. And I will also make video tutorials like this daily answering your questions. So if you want to get all of this, including the classroom with all my best trainings, the agent OS, four weekly coaching calls per week, a map where you can meet people locally who are building with AI agents just like you. And if you want to be able to DM me, ask me any

questions and also post inside the community and just meet lots of cool people and enjoy the journey, you can get it all inside the profit boarding. Thanks so much for watching. I'll see you on the next one. Cheers. Bye-bye. I'm struggling to install Paperclip. Uh so probably you can just get that inside uh inside the paperclipip GitHub I would say. But if it's a specific problem with the agent OS, just like DM me inside the community

and I can speak to the agents and get an answer for you on how to set that up or or what the issue is. Just send me a screenshot, etc. Today I'm going to show you how to use Open Design, which is a powerful free open-source project that you can plug into your systems to design and build anything that you want. So, if you want to see some examples of what we've built, you can see that

we've already plugged it into our agent OS system over here. And it's built some super nice stuff. Now, the main point of this is that number one, this is a free design tool. Number two is very similar to quad design. And number three, you can build this with free local models. And the other thing to note here is like even if you're using Fable 5 like even Fable 5 itself not very good at doing UI changes

right claude itself not very good at understanding what good UI is but if you have open design you can get amazing designs like you can see animated websites you can build apps tools amazing really interesting images as you can see and this is all inside one studio where you can build anything you want which is absolutely amazing. So you can see the open design is plugged into our agent OS here and then we can describe exactly

what we want. So I'm going to talk you through how the system works. And I call this the AI design studio. So you can type one sentence and get a prototype dashboard, slide deck, image, video, etc. And it's built on your Mac and or built by your Windows, built by the agents you already use. And you don't need to plug in any API keys or anything like that. So you can just type a sentence, Open Design

goes off and builds stuff. your own agent runs it and then you get a finished design. Now, as an example of this, if we go to our settings here inside agent OS and then we shall go to the settings section, scroll down, you can see here that we can plug this into our existing CLI. So, what does that mean? That means for example, if you have Gemini CLI, which is free, you can operate this. If you

have open code, which has free models, you can operate this, right? If you're already paying for a claude subscription, well, you can use that to operate open code, which means that you can use free models and existing CLI you already have to run this whole system and build and automate whatever you want. That is absolutely amazing when you think about it. Now, if you're wondering how do you use this? Well, basically they have installation instructions on

the GitHub as you can see, and there's all sorts of amazing things you can build here. You can even run it with Hermes, which is mind-blowing in itself. So you can get an agent to run this directly. You can see all the cool stuff that you can build with this. Right now you might be wondering, okay, like well how do you set it up? So we've already plugged it into our agent OS. Otherwise you can just

follow up with the setup instructions inside the GitHub and then from here you build whatever you want, right? Um and also this is open source so you can actually customize it however you want to and you can see some examples of what's already inside our workspace and what we built this. and it's it's super fun and it's easy to build. Now, if you're wondering, okay, once you've set up, how do you actually start using it? So,

basically, you can just go down to the community section here, find a design that you actually like, and then you can customize it however you want. So, for example, if we have a look and we scroll down and we're like, do you know what? I really like this one. Okay, great. Let's click on make the same. like so. And then we can just change this and explain exactly what we want. So let's say it's for example

for an AI or for the AI profit ordering community and AI automation community focused on helping people save time and grow with AI. We can hit send now. And basically what that's going to do is start building this out step by step. So you can see we've got the prompt on the left we're using Hermes with a free model called step 3.7 flash free and then from here it's going to start creating on the right hand

side. So on the left hand side we have the prompt itself. On the right hand side the creation will appear once this is fully built. And so this is just working in the background whilst I go off and do other things. I can even, for example, open up a separate tab of the agent OS and just go off and start building inside a separate CLI and just build whatever I want there, which is the cool thing

about this whole system and it's all ready to go. So, you can see it's now building out step by step. That's super easy. And now you've got your own personal free AI studio and it's running on free models because, for example, Hermes is a free open source project you can use to build with it. And then step 3.7 flash is free to use inside Hermes. How amazing is that? So now you got a free AI studio

designer. Um you don't need Figma. You don't need to wait on designer. You don't need a team of people. Everything can just be built and automated. Now the AI design studio, here's the way that I look at it. This is a framework that I've built for you so you can understand exactly how to use this and get the most out of it. So you can have a full design studio that lives inside your own machine and

runs on the AI agents you already have. Now there's five things that make this work. You have one sentence you plug in. So you can describe what you want. You get a real prototype. That could be a dashboard, could be a slide deck, could be an image, could be a video. You don't need any design skills. It's a blank canvas. Um, and there's no wrestling with templates. This is just ready to go. As you've seen right

here, we've already got the website pretty much. Oh, look at that. We've got the website already built. How amazing is that? Now from here what we can do is we can click on download. We can open that up. It will be inside my workspace as well. That's the great thing about having an agent operating system. And we've just built this stunning website in like one click. How insane is that? So that was super easy to set

up and build. Um super chill. And then you can see that's still beginning to edit and build out. You can see already that we've got the example here and it's now being customized to us. So if you look at that previous version we just opened up, it says introducing AI powered web design which the original template we used but now you can see inside the preview that it says introducing the air profitable room. So it's customized

the design around the topic that I plugged in which is the air profitable community. [snorts] Now we can also there's there's a lot you can do with this. So for example, you can click on the design section over here with the design files. You can view the index as well. You can open this up. You can click on new sketch. You can uh check what you've built etc. You can see here that we've got this and

we can also open this up and then we can download it. We can also share it with people as well. We can deploy it directly to our websites. We've got the settings here. So we can actually change the appearance and everything else. definitely recommend dark mode there. And then you can see what's been done. Now, if you want to customize this even more or change the design system or anything else like that, you can just type

inside the chat here. So, whatever changes you want to make, you can make it inside the chat and it's pretty relaxed and easy to do. Now, if we go back to the workspace here, you can see that we've got the full design ready to go. And I just automated and built that whilst I was talking to you. So, it says introducing the powerful boardroom. Explains what it does. talks about it, etc. It's got a link to

the community at the top, the playbooks, the process, um, and everything about it. Right? And that was fully automated into like a beautiful UI in just a couple of minutes. Now, if we also go back here, you'll see our recent projects inside this section. So, we can come back to it anytime. We have the chat here where we can talk to it. We have our workspace where we can quickly open up these other projects. And if

we just click on this one, it just opens up like that. Click on that one. Boom. It's open. And so you can just have like amazing designs in one click with this AI design studio. Super simple. And so just to recap, one sentence in, you build it. Your agents run it. So it drives the CLI you already have plugged in. You can use free CLI, you can use free APIs, you could use local models. So if

you want this completely free, you can do that. It has 150 design systems built in, which is unbelievable. So over 100 skills as well for UI. So if you want to create better UI, this is an amazing way to do it. It stays on your computer, so the whole studio runs locally, your ideas, your brand, your work. None of it leaves your machine if you don't want it to. And it can run on free private local

models. And then everything sits inside your agent operating system next to all your AI agents with one screen, one workflow. So design just becomes another thing that the agent operating system can do, right? And there's so much you can do with this already. Like for example, we've got the SEO section. We have the loop engineering section here for quality control. We have a music agent, video agent. We have notebook 11m plugged in camb board, the memory

galaxy for storing all our memories and everything that we do. And now we have open design plugged in there too. So it just becomes exponentially more powerful the more stuff that we build in here. It's unbelievable. Now let's talk about the old way versus the new way and why you would do this. And this is a big shift because most AI design tools you you don't own and you can't really customize. This system you can build

however you want it and you can customize it exactly how you want it. So for example, the old way is like you'd be using Figma plus a designer or hours of messing around. Every AI design tool wanted its own API key which could get expensive and then it could run a weak or local model that actually makes really bad stuff. And I think we've all seen this even with Claude. Example, if you're using claude light, usually

the outputs are pretty bad with UI and you have to go back and forth a lot or you have to give it examples to brief it on exactly how you want your UI to look like your user interface. Now the design is really easy to automate and it actually looks good because you've got those design skills plugged in and so your agents can build and automate really nice design straight away. So the old way is like

you know the result is design is the bottleneck that keeps that you keep avoiding with AI. I know plenty of people that do that. The new way with the AI design studio is that number one, it's free. Number two, you can build in a sentence. Uh, number three, it runs on agents you already have, so you don't need to add new API keys. You don't need to rely on local models. You can have your Frontier agents

do the work through the CLA. It lives inside your agent operating system beside everything else with the workspace and everything. The whole studio runs on your computer and the result is you get design the speed you can think of, right? And that's exactly what we did today. Now you also might wonder okay why not just use claude design directly and you could but the thing is with claude's design option that runs in anthropics cloud not your

machine it only designs with one model which is claude which use up tokens it runs on your cloud and anthropic usage and subscription your designs live on their servers and it's closed you know you have to use it exactly as they ship it and if you don't have internet you can't use it if you have this system running with local models you can still use the system. So it runs the new way with open design is

like it's free, it's local, you can use any agent that you want and it works offline. And bear in mind the cool thing about this is when you plug in Open Design into your system, it already knows every agent you run. And this is the part that makes it click. So when Open Design starts, it scans your Mac. It finds every coding agent you've already installed. Then it just uses them. No setup keys. uh nothing to

paste on my machine. For example, it found Hermes, Claude Code, Codeex, Gemini, Kimmy, and anti-gravity. And I could just plug in these agents just from a drop-own box. So, it's super simple. You can see exactly how that works inside the terminal right here. So, that's basically what it makes, right? Prototypes, dashboards, slide decks, images. It uses hyperframes as well for videos, and it's got 150 design systems inside there. Now, if you want the full AI design

studio inside your agent operating system, I've already wired it in the dashboard where my agents live on one screen. It detects your CLI, designs from sentence, and embeds right there next to everything else. So, you can get the full agent operating system with every agent on one screen and the design system built in with the AI design studio setup, a 30-day road map as well, and a room of 3,600 founders with someone online to help you

24/7. You can get that all inside the air puffer volume link in the comments description or go to the pufferboard.com. So you can run open design, let it find your agent, pick your designer and then start building. Now let's talk about three things that people get wrong. Some people say well AI design tools that they require a lot of tokens. Again you can use free models, you can use free APIs, you can use the CLI that

you already have running. So no problems there. Number two is some people say, "Well, if it runs on my own machine, it must use a weak model." Actually, no, because it can use your frontier agents through the CLI. Plus, it has over 100 skills and 150 brand systems. So, the app is local, but the brain that powers it. That can be your frontier level model through the CLI. Number three is like some people say, well, setting

up another tool would be a pain um and it won't fit. That's exactly why we give away the agent operating system inside the air volume. So, this is just ready to set up and install straight away. And you might say, well, that sounds complicated. actually no like so many people we've had over 184 pages of wins testimonials people building amazing stuff with this you see all the people building their own agent operating system so I know

if they can do it and I can do it then you can do it too right none of us are coders but we can all do this so what changes when you wire this in well you don't need to pay for design you don't need to use API keys you don't need to use weak tools you can use your CLI you don't need to switch between apps everything lives inside agent operating system you don't need to

have your work on somebody else's server and you just started shipping straight away. Unbelievable. And you know, design used to be the bottleneck. Now it's just one sentence away. Now, if you want the whole studio inside your machine, you know, you've seen it work. You've seen how powerful is. You've seen use cases and examples. You can build websites, apps, tools, videos, games, whatever you want with this stuff. You can get that all inside the air room.

So, the full agent operating system, local claw, GLM, Hermes, etc. It's all inside there. So, this is my AI automation community designed to help you scale, save time, and grow with AI automation. You can ask questions inside the community, and I answer them ASAP personally, and so does the whole community as you can see right here. And then also inside the classroom, you can see all of our best trainings and new classes. We have the full

agent OS ready to install with a video tutorial, the last update date, and zip files to keep using it. We've got new daily tutorials dropping on all this cool stuff that we're building. You can also get access to all of our best lessons and trainings. We have four weekly coaching calls where you can ask questions, share your screen, um wireless in real time. And then also inside the map, you can meet people locally who are building

with stuff like this. Right? You've seen how many people are getting results to this. You can connect with them inside your local city. So feel free to get that link in the comments description or go to the aiprofit.com. Thanks for watching. Cheers. Bye-bye. There is a brand new local model called North Mini code that is super powerful for coding and you can also get access to it for free. So this is available on O Lama now.

So, North Mini Code and OAMA are working together and it's pretty powerful as you can see right here. So, if we look at the benchmarks, it's a little 30 billion parameter model that scores models four times it size according to the artificial analysis coding index. So, you can see for example how North Mini Code which uh is performing at 33.4 here is outperforming Devstral, Mistra 4 and Neatron 3 Super, which is unbelievable. Now, we've got it

running inside our agent operating system already. So if we go to the local section here, we can build with it and we have North Mini code plugged in. You can also plug this into your AI agents and that means it's free, it's local, it's private, it can work offline and it can actually build stuff. So for example, let's give it a little test right here just as an example. Build a colorful to-do list app. And then

we can control this with our voice. We can start building with it. And you can see that's working right here. And so this is local. It's ready to go. It can actually build stuff and it's free to use, which is unbelievable. Now, if we actually go to the preview section here, we can see what we've previously built. So everything that we've built is saved. And then you can see that is quickly coding out here. Now, once

that HTML is fully coded out, we can actually preview it. as you can see. And if we test it, it actually works. Unbelievable, right? So, this is a free local model just dropped, works privately, works offline, works with Hermes agent or whatever agent you want to plug into. And also, we've got a workspace here where you can use your local models with this whole system and it's really good and ready to go. So, you might be

wondering, okay, how does North Mini Code work? how does it perform, etc. Let's pull up the benchmarks right here. So, if we compare it on benchmarks, it's not quite up there with Quen 3.6, but you need a good setup for Quen 3.6. However, it is outperforming Gemma 4, as you can see on Terminal Bench. It's also outperforming Gemma 4 on Terminal Bench Hard SW Bench verified. It's absolutely crushing Gemma 4 and it's right up there with

Deathstrom Small 2 and it's up there with Quen 3.6 six as well surprisingly. So it's an agentic coding model that's pretty powerful and easy to build with as you've seen. You can even control it with your voice. You can build stuff with it. It actually works and it's ready to go. So pretty powerful stuff. So let's talk about the local AI coding engine. This is a free coding model that lives inside your your computer. It's fast,

it's private, it's made for building and five things make it work. So number one, it's a coder. So, North Mini Code is trained for one job, which is writing software. Number two, it's a small body, so it's only 30 billion in size, but only a few experts actually fire up a word. So, it's quick to run the seesaw. Um, and it outscores models four times larger at coding, which is unbelievable. So, it can outperform models four

times its size because it's small, but it's a mixture of experts model. It has reasoning on, so you can switch on reasoning whenever you want to. It's free and it's under the Apache 2.0 license. Uh works offline, too. And you can build by voice as well. So, let's compare these side by side. You know, you could pay for a subscription, but that would get expensive. Or you can use a tool like this to basically code unlimited.

You've got a free coder built only for software. It beats models four times its size. It works at 92 words a second on a normal Mac with no limits. Nothing you type ever leaves your machine. You say the word and a whole appears as you've seen today. And the result is a fast private coding engine that you actually own. That is unbelievable. Now, how does it work? Why is it so quick? So, it only wakes a

few experts per word. This is what makes it so fast. You can run this on a laptop, too. So, old models wake the whole brain for every single word, which means big models are quite slow locally. North is split into 128 experts and only eight of them fire for each word. So it's a giant brain with tiny effort and that's how a 30 billion parameter model runs as quick as a small one as you've seen. So

what's actually inside it? Well, it's 30 billion parameters total size but only 3 billion uh fires per word. So eight of it is 128 experts. That's where the speed comes from. 256k context window which is pretty good. That is pretty impressive. But bear in mind like Kimmy K2.7 which is a really powerful model that only has a 256k context window. So it is good. Then you got 3:1 attention mix which means that it's quick on long

files and also it's RLVR trained on real work with reinforcement learning with verifiable rewards on real software and terminal tasks not just text. has native tool use. So, it's built to drive coding agents, call tools, run a terminal, think between steps. That is great if you want to plug it into Hermes agent. And on Apache 2.0, it's free and open, right? Uh you can use it for anything, including commercial stuff, which is pretty nice. And also,

it was trained across real coding agents. So, SW agent, open code, terminus, and more. So, it's good at messy real world work, not just clean benchmark puzzles. Now, you might wonder how, okay, how big is the file? So, it's 19 GB at Q4. So, it fits a 16 to 36 GB Mac with room to spare. 92 seconds uh 92 words a second on my M4 Max, which I measured. So, it's quicker than model's half it size.

It punches above its weight. So it outscores Neatron 3 Super, Mistral 4, and Devstral 2, and it scored 33.4 on coding index, which means it beats Quen 3.5, Gemma 4, and Dev Straw small 2. Now, I actually tested this just on a quick snake game test. Um, if you don't have the thinking on, it takes about 20 seconds to build. If you have thinking on, then it takes about 48 seconds to build. And you can see

some examples. are just you know interesting fun stuff that we built here. [clears throat] Now we actually keep it warm to make it feel instant as private as well. So we keep it warm in memory so it never has to reload and that just means that there's no lag when we're using it and then also it runs on a loop inside our Mac which we actually checked as you can see inside the terminal here. Now if

you want north and this full coding engine inside your dashboard you can check it out. We've actually already built it into the agent operating system. So you can get that inside the agent OS with the voice input um builds previews live. Every app is saved in the workspace and sits next to my cloud agents as a free fast coder. Plus we've already plugged it into Hermes agent as well. So if we go to Hermes here, we

can use this model with Hermes agent too, which is unreal. We've got the local agent ready to go right there. So you can run it in about 10 minutes. You just need to update Olama, pull north in, keep it warm, and then wake it once, right? And if you're wondering how do you do that inside your terminal, here are the instructions you can use to run this inside your terminal quickly, step by step. So it's it's

done in like four steps, as you can see, and it's pretty powerful. Now, some people say a free local model can't really code. I mean, it outscores models four times its size, so that's pretty impressive in itself. And you've seen it actually build stuff today. You might also think, well, a 30 GB class model will be way too slow. Only fires like eight of its 28 experts, so it runs at 92 words a second. It's pretty

good from what I've tested so far, and you've seen it work live today. Also, you might say, well, setting up a local model is too technical. Literally, it's three short terminal commands. So, we give you the commands. You can see them right here. This is how you can run North Code Mini on your machine. So, just to recap, here's what you learned today. You learned how to run a free model on Apache 2.0 that's a free

coder. You learned how it actually outperforms giants four times the size, which is unbelievable. Again, I would test this all for yourself. Don't like believe all the benchmarks. Test out yourself. See what you think. If you like it, great. If you don't, try a different model. You learned how to stop waiting because it's pretty fast. You learned how to run it privately and locally. and you learned how to pick between speed or depth. So you can

switch on thinking on or off and you can build [snorts] by voice as you've seen today. Now if you want to get the full system from me, you can get that inside the agent OS system. Um this is inside the proper boardroom. So you get the full agent OS with North Claw, GLM, Hermes, and more inside one dashboard. You get the local AI coding engine setup with the voice control, the previews, and the system where it

just runs warm ready to go. You got a 30-day road map inside the profitable boardroom. And you can get this all inside our community here. So if you go inside the classroom once you've joined link in the comments description or go to the airwarm.com then go to the agent OS system here you can grab the video tutorial. We've got the last updated date on this whole setup the resources with the zip file and we add new

daily tutorials as you can see to get the most out of all this stuff. Inside the community, you can ask questions and each day I answer them with a video tutorial so that you can get as much help as you want. Inside the calendar, you can jump on weekly coachs, share your screen, ask questions in real time. And then also you get a map where you can connect with people locally who are building with AI agents

just like you've seen today. So if you want to get that all, it's inside the profit boardroom link in the comments description or go to the air profum.com. Thanks for watching. Oh no. >> There we go. [laughter] Today we'll be Oh, this is pretty good. We're using North Mini free locally and on a free API with Hermes agent and it's actually good. Wow. There's a brand new free API and free local model that you can use

with Hermes agent and it's called North Mini. I'm going to show you exactly how it works. We've run it both locally and also with the API. Pretty powerful stuff. Super fast. And it's designed for agentic coding. We've already plugged it into Hermes agent like you can see. And we said like are you working? And it actually replies like you can see right here. So, it can work with Hermes agent. He's pretty quick to reply and he

can do all sorts of stuff. So, if we say, for example, schedule a Japanese practice session at 5:00 a.m. today or 5:00 a.m. tomorrow plus daily as a schedule task inside Hermes. We can plug that in and then Hermes will use North Mini to just go off and build this. Now, you might say at this point, okay, how does this work? What are the benchmarks like? How powerful is it? How do you get access? I'm going

to cover all of those questions today. So, number one, how do you get access to it? So, you can actually get access on open router. So, if you type in North Mini, you'll see North Mini code is ready to go. It's 256K context window and it's free to use and you can plug it into Hermes agent directly. Pretty awesome. Now, how do you actually set this up with Hermes? All you do is you go to your

terminal like so. And then you go to Hermes model, select open router from the list, and then you would select North Mini code as the model for uh your Hermes agent. That's how easy it is. So just type in Hermes model set up over Maruta. So what is the API? It's this free one. How do you get access to it inside terminal? Now you can also run it with O Lama. So if you prefer to use

O Lama and run it locally, this is not a cloud model from what I've seen. So you can install Oola in one single click using this terminal command. And then from here you just go to this section and you can see again it's a local model. It's not cloud-based which means it's free for anyone to use and run locally. And then to pull the model you would click this paste into terminal with alarm running. To run

it inside Hermes agent you can use this terminal command. You can also run it with open claw clawed codeex app codeex and open code as well. Pretty awesome. And so if you are out of tokens or if you've run out of usage on your existing limits, you can just use a free model like this and plug it into Hermes, right? Nothing can stop you. That's pretty cool. And so this is how you can use the system,

how it works, etc. This is something I call the free API command engine. So you can wire it into Hermes and you get an agent that can write files, run tools, build real things for you for free. And you know, we just for fun, we built this out with Hermes, but you can use it aentically and it can call tools. It's actually a very small model. So this is a really small model if you're running it

locally, which means it's really fast and it outperforms Gemma 4 uh on some of the benchmarks. It's 30 billion parameters with 3 billion active. It's one command to run it 256k context window and free whether you use it on the API or if you use it directly with um as well. So you got two different options right there and you can see that it's working. It scheduled the task pretty simple and easy and you can see

that it's currently scheduled that Japanese practice that we just talked about right there. Pretty nice. So here's the announcement of North Mini and its setup and you can see how it performs on benchmarks. So again you would compare it against models like Quen 3.6, Gemma 4. These are the comparable models if you want to understand how it works etc. And you can see the quote from Coher here who built it. So, North Mini Code is Coher's

first agentic coding model. A 30 billion parameter mixture of experts model with 3 billion active optimized for code generation, agentic software engineering, internal tasks that is perfect for Hermes agent. It's also available on hugging face and open routter for free as well. So, you can see the details on hugging face right here in terms of the architecture, how it works, everything else. So, how can you wire it into Hermes? You would just grab a free open

router key, create a Hermes profile for it. So, we actually created North Mini as a profile, and you can use this terminal command to create a separate agent profile for North Mini. Why would you do that? I think it's good to separate agent profiles by API because then if one goes down you can use another one. You don't need to switch the models manually and also you can test them side by side and give them the

same tasks. So if you look at our agent operating system for Hermes you can see that we can select between all these different models and we have the conversation history for each one and we can just use them based on their skills. So we have communicated 7 quen 3.7 and also north mini ready to go. We can see the full conversation history over here. We can also talk to our AI agents. We can voice activate them.

We can generate images, video and voice with them as well. But if you just want to chat with North Mini or build out teams with them, you could also use the camb board here. So you could actually set up a camb board just for North Mini and then give it tasks. It will automatically triage you inside the camb board and build it step by step. So now at this point you understand how to set up an

agent profile for this, how to run it with free API or with local models. You've seen it work in action. you've seen how powerful the model is. Like is a big big update. I mean, it's it's pretty useful. A lot of people run out of tokens quickly. This is the opportunity to to fix that. Now, let's talk about the old way versus the new way as well. So, if you're using an API currently or every agent

uses up tokens, you have to kind of ration those tokens and you're scared of doing stuff because you don't want to use up too many tokens whilst you're building. And that is a big problem, my friends. Right? And then also you might want to let it run overnight as a 24 AI agent, but if you're running if you're scared of running out of tokens, well that's a nightmare, right? Whereas if you have a free API, you

can run it all day 24/7. There's no meter, especially if it's local. You have a free agentic model wired into Hermes. You can throw every small job without thinking twice. You can spin up several agents in parallel for free. And you can save the mo the premium models for the jobs that actually need them, right? So you can use your Frontier models for the really powerful jobs and tools like North Code Mini for the small jobs.

Now if you want every uh system and setup that I've shown you today inside the agent OS, you can get that inside the profit boardroom link in the comments description or just go to the AI profit.com to get access. And you also get four coaching calls a week, plus daily tutorials as new models drop, a 30-day road map, every prompt in the Obsidian memory setup for all your agents, and 3,600 members inside the profitable volume who

are building systems like this as well. So, you can get that all inside there. Now, some people say, well, free models can't really build anything. But you've seen how it worked today, like it can actually be used to. Other people say, well, setting up a new model, that's a lot of work. But as you see, it's just like one quick copy and paste terminal command. And other people say, well, I'll just keep using my paid model

for everything, but then you keep paying for the cheap jobs, too. Whereas you could route the grind to free models, save the premium for what it's worth. Um, and that's the whole game right now. And you might say, well, this sounds technical or difficult to set up, etc. We've got 184 pages of testimonials and wins from people setting this sort of stuff up inside the AI profitable boardroom, right? So, if they're nontechnical and they can do

it, and if I'm non technical and I can do it, then we can all build with this, right? You don't need to be a coder or developer or technical to build with AI agents anymore. That is totally changed. So, what you just gained a free coder co here north mini code completely free on the API. A real agent because you've wired it into Hermes. It can write files. It can run tools. It can build. It can

schedule tasks for you. It's a twominut setup. You just set up a profile. Showing you the terminal commands for that already. It can build. So you have one command and then you get a finished artifact in its workspace. So for example, everything that we build with whatever agent we're using, we get the full setup inside here. Right? So we can see what we've built. We can preview it and we can come back to it later. So

everything that we build with our Homies agents is saved inside our workspace, which is just awesome. and easy to use whenever we want to get there, right? And then you can run it all day, especially if you're running it local. So you can have this running 24/7 and doing task view and you actually have the output because this is an Apache 2.0 weights license. Um, so you can keep everything that makes and I would say, you

know, honestly the best agents to experiment with are the free ones because it doesn't matter like if you're not going to worry have to worry about tokens or limits or resources. You can just, you know, build cool stuff and see what it does. So if you want to make the free model part of your system, we um you know there's new free models dropping every few weeks now. The agent operating system inside the air offer boarding

lets you wire each one in and route work to whatever is best and the cheapest without rebuilding anything. So if you want the full agent operating zip file with Hermes and every model inside one dashboard, the setup walkthrough, four weekly coaching calls, 3,600 members and 155 uh sorry 184 pages of members wins. You can get that inside the AI profitable boarding link in the comments description or go to the aiprofitboarding.com. Inside the community, you can ask

questions, get help and support in real time. I answer these questions personally. Inside the classroom, you get access to all of my best trainings, including the new daily updates, and we have the agent OS system over here. We update it daily. So, we're going to add a new version later today. You get the video tutorials, the zip file, and new tutorials added as they drop. You can also jump on weekly coaching calls, get help and support

in real time. Inside the map, you can meet people locally who are building with AI agents like Hermes and North Mini in your local area. And this is all available inside the AIO boardroom link in the comments description or just go to the.com to get access. Thanks for watching. See what questions we got here. H I should try some of these says Jack. Does Hermes agent work good for coding? I'm used to claw code and codeex.

Looks like you're using it well. Yeah. So it's okay for coding. I mean it's not like for example Hermes is it's not really designed for coding. It's more for agentic tasks. So the way that I would look at it is you build with clawed code and codeex for like big coding tasks and then you use Hermes for agentic work like scheduling and and actually doing stuff in the real world, right? So for example, if you wanted

to schedule a task, if you wanted to call tools, etc., then you can use Hermes. >> [music] [music] [music] [music] [music] [music] [music] [music] >> Where the >> [music] [music] [music] [music] [music] [music] [music] [music] [music] >> Fall [music] >> [music] [music] [music] [music] [music] [music] [music] [music] >> This Today I want to show you a super powerful system we've put together which is basically like an AI avatar video engine that can not only create the

avatar but can also put the whole video together, add B-roll, do the research, edit it all together like a full video team, except it's not a team. It's just an AI agent that plugs it all together and all you have to do is type in one single prompt and it goes from brief to research to avatar to edit and then you get the full output. So you might be wondering, okay, you know, how good is this

stuff? So you can see an example right here. Let me pull up some other longer form examples. So This is an example of a full video setup put together. Let's open this up. Stop. model. >> So, you can see like the quality of the B-roll, the beautifully edited screen, etc. This is all put together in one side, one prompt. Now, here's where it gets really crazy cuz it can actually create like full 6 minute videos. So,

this is uh a 5minute video put together with B-roll, the research, the script, the voice over, etc. And it was all fully done using this video agent. So, we're at a point now where basically you can generate, you know, 5 minute videos in one single click that actually look good and it's super easy and simple to do. And this is using our full infinite video engine system that I'm showing you right now. So, how does it

work? So, you can literally type in a topic here and then it will come up with a video. So let's say for example, North Mini code which is a new free local engine that just dropped. If you that AI has just dropped, let's get it to do some research and create a script around that. So we can say okay North Mini Code local AI agent plus O Lama. So we can plug that in. That's what the

video is about. Literally as simple as this. We can also change the settings here. So we can change like the time and how long it will go for the voice over. So whether it's a presenter, so like a a presenter or like an actual voiceover. So we can just add my voice here. And then we can choose between grock or miniax for generating the B-roll. And it will edit it all perfectly for us. Now we can

also change the length here to like 10 minutes long if you want. But just as a quick demo, I I'll make this like 30 seconds long. So from here we can click on write the script and that will now begin to script out the full video into something like this. So what it's going to do is script out, but it's also going to script out the B-roll scene by scene based on what you're doing. Right? So

for example, depending on what the topic is about, it will generate relevant B-roll to that as well as a relevant script. And it's also going to research the topic directly. So you type a topic, it researches live, it writes the script, it speaks it in your voice. Um, it puts Avatar on camera, finds the B-roll, and edits the whole thing into one finished video like you can see right here. It's absolutely unbelievable. And these are three

different examples which you can see in action. Three different videos built. So, you don't have to put like a face on it. You know, you could you don't have to put an AI avatar on it. You can just have it as a voice over, which I think looks even better. And sometimes that is even nicer. And then you can see this has come back to us with the full script and the B-roll and everything else. Right?

So we have the individual scenes for each part. Then we have the details of the script. So what it's going to say inside the voiceover. And we also finally have the scene by scene for the B-roll as well. If we want to change anything, we can actually click rewrite. We can go back to the brief if we want to change the topic. And if we're happy to go with that, we can just check all the research

notes here too. And if we're happy with that, we can now click on generate avatar and B-roll. And you can see that is now creating the avatar and also the scenes for the B-roll, right? And it it plugs it all together as one simple system. So you can see how you can just type a topic and that's basically it. And all you do is you literally just check a couple of things, quality control, and you're good

to go. So before like making a video would take up a lot of time, it's time consuming. It's energy draining. Even for example using AI to do this was not that simple. Now this is a very powerful simple system that we've built as an infinite video engine and it's inside the profitable bottom if you want to get access to this. Well, you could build your own as well if you wanted to. You don't have to to

use my system. But the main thing here is like this is what's possible now, right? This this is what you can do now. And what scares me is how fast this is moving and then also how this basically replaces a whole team of people, you know, in like one click. is pretty unbelievable when you think about this. So, if you're watching this, you know, I would start looking at this ASAP because this stuff is moving really,

really fast. And so, it just goes from research to script to voice uh to avatar and then we get the whole thing finished and set up here. And the other great thing about this as well, you can see when it's ready. So, we've got the avatar ready there. And also, we can view everything that we've previously created as well. Now you can see the B-roll is generated as well directly here. So we got the B-roll for

each section. Scene number two is just getting done. And then also if we go to our video agent, we can see everything that we previously created inside the workspace here, which is great. So we can come back and we can view what we've built and we can see everything that was done previously as well. So that's all ready to go and done now. So we can now click on assemble and that'll basically edit the whole thing

together, put it together so it's looking good. Okay. And then once it's completed, it will land in the workspace and we'll also be able to preview it here too. That's how easy it is. I want to explain something more complicated, but that's basically how it works. Now, if you're wondering again like how was this whole thing put together? It's like a combination of uh Hey Gen 11 Labs and then Miniax for the B-roll and also you

can use like Miniaax or whatever agent model you want for doing the research itself. And then [snorts] we've put this inside the agent operating system just because you know anything that you do day-to-day you want to have it in like a one-click workflow which is why for example we've got SEO over here. We've got the music agent over here. Right? Every workflow that I work on dayto-day I just try and automate it. And you know if

you're watching this I'd recommend that you do the same just so that you can save time and it's easy for you to come back to. So now you can see the full video ready to go. This is the one that we just created. Super [snorts] simple and easy to set up. It's got the voice over there. It's fully edited. The B-roll is combined together. Um, it looks awesome. Even like the change of the camera angles and

everything else. And you saw how simple and easy that was. So, that is the infinite video engine. You can also make much longer videos. So, I showed you a 6-minute video before, but basically you can type one topic into the director. It reads the re um it researches everything, creates a voice over, creates the avatar, creates a B-roll, plugs it all together, and then it's all inside one dashboard that you can customize and build you want.

Right now, some people say "Okay this seems hard to set up." Honestly, if you can type a sentence and click a button, you could run this because it's all automatic. So if you look for example, we've got loads of people inside the AR profitable volume who have set up my exact system for mission control and this agent operating system and they're getting awesome results with it. So if I'm nontechnical and you're nontechnical and we're all not

coders, then we can all get results with this, right? It it doesn't matter about your experience or anything like that. And then you can type one sentence, it'll go off and build stuff. It researches a topic, writes a script, adds a voiceover, adds a B-roll, plugs it all together as you can see. Other people say, "Well, AI video doesn't look very good." But you can actually see this looks really good and it's better than what most

editors can do, right? It all fits together really smoothly. Other people say, "Well, I don't have time to learn this." You literally, you just learn one box. Like, you already know how to prompt AI. You already know how to talk to chat or text a friend. If you know that, then you can use this system. And people say, "Well, I'll wait until you know something is more proven." But the people using this daily with this now

are moving forward whilst everyone else waits. So you don't want that gap to widen anymore. I think if you've not used this before, if you've not learned this before, this is a perfect time to start learning. So that's what you've learned today um in terms of you know what you could do. You could use this for content, you could use this for clients, you could use this for like even courses and stuff like that. So there's

so much power to this as well and it could work for any business as well. So if you want to get the full system, the whole video engine, you can get that inside the AR prof. You get the full infinite video engine, the full agent operating system zip file, the setup walkthrough, four weekly coaching calls, 3,600 members, and it's all inside this community. As you can see, inside the classroom, you can get new daily trainings. We

add new daily updates, and we also update this whole system as you can see. So you can see the last update, you can see the zip file here. So it's all ready to go and you get new daily tutorials like you can see inside the community you can ask questions get help and support whenever you need to. Inside the calendar you can joining course inside the map you can meet people locally who are near you who

are building stuff like this and it's all inside the air for so see you inside there. Cheers for watching. Bye-bye. All right everyone, thanks for being on today. I will see you on the next one. Cheers. Bye-bye.