How to Maximize Claude Fable 5 Before It's Removed

Heat. Heat. N. Heat. Heat. Heat. Heat. How much? Heat. Heat. Heat. Heat. Heat. Heat. Bye-bye. Heat. Heat. Heat. Heat. DG Jerome, good to see you here, man. Thank you very much. Music agent doing his job. Fable 5 is back until the 12th, I believe. So, that's good. Good news there. Long may it continue. So, if no one's seen the news yet, Claude Fable 5 is available through July the 12th, which is great news. Heat. Heat. Heat.

Heat. I can just imagine like so many people doing that token maxing till the early hours just to get through to the deadline. Heat. Heat. Yeah, it's definitely worth making the most of Fable 5 whilst you can. This might be like the final time we see a a Frontier model included inside the subscription. So definitely worth it. your Gemini 3.5 Pro and HY3 videos today were great. Thank you so much. I think that was actually my

team, right? I did like a couple on HY3, but the team did them on Gemini 3.5 Pro, so credit to them. I think we may see monthly Grock models. What do you mean by monthly? Like new releases each month. I hope it gets better. I mean, I think they've got potential for sure, but what we're seeing with all these models is like they're dropping new updates monthly as well. So, it seems to be speeding up in

general. Yep, we can get that set up here. I'll do that now. Configure each model. By the way, if you do need to configure Agent OS and get it linked, uh, Michael, I've already met I've already DM'd you inside there. Uh, if you want to get the the agent OS, it's literally right at the top there, right? So, it's once you join the AR profit boardroom, it's literally right at the top there. And then you can

see it says Agent OS here. So, you can grab it right there. Um, and then I I'm pretty sure I DM'd you this morning, too. Yes. So, I actually direct messaged you already here as well. Um, so it's right at the top as soon as you join. And then in every video, we show you how to get it. And then also, we DM'd you, too. So, you should be able to find it, babe. Yeah, that's going

to get interesting. They've just been at the fringe for quite a long though. For quite a long time. That's the only issue. Heat. Hey, Heat. I think I heard it's coming later this year, right? You can already reserve a copy, I think. Well, we'll try and stay away from that. It's a bit of a distraction. Not good for productivity. Heat. Heat. Heat. Heat. Heat. Heat. Heat. Heat. Heat. Heat. Yes, you can. So, you can plug in

the agent OS as a CLI into the uh claw claw CLI. So, you can plug CL CLI into the agent OS. That's what I do to use it inside agent OS. Hey hey hey. to update to the latest version of the agent OS. Just get the file and then there's an update markdown file inside there that you use and you just give that to your agents to update it. So your agents can set that up for

you. Heat. Heat. N. Hey, hey, hey. Heat. Heat. Michael, Michael, Michael, let's let's pull this up, mate. All right. So, to get the zip file for the Agent OS, here's what you're going to do. You're going to go to agent OS, which you can see right here. And then you're going to scroll down like so. Right. And when you scroll down, you'll see it inside the resource se resources section, right? Um, so you see that resources

and then it's got a zip file here. That's the zip file you want, right? Um, and you see where it says Get the zip file attached below. That's what we're referring to. So, you want to scroll down. Get the zip file right there Michael. And it's right there, mate. If you have any other troubles, let me know. But you should be able to find it. So, you go to Agent OS here. Scroll down. Zip file right

there. So, Agent OS, scroll down, zip file right there. Yeah, if you want to get the latest update, then just get the new zip file. Bear in mind, like you don't need to update every version. Just get the version that you like or the version that you see a new feature in that you're like, "Okay, let's get that liquid drum and bass." That's what we're talking about. Heat. Heat. All right, All right, cool. Um, so here's

where you want to go, mate. Have you checked the DM I sent you? So you have access to the classroom and you go to the classroom. You go to new daily updates and the agent OS is right there. Um, also we'll add a new section inside here just to make it even more obvious. So if you go there you go. So you go here mate just click on that button. So classroom start here agent OS or

you can go to the start here folks scroll down agent OS the other option you have classroom new daily updates agent OS right um and that just makes it really easy. Yeah. So for configuring each tool inside the agent OS use the guide. So what you want to do is you get the zip file you give it to your agent to install and then you configure everything from there. And all the installation files and everything you

want to install is inside the agent OS system here. So it literally teaches your agent exactly how to install each part of it. Michael, just check uh check your DMs, mate. Heat. Heat. That's it. Work out and work in at the same time. productive. Heat. Heat. Heat. Heat. For Hermes Jarvis, you want to use the chat GBT realtime API. That's the only fast API I've seen for generating voice. So, I'd focus on that. Tried using Fable

5 for a text support script today. That's nice. Yeah, good stuff. Heat. Heat. Goodbye. I have Heat. Heat. Thank you. It's a pleasure. What do I do? Heat. Heat. Nice. Hey. Hey. Hey. How much has Paperclip influenced your design choice for OS? Not at all actually. It was just like one thing we plugged in, but yeah, it didn't really influence us at all. I mean, Paperclip itself doesn't really impact any of the other sections of the

agent OS. So, it's just like it changed our choice in terms of adding it inside the team orchestration, but that was it. HY3 works very well. I want to test out with codeex actually. is something I'm working on next. So Hortner says figured out um I'd ask about a clip paperclip since I'm currently messing with it to see if there's anything I can learn from it. So in terms of learning from paperclipip really is what it's

great for is orchestrating agents. So if you look at our agent OS with paperclipip builtin, we can have like multiple teams of agents as you can see. So we got Julian Goldie, we have Goldie Labs and we have Goldie agency and they all work together as different sort of AIdriven companies with different org charts. And so when you're building with this stuff, it's not really for design. I mean, you could build a design based company, but

what it's focused on is orchestrating teams of agents, having them work together, and then making sure that you can orchestrate, for example, Hermes or Claude inside one team to actually build stuff out. Then you can have them inbox you, you can see everything they've created. And it with our setup, we have the build section here as well. So, we can see everything that we build there. So, that's the way I'd look at it is like it's

a great system for orchestrating agents. Back in a sec. Heat. Heat. Heat. Heat. Hey everybody. Yeah, I'm not I'm not planning to add Higsfield simply because I don't know many people using it um that much. But I think you could, you know, you can easily build it out if you wanted to. Uh, yeah, for us, we just not going to build it out. But Hicksfield had their own sort of OS, right? It's Higsfield computer or something

like that. So, I think you could use that instead. Yeah, we're just building out some stuff inside the agent OS. Um, you can see the to-do list here in terms of what we're going to cover in a second. So, Claude agent loops. Uh, going to do a Q&A on the agent OS in a second. Setting up codeex with 10 cents HY3 to test it out and just building out some cool There we go. I walked in

the gym the other day. Someone said that to me. Good news today. Claude Fable 5 on all paid plans has been extended to July the 12th. So you have another four to 5 days to get the most out of Claude Fable 5. And today I'm going to show you exactly what I would recommend you doing before it actually gets removed. So just to recap here, this means that Fable 5 is now available on your subscription and

you can use 50% of your Clawude weekly limit on Fable 5. So this is pretty cool. And what I would recommend for you is you start thinking about the best ways to use this. You only have four days to use the best models. you don't want to browse him away. And you know, Fable 5 is Anthropic's new top model, the first in their Claude 5 family on the benchmarks I've run. It's the strongest model that I've

tested so far. And so, if you're wondering how to get the most out of this, I'm going to talk about three to four different moves that you can make right now in terms of a 4-day plan to get the most out of it. So, first of all, you just want to make sure that you do still have Fable 5 inside your Claude. So you can see we have Fable 5 over here and it's included until 12th

of July. And the way that we're building with this is first of all we are setting up our agent operating system. So recently I've been working on Overdrive just to get our agent operating system with every single workflow that I work on like fully automated inside one system. So for me for example, we have a full memory galaxy here. We've used Claude Fable 5 to actually build out some amazing Hermes workflows. And the cool thing is

about this, like anything else that you're working on, you can get Claude to help you. So, for example, if I spend a lot of time researching new ideas, trying to find content ideas, researching uh different keywords, different competitors, etc. And this whole system, Hermes Astros, was coded out with Fable 5, and it automatically finds competitor ideas and and new content ideas for me. and then actually gives me the angle for my specific business. So that is

method number one. And you know every single workflow that you work on day-to-day, you want to go into Claude Fable 5 and be like, how do I automate this? Can you build a tool to automate that? Etc. So another example here, we've got this outreach tool inside Hermes as well. And everyone inside our AR profit bom community was like asking how can you generate leads with AI like what's the best way to do it? And so

we wanted to make a simplified SAS that we could just give to people and they can search for the leads they want, send out emails, automate the actual email campaign, and then actually get Hermes to manage the email inbox and the send inbox. And we build that into this system here. So what you want to do really is just think about, okay, what am I working on dayto-day? And then how can I automate that? And with

Claude Fable 5, you're really at the point now where you can automate anything as long as you explain clearly what your idea is. And actually, one of the things I do see a lot of people struggle with is clarity is just understanding, okay, this is my idea, but let's break it down into steps. Let's simplify it as much as we can. So that's essentially what we do with the agent OS each day. In fact, every time

someone asks us for something useful, we actually plug it into our system so that we can help people as much as we possibly can. So, Fable 5 super powerful. We may be at the end of an era now where you can't use Fable 5 anymore as well. Bear in mind, like, you know, we might be at the point now where new Frontier models like Fable 5 don't get released on the existing claw plan. So, if this

is the last window, you might as well make the most out of it. And that also brings me to the next step which is you want to list everything that you work on and actually time it. And then the tasks that take the most time you should try and automate with AI as well. So I'll give you an example like back in the day I used to spend a lot of time doing keyword research for SEO.

So what we built out recently inside the agent OS and this is just based on me knowing from timing my tasks in the past that this would take a lot of time is we set up a tool where you can look through your Google search console data. You can filter the date range, you can run the research and then automatically we can automate our keyword research and it suggests the best keywords to us based on what

our website's already ranking for. Now, if I was to do that manually and go through Google Search Console, search for keyword ideas, filter all the data, look at the right websites, it's a lot of clicking buttons and it's a lot of time. Whereas with something like this, you can easily automate it and then you can just click on like use topic and automate the content and deploy it to your website too like you can see we've

done here. So the main point here is like you want to start building out an agent OS dashboard that connects all your tools together and then you can easily have everything together. And then also you want to make sure that you list every workflow you're working on. Write down each one of steps. So for example like five leads, check the domain, write the email, etc. That only takes like 10 minutes with notepad. And that is your

list. That list is your automation backlog. And then you want to make sure, okay, you're automating each workflow one step at a time. So don't ask like Fable 5, automate my business. Obviously, you want to be very specific in terms of okay, write out or create a code or create a tool that helps me automate this step by step. Here's what I do. Step by step, please set it up as a tool. So those two things,

the agent OS and then asking Claude to build out all your automation backlog tasks into agent OS is going to save you a lot of time as well. And the other thing I would say whilst you're doing this is that the problem with something like Fable 5 is that it uses a lot of tokens by default. It can run through a lot of tokens by default. So what does that mean? Well, you want to have a

system where you can minimize the amount of tokens you use. We actually created a token minimizer playbook inside the AI profit boardroom. He's got 10 different moves that you can use to reduce the amount of tokens that Fable uses. And this means that whilst you're building everything out for your systems, whilst you're creating all these automations and customer workflows and custom tools, you actually get Fable 5 to reduce the amount of tokens it uses so that

you can squeeze more out of it during this window because otherwise what's going to happen is you're going to rinse through those credits very quickly. So how can you do that? Well, one option, and this is something where maybe you don't have the time to sit down with Fable 5 for hours, but you know you're going to automate these tasks later. One option that you can do is you can actually get Claude and Fable 5 to

build out the plan for automating each of these tasks. So, if I'm like, right, okay, well, I need to automate SEO content. What I can do is go into Claude Fable 5 and be like, okay, build out a plan for automating this uh system that we want to automate next and then later with that plan you can get Opus 4.8 made to implement it. And actually, if you look at Kilo codes research on this, they actually

found that with the right plan where all the forks are decided up front, even a cheaper model or a less powerful model can get the same outputs because it's just following the plan. It's just implementing the plan. So, that's one method. Another method is that you can reduce the effort dial. So, inside Claude, you can switch between what model you want to use. There's, for example, ultra code and max. and then you can go all the

way down to low. Now, if you're not doing anything too powerful that doesn't require too much thinking, for example, like basic UI, then you could just go with medium or high, right? And that way you use a lot less tokens and you don't burn through the token allowance so quickly. Another option that you have is Headroom. So, Headroom is a powerful system for reducing and compressing the amount of tokens you use. It's a free open-source project.

You can literally just paste a GitHub link into Claude and it will actually minimize the tokens you use. And then you have something like to ponytail. So if you're coding out a lot of stuff, particularly for example, if you're building out an agent OS with an agent OS, it uses a lot of code. It's it's burning through a lot of tokens. So you can use something like Ponytail. And the great thing about that is that you

you reduce the amount that it actually reads and you make it like a lazy developer, right? So, for example, with the old method without ponytail, it might read like the whole file, like all 2,000 lines for code. With a new way, it actually creates less code and it reads through less code, which means that you can reduce up to 85% of your tokens. And I actually tested this out and that came through. So, these are some

really important details that you can use. I mean, just to recap there, build out your agent OS, list every workflow you work by hand, automate each workflow one step at a time, make sure that you have the token minimization playbook set up, and then once you have the best model as well, just stress test everything, right? You can run every automation you built, whatever breaks, Fable 5 can fix it before the 13th of July, and then

you still get the most out of this model. And then of course on the 12th, you know, nothing you built stops working because you stress tested it and you've automated every single workflow. So it's pretty cool. Um, you know, before it was supposed to end today, but now it's been extended for four more days, so you might as well make the most of that. Now, some people say, well, four days isn't enough time to build anything

real. Honestly, for most people, if they just sat down for an hour or two, they could automate most of the stuff that they don't want to do. Other people say, "Well, I'll just wait until Fable 5 comes back." That day may never come. Just just be aware of that. Like, there might be another model that comes out. I mean, you might get Fable 6 or Fable 7 that comes out next, but who knows if that's going

to come back on the subscription or not? And then people will say, "I'll hit my token limit in a day. Why bother?" But if you use those token minimization playbooks, uh we've got more inside the air boardroom. There's actually like 10 boos you can use. Uh you can DM me if you can't find it. But yeah, it's pretty powerful stuff. And also building the agent OS is is pretty life-changing. I mean, if we look at all

the testimonials here, we got 196 pages of people using our agent OS, and they're absolutely loving it, right? So, an agent OS can literally change your life. It's one of the most powerful things you can set up with AI. 99% of people don't even know about it. You're super early if you know about this. And it's pretty easy to set up. At the moment, pretty much everything that I do runs through our agent OS setup. And

some people might say, "This is too technical for me." Honestly, if you can just uh get us and give it to Claude, you're good to go. Like, that's pretty much it. All it takes to install the Agent OS. So, if you want to get everything from us, I mean, we've used Fable 5 for 3 to four hours every day the last uh you know, few days since it's been out, you can get my full system for

the agent OS inside the AR Profer boardroom link in the comments description or just go to the arrum.com. Inside there, you get the zip file ready to install. You get the token minimization playbooks. You get every CLI that you can plug into agent OS as well. So you can plug all your existing CLIs like Claude into the Agent OS. We also set up free local model systems as well. And you get four weekly coaching calls where

you get help and support in real time. Plus you can get all of our pre-built agents and you can connect with 4,000 members inside the AR profitable room. So link in the comments description or go to the profitable.com. Also got tutorials on Fable 5 inside there. If you want to get our agent OS, we just updated it. get a video tuto tutorial full step-by-step guide on how to set up and a zip file to install it.

And then you can see that we add new guides all the time on how to use it and all the best stuff that comes out. Inside the community, you can ask questions, get help and support in real time. I personally answer each question every day with a video tutorial. Inside the calendar, you can drop a weekly coaching calls, get help and support in real time. And then inside the map, you can meet people in your local

area who are building agent OS and um with Fable 5 like you can see today. So feel free to get that link in the comments description or just go to the aprofit.com. Thanks for watching. I used Oh no, sad times. Why are you always in the agent OS? Cuz it's super powerful. It's the best thing is HY3 in the AR profitable volume. So we have it inside the agent OS. We've built out HY3 coder inside here

and it basically uses the free a you can plug in the free API from open router and then just code out whenever you want to. So you can see for example here we've got HY3 coder. We can code inside this chat box. We get a preview of everything we've created and then we can save our builds for later. So if you want to use HY3 we've actually got a custommade system inside the AI profitable board over

here. Today I'm going to show you five different Claude agent loops that you can build to basically have Claude running without you autonomously to build and automate anything you want. Now if you're wondering, okay, what are loops? Essentially, this means that you don't need to prompt anymore because you can give loops to your AI agents like we've got right here. And I'll explain exactly how it works in a second. And each one acts, checks its own

work with an intermedi. Now, inside my Aentic operating system, I've actually built out five different loops. One to build anything to a spec, one that works with a camb board, one that takes an idea from inbox to shipped, one that watches the news, and one that writes your SEO, right? all running on one shared memory that makes them smarter every time. So I'm going to explain exactly how each loop works. Now the difference here is like

you are no longer the person quality controlling or checking anything which saves a lot of time and also these loops can run without you autonomously or you can actually add a human in the loop which I've also built out. So you can have two different styles of loops depending on what you want to build. If you saw the tweet from OpenClaw founder Peter Steinberger recently, he was talking about this as well. And it's essentially a system

where you're not going back and forth off with AI anymore. This saves so much time. It just runs in the background and you can get way more done with these powerful systems. In fact, your only job now is to make sure the ar you're the architect, right? So before, and you probably can relate to this, you know, for a year I was I was loop. So, I'd type a prompt. I'd wait. I'd read the answer, spot

what was wrong, type again and again, and nothing would move until I was sitting there driving it, right? So, my output was pretty much capped at how long I could stare at a screen. And for a lot of people watching this, you can probably relate to that. Now, what we have is a system where we build the loops ourself, right? So, I define what's done and what that looks like. An agent acts a separate judge checks

it against the goal and it repeats until its own work passes the quality control checks. Now we have five of these running inside the agent OS building, planning, shipping, watching, writing and they will run whilst I sleep and then I wake up to the work done and you can run the same right. We've actually got loads of people using the agent OS inside the air for one. We have over 196 pages of testimonials and wins from

people using systems like this. So if I can do it and I'm not technical and you you might not be you might be nontechnical too. You know this is a pretty powerful system. So how does it work? Well if you look at the old way versus the new way one makes you the engine the other makes you the architect. So for example with the old way with the prompting using the old way uh you type you

read you wait you correct on every turn. So most people going into chat GPT for example like this and they're just going back and forth and it takes a lot of time. is very inefficient. And the problem with that as well is like nothing moves unless you're at the keyboard. There's no check on the work but your own eyes. The output is capped by your attention. With the new loop systems, you write the loop, it runs

itself. You define done once. The agent acts. A judge checks it. It repeats on its own until it passes and it runs whilst he sleeps. So you wake up to it done, right? And every loop is the same shape which is act, observe, judge, and repeat. So it loops round and gets stuff done without you or you can have like just a quick check to say okay this is good to go. So let's talk about the

first loop here which is loop engineering. So for example, if we have a look at this system, we have loop engineering and what we can essentially do here is we define what's done. We give it a starting point if we have one and then we can select the builder aka the API for the builder, how many rounds it goes round and then which API we use for the judge. So you could have like a GLM 5.2

two which is a powerful model for the judge and then you can have a free API for the builder and that means number one you use less tokens and number two it costs less and number three this just runs around in a loop so you can say okay build out a website and we've built out several things here as you can see you can say build out this project and it will loop around however many rounds

you have the builder will create it and the judge will judge it and then it just loops around until the judge the work is done and I don't need to touch anything and also we can just the outputs we've created over here inside our workspace. So it all gets saved and I can check it up later. Next up we have the camb board. So this is loop number two. A loop with three rolls instead of one.

So for example, you can have a planner that breaks your goal into cards, a builder building each card, and a reviewer that checks it actually landed before the card moves to done. Let me show you an example of this. So, if we take a look at this, we've got this content system where we created a video and a step-by-step guide with a content judge. So, we have separate agent profiles. We just drop our task inside the

content board and then we can say okay build this video, create this blog, etc. And it can actually create the video or it can create the blog post as you can see. And essentially video builder would create the video, a director would help with that and a content judge would actually look at the content and see if it's good or not. And then once it's done, it all goes around here. So automatically the task gets triaged.

It goes into triage to do ready running blocked if it can't move forward and then done. And I don't need to touch anything. And again like the loop the the loop helps you quality control the work because it's just running on autopilot. Then we also have the pipeline. So the pipeline system is pretty powerful because you know you can use this loop for turning ideas into finished work. You capture an idea, an agent classifies it, roots

it and plans it, you approve it once. Then a project manager and its sub agents build it out and the whole thing lives in your vault. So nothing gets lost between an idea and it's done. So if we have a look at this for example, we have a system over here where we can basically go from idea to implementation without any sort of guidance from me. So if we have a look at this one for example,

this feature for an AI SEO app, we can let the agent shape it. And then what it's going to do from here is ask us to approve it. So we're going to say ask build and approve. And then from there, it's just going to start building out that example, right? So we can click on build the deliverable over here. It actually get completed, which is pretty powerful stuff. So this is running in the background. It's getting

completed. And then once it's done, you'll see all of our done projects over here. So these are all different apps that were built. We can see them, preview them, and literally the only thing that we have to do is just approve the plan, and we can delete any ideas, too, if we don't like them. And so the great thing about that is the we literally go from idea to done, and all I need to do is

just approve it. And I think that's a powerful loop because when you're looking at this, for example, like this system here, you can go from if you have like lots of ideas but you just don't have the time to implement them, you can build something like this out and you can see everything that you've built and you can come back to it later and it's pretty easy and simple, right? So everything is set up inside one

system. We can review it. Uh but the main thing is here that I don't need to be the one building. I don't need to be the one checking the work. I don't need to be the one like giving feedback or prompting or anything like that. So, it's super powerful. Then we have the Oracle. Now, the Oracle runs on a loop. This is built with Hermes agent and essentially it's a loop on a timer. So, every morning

it searches for the latest breaking news in AI because obviously I need to stay updated with that. It ranks it by relevance and hands you the six biggest stories to post content about today. each with the original source, your unique angle, and a ready hook. So, one click turns any story into ranked SEO articles on your website. Also logs every news update to our Obsidian memory. So, for example, over here, this is running um you can

see it was last consulted 4 hours ago. We can see that we've published loads of content over here. So for example like this this is a article we've already published on that trending news topic and we can do that every day day by day. And the great thing about that is that it's just running on a loop. I don't need to prompt it. I don't need to see it say like hey check the latest news or

search for me the latest news or um give me content ideas. I've got six of them ready to go at any time. So for example this one would be a great topic to create content around and it's just running in the background for me. The same with, for example, Hermes Asteros. Hermes Astros does the same thing. It monitors certain keywords and then gives us content ideas with unique angles based on those uh keyword ideas. And then

the fifth loop is the SEO pipeline. So the way this loops work is basically it generates keywords for us, right? So we can research keywords to create content around. Then we can click on use topic. Then we can generate the articles and we can generate SEO content in like one single click. If you want to see an example of that, you can see all these articles that we've published right here on our particular topic. Super easy

and simple to set up. And so it's an SEO content loop. Now the final loop that makes everything compound and work together is the memory system. So every time we are using these agents, we update our memory automatically. So if we look at the recent, you can see that Hermes Apollo just got updated inside our memory loop. And this is updated every few hours automatically. And so this runs on a loop because the memory is automatically

updated by our agents. And then our agents pull out the context and use that to update me and find new ideas and create better outputs for me, personalize to me because it knows inside my memory galaxy, my projects, who I'm working with, my team, my vision, my voice, my brand, my uh companies, everything is connected inside one memory galaxy. And so that runs on a loop as well. So that's basically it. That is every loop system

that we built. We built it out with Claude and a lot of the systems run in the back end with Claude CLI and Hermes as well. If you want every loop from me, if you don't want to wire up five different uh systems, then you get the full agent OS system inside one dashboard with one shared memory ready to run inside the AI profitab. You also get four weekly coaching calls where you can ask questions, share

your screen, get help and support in real time as well. So inside the AI profitable boredom here, you can get access to our agent OS. This is our community for helping you learn, save time, and grow with AI automation. The great thing about getting the agent west is like some people think you need to be technical to run loops. But if you get our loops and our systems, then you don't need to be technical cuz you

can just give uh this zip file to to Claude or Hermes and it will set out for you. You see when it was last updated, you can get a video tutorial on how it works. You've got a full buildout guide here. And then we've also got new daily guides based on what's actually useful as you can see right here. So, we update it all the time. We also answer community questions daily and I personally answer them.

Plus, there's always people online to help you 24/7. And inside the calendar, you can jump on weekly coaching calls, share your screen, ask questions, meet people in real time. Inside the map, you can meet people in your local area who are building with AI agents like you. And that's all available inside the AR profitable boardroom link in the comments description or just go to the AR prof.com. Thanks for watching. uh for that if it's big and

complicated feel free to DM me inside the air for boarding and I can take a look for you just send me some screenshots and that sort of thing. Do you have a back? Yeah, of course. Yeah, I mean we actually um we we actually have like a agent specifically for doing the agent OS and building out. So if we need to roll back and update, we can. But it's never happened so far. Today we're going to

be answering the latest questions about our agent OS system. How to build agents, how to get the most out of them, what agents I don't use anymore, and how to build amazing systems like you can see right here. here. And this is basically an easy way to automate and build anything with AI and make it 10 times more powerful because all of your best automations are just one click away. If I'm like, right, I need to

automate SEO, boop, there we go. We've got SEO automated, ready to go right there. If we need to build agent loops, no problem. We've got the agent loop system right there. HY3 comes out, no problem. We'll build out a free API system where we can code automatically with 10 cents HY3, preview it, and save everything inside one workspace. And so this is a powerful system that improves every single day. I've even got my to-do list plugged

in right there. We've got paperclipip agent masterminds. We've got group chats with agents, ideas to implementation systems, and everything we need to win with AI. And so what we're going to do today is answer some of the latest questions inside my community, the air profit boarding, because if those questions, you probably have similar questions as well. And so I'm going to help you as much as we can and build out some awesome stuff. Let's take a

look at the latest questions. So, first question we actually got here. This is pretty interesting. So, MJ Jordan was saying, you know, which agent did you stop using and why? So, there's one agent that stands out to me for this answer. And maybe some other people can relate, but for me personally, it was Open Claw. I just found like as soon as Hermes got good enough to basically automate all the same things, it was like a

smoother, better version of Open Claw that I could build better stuff out. So for me personally, I rarely use Hermes. And actually, if you go to the settings inside your workspace, you can hide inside our agent OS, you can hide anything that you don't use. So if I don't use open claw anymore, I can just hide it here. And I can come back to it later if they release a good update. But right now, probably don't

need it. I think as well when you're using agents or using systems, the simplest solution is the best. Like you don't need all this functionality. You just need the systems that matter for you most. So like for most people even just having the chat system here would make a huge difference to them cuz they can navigate across different agent profiles. They can use claude in the background. They can have a pipeline with ideas and implementation. And

so I think that's a really cool way to use AI. Next up, big announcement. So, Fable 5 has been extended for all paid plans through July the 12th, which is great news. You can use up to 50% of your weekly usage limit on Claude Fable 5. So, if you're not using Fable 5 or if you haven't had time to check it out, definitely do that. This is really good news that it's back. We've been building out

a lot of cool stuff with Fable 5 into the Agent OS system. And you can see, for example, we've been building out like all sorts of interesting stuff like we were setting up some Asian loops this morning. We're using uh codeex with 10 cent hy as well to test it out. And so yeah, Claude can build some awesome stuff, especially with Fable 5. Stephen was asking about how to produce content with AI. So, we've actually got

really good workflow here. This is one of my favorite workflows that we still use today. Pretty powerful. We also got a new system here, too, that uses the same sort of method. Um, and we also have our Twitter automation here as well. But if you're wondering like does, you know, AI content perform well, do people like it, can it get a lot of reach, etc. You can see, for example, even yesterday with our systems inside the

puff of warding, we reach 650,000 people in one day, right? And that's just on one platform. So, it can reach a lot of people and it's really powerful if you have the right systems in place, which is something I've been fine-tuning for years now. And we just hit 4,000 members inside the profit bum as well. So David, thank you very much for celebrating. never imagined we'd grow this big, but I think that's a big testament to

the community and how many great people we have inside there. You can also see here, so Andrea actually created their own agent OS system as well based on us. So you can get some amazing stuff and you can see an example of this right here how it works. Um the great thing about these sort of systems is if you have a community where you're sharing you're learning you're growing you posting and sharing all the stuff you're

working on it it can be literally life-changing. So the reason our agent OS is so good is cuz we've got a community of people who are like we need to improve this, we need to add that, we need to change this, we need to remove that, right? And so so many people are building this, giving us feedback, and then helping us improve it. And this is why I personally answer the questions every single day cuz it's

just like the best way to build a great community where we all win together and we build something amazing. I mean, for example, Sheena, they actually turned their agent OS into a powerful system that just self-improves for lead generation. There's so many cool use cases for this. So, it's great to see these sort of shares and and people building amazing stuff. Now, Elsa was asking, you know, what's the best way and the best use cases for

using Fable 5 and then also reducing the amount of tokens that you use as well. So for us, we are using it to build new features into the agent OS. So for example, like the system with Hermes and Asteros wouldn't have been possible without the Fable 5 update cuz it's just like so powerful but so neatly organized and great UI and everything else. So just adding new features inside the Agent OS is my big focus with

Fable 5. And then for anyone who's watching this, you know, I'd recommend that you write down everything that you're working on. Spend just 10 minutes on it. Write down in three to four steps what the workflow is and then ask Fable 5 to automate it or to build a tool that automates it for you. So for example, you could build that into the agent OS. We did that with keyword research and with SEO content creation. And

then for reducing the amount of tokens that you use, I would recommend three things. So there's three open- source projects that are free and also reduce the amount of tokens that Fable will use. So they are caveman, headroom, and ponytail. Ponytail is great for coding. Headroom compresses the amount of tokens you use. And then headroom also compresses that. Uh, caveman also reduces the amount of output tokens because it basically just responds like a caveman. So, it's

very blunt and straight to the point. Also, a lot of cool people like share awesome stuff like you can see right here like free tools and free AI tools and this is something that I share inside the community too. Like for example, if you haven't checked out already, 10 cent HY3 is available for free on the API via open router and you can get that for 2 weeks. Definitely worth checking out. This is a good question.

So Moit was asking, you know, Hermes is changing the way he thinks about agents. What are what's like one feature or workflow or use case that's completely changed how you use it? And for me personally, it's Hermes Astros because it gives me content ideas like instantly and it makes it very easy to automate something that used to take hours. So ideation for content creation can take hours especially to find like really good topics, really good angles.

With this full system, we just monitor and find um trending keywords. We can change what keywords we want to focus on. So for example, if we click on the watch list here, we can change which competitors and which keywords we monitor. And then also when we're doing this, we actually get unique content angles and ideas that we can create content around. That's literally life-changing itself. Saves literally hours. But the other cool thing here is that we

can just plug that into our video agent into notebook or into our SEO content pipeline to quickly create and automate that content as well. So not only does it come up with the ideas, but it also helps us create the content too, which is amazing. So, they are all the questions we've answered today. Every single question has been answered from the community. If you have any questions and you want me to answer them like this, feel

free to post them inside the community of VR profit boardroom. I personally answer them every single day. And also, there's always people online. I mean, there's 4,000 members inside there. So, there's always people online to help you and support you whenever you need to. And today we've covered the best workflows, what to use with Fable 5, the fact that Fable 5 has been extended, which agents to stop using, and some of my best custom automations. So

if you want to get my full agent OS system, I mean you could set it up yourself, but if you want to get my full system, it's right here inside the classroom of the air profitable boardroom. So go to new daily updates and then you can get the video tutorial. You can get the last update date. You can get the zip file to install it and then we add new daily tutorials as you can see right

here to help you as much as we can. Inside the calendar, you can jump on weekly coaching calls, get help and support in real time, meet people um on live calls who are building with agent operating systems too. And then inside the map, you can meet people locally near you who are building with AI agents. So feel free to get that link in the comments description or just go to the arpufferform.com. Thanks for watching. So, this

is a brand new free SEO O agent OS as you can see right here where you can basically control a team of agents working in an office. There's actually like 28 different agents as you can see. You can ask them to do different tasks and you can enable them whenever you want to as well. So you can do like a full audit with your agency. Now when you actually set up this open source project the other

cool thing is it will actually ask you which website you want to focus on and then you can see all of your agents inside one place which is pretty cool. The UI is a little bit hard to navigate, but you can see an example right here. And then if we want to, for example, do any of these tasks, we can ask it or we can type what we want inside here. So, for example, we can run

the beast plan planner or we can do the keyword TRL map or we can do the review readiness gaps as well. So these are all the genetic workflows that we can run as you can see and also we can over here say like okay build the brain and what it's actually going to do if we zoom out here is build out a second brain for our SEO team which is pretty cool in itself. So you can

see the brain of knowledge here and these are basically all these different workflows and playbooks and any information about you and your website that it can use to generate these outputs which is pretty cool. Then if we go on the right hand side here, we've got a full wiki of all these different tasks and agents that we can monitor and get to do stuff and we can actually change the setup over here. So we can switch

between whether we want to for example use our LM provider. We've plugged in cloud CLI so we don't need to pay anything extra for it. We can also plug in our data for SEO key and we have Google cloud, Google AI studio and nothing else. Now what we can also do is add multiple clients. So, we can manage multiple different clients with this system. So, if you're an agency and you're like, I need a really good

agent OS, this might be a good free alternative. Now, at this point, you might be going, okay, what is SEO office? So, this is a free open-source project from Agree Daniel looks really cool. Basically, it has all these different skills and different setups here. So, you can get a 3D office with your SEO agency. You can walk into the 3D office, click a desk, and then just get work done. You got 25 different AI specialists to

run audits, research reports, and everything else, which really, really powerful. It can run on Mac, Linux, or Windows as well. And then it's just like one click install here. So, you can just set it up and get it installed. The only thing you need to configure from there is the data for SEO API key. And if you're not sure how to do that, you just go to data for SEO API dashboard. That's basically how to do

it. So I've plugged it into our agent OS here. So like inside our full SEO content pipeline, I can go from like research to open SEO for AI rank tracking. We've got SEO office over here. We can generate content based on the keywords we get back from it and then deploy it to our website as well. So it's an SEO office engine, which is pretty cool. And you can have a 25 specialist SEO agency just running

on your computer. It's really like the first uh SEO agency operating system I've seen where you can walk into a 3D office and everything else. Now, if you're wondering what it actually is, so it's local first. Every client gets a second brain which means for example like we have our memory galaxy inside the agent OS of our own system. But then also inside the SEO office, it has its own memory galaxy here has its own second

brain. Now, this is good for sharing, for example, content guidelines, style guidelines, how to create content, playbooks, etc., skills even. So, each one of these, for example, we've got like playbooks on keywords and everything else. And we can open them up and see these skills themselves. So, these are all different skills and we can review them. We can see what they've got, what they recommend, etc. And it also gives us examples of how it comes up

with that. So, for example, here it breaks down the keyword, the volume, the competitor position, our position, everything else. It's really, really cool. So, it's a great way to just get loads of playbooks, plug it into one system, have a team of specialist agents, you basically got a zero human SEO agency. And if you want to activate any of the other 25 agents, you just click on them and then you can get them to work from

there. Pretty cool. Now, what happens when you run this? So, if you ask the orchestrator to build the brain for a client, the office moves through five phases. So you got the intake diagnostics discovery synthesis, and the plan. So intake basically sets up a client like the manifest keeper records the client's identity, all the key details about the client. Then it's going to start analyzing and auditing the website. From there you have discovery specialist. So if

we have a look at that office again, what you can see is these are all different specialists like we have our keyword specialists over here. And so depending on what phase of the sweep you're on, it will break it down step by step. So we have for example uh different agents that can look at the schema, the site maps. We have discovery specialists that can do the keyword research. We have for example synthesis specialists that turn

the data into strategy, everything we need to win with this stuff. And then the cool thing about this as well is like it's open source. So you can have it running locally. You've got all the agents ready to go. That saves time. you can automate everything and you have all of your client knowledge inside one place as well. I do think it in implementation just to be 100% honest it might be a little bit tricky to

set up but I think you could configure it for like a few hours and then get it ready to go but I like the idea of like visualizing the full office as well that just in itself it's pretty cool. So really interesting system right there you can also look through the setup and the system as well. So if we click on system we can see for example we've got claude and our claude CLI plugged in. We

have data for SEO ready and configured. We can see that we've got my website configured for this as well. So it can like crawl and analyze my website directly here. And you might say like an AI audit can't match a real SEO consultant. I would just use your own knowledge or your team's knowledge in combination with this. Always apply your own common sense when it comes to this sort of stuff. of people say, well, you know,

doesn't this use a lot of tokens or isn't this expensive? But you can use your own CLIs with it and configure your own LLMs with it. So, you don't have to pay anything for an extra. And then also, you might say as well, okay, this is just another SEO tool, but this could actually replace a lot of SEO tools for you. If it's got data for SEO plugged in, which is basically what a lot of other

SEO tools use as the API, then you're basically creating your own tool and replacing all the other tools that you have here. It's like your own DIY version of Samrush or Adrius almost. So you have the office, you have the orchestrator, the brain and the data. The office is the 3D floor here. The orchestrator is a project manager in the middle who you can organize with directly here. The brain is a per client knowledge base and

then the data is for your own SEO tools and keys and that sort of thing. And then to set it up, it's just like one simple terminal command. So you can see to install it, you can get that from the GitHub. You might say, "I'm not technical. Is this going to be difficult?" Again, I would say it's going to take a little bit of time to configure, but everything that's useful does anyway. I think that's as

automated as you can get really when it comes to this stuff. And then you just pick your AI provider, start adding your first client, and you can give it a tab inside your HOS. So that's basically it. Now, if you want to get my full setup with the keyword research tool, we've got Open SEO plugged in there. You can get SEO office from GitHub for free and you can generate content and deploy it inside our system

too. You can get all of that inside the office boardroom and it also works with our memory system here. So link in the comments description if you want to get the AI profit boardroom community with the agent OS system as you can see over here. And then also if you have any questions you can ask questions inside the community. I personally answer them with video tutorials and there's lots of good SEOs inside there. The other good

thing about this is if you want to get a free SEO strategy session, you can get a one-to-one call with us, me and my team of world-class experts. On a free SEO strategy session via goldie agency and on that call, we'll look at your website. We analyze how to get more traffic. We'll give you a free SEO domination plan. You'll discover the secrets SEO link building and you'll learn how to rank your website based on what's

working for us. So, feel free to get that link in the comments description or just go to goldie. agency and if you want our agent OS setup you can get that inside there of war. Cheers. Today I'm going to show you a powerful system we've used to basically set up a video editor inside the agent OS and you can see it actually create like full videos put them together edit them beautifully and you can see like

the before and after as well it's pretty powerful to set up so here's an example as well I'll show you more examples in a minute in terms of how it works this is based on a new open-source skill that we've set up and it's pretty easy to do so what you can do here is you can add the video that you want to edit and then the AI agent can do that for you and you just

give it the prompt here and then it works directly. So how does this work? Well, basically we created a custom workflow here where we got this GitHub. So it's an free open source project as you can see. Comes with lots of cool video skills. You can teach that to Hermes or to Claude or whatever you prefer to use. And then we plugged it into our agent OS system. And it's a really powerful system that basically replaces

a team of video editors. So before you would have a team that creates a video, puts it together, everything else. This whole system now automates that fully for you. And we've created basically what you can see here is a full kind of SAS tool for video editing, which is really cool. So it's a video agent. And essentially you can save everything that you've created on the left hand side. You can give it a prompt over here

and then you can see the output over here which is really cool. So how does it work step by step? Well essentially what you do is you just prompt it and the agent follows your instructions kind of like the same way you would use chat GBT but instead of like for example creating a blog post or something like that you're creating a video. Now, the thing to note about AI videos normally is like if you generate

them, they still need a lot of editing. So, for example, if we look at this system here, as you can see, these videos are great, but there's no real editing on them, right? And that's with this tool here. But if you use the video agent that we've plugged in here and we've used it with Hermes agent, it can easily start editing our videos with one single prompt. So it takes everything you've got, runs it through the

video editor, and then you get the final output. And you can literally install this in like 5 minutes. So if you want to get the open source project, it's available here as you can see. And it's literally like one easy setup to install it. So you can copy and paste that into claw.codeex or Hermes or OpenClaw. And then once you've done that, you're good to go. So, here's an example. The way to get the most out

of it is like give it a really strong brief. So, here's a really bad brief versus a good one to get the most out of this. And then it can actually tighten up the existing video that's created. So if you create a video with this, you can actually make it way more interesting and remove any of the fluff as well. You can also create like nice highlight videos. and improve the sound as well of whatever you

create. Now, one thing to note here is that it can take a while. So, the way you would use this is you would go into the video editor and give it a task, but then I would just leave that tab open and come back to it later cuz like for actually putting it together, it's going to have a skill that it runs and a workflow that it runs and so you just want to leave it running

in the background and then come back to it later. Also, you can plug in 11 Labs directly into it. But yeah, it's really cool. It's like having your own human editor ready 24/7 that can create awesome stuff. So this was fully created with AI too, which is pretty amazing. So this is like a AI avatar video that's put together. And then it can even create for example this bit too. So pretty powerful stuff. Now also what

I like about having it inside this system is that we can use the video team here but then we also have a video agent over here. So with this system if you want to create like a full avatar video with B-roll, the AI avatar, the voice over and everything else. We can do that with one prompt and it even researches creates a voice over and everything else. So between these two systems, this one and this one,

you've got a really powerful system that can put everything together for you. And also it saves automatically to your workspace, right? So everything that you've created with these video agents, you can come back to later. And the thing that I found quite often is like if you're creating a lot of videos like this, sometimes you lose the files, it's difficult to organize, etc. This system just plugs it all together. And also the other great thing about

this is it's plugged into our memory and context system. So it can use that to personalize the video and the outputs and everything else. So if you want to get our full setup with the video agent, you can get that inside the AR profitable room link in the comments description or just go to the AI profile.com inside the community. You can ask questions, get help and support in real time. I personally answer the questions inside there

every day inside the classroom. If you want to learn more about video agents and how to use AI avatars, you can get lots of training inside the classroom here. If you want the agent OS, you can get the full setup with the latest update and the zip file to install over here. And then we add new daily guides as you can see. Now inside the calendar, you can jump a week with coaching calls, get help and

support real time. Inside the map, you can meet people in your local area who are building with AI agents like you. And this is all available inside the air puff boarding link in the comments description or just go to the airpuff.com. Thanks for watching. Rash says hello sir. Hello Today I'm going to show you a new way to use codeex for free using a combination of codeex and then also we've got 10 cent hy that only

just dropped about 24 hours ago. So this is a brand new model from China. It's open source and it's available for free on the API. Also the other thing I would say here is that this API is only available for two weeks. You might as well make the most out of it today which is what I'm showing you. So essentially we've plugged in HY3 from Tencent into codeex. You can get a free API from open router

and then you can easily get that API and build whatever you want for it. Right now we've created this custom version where we can use it with goal mode. We can see everything that we've created. We can check out the workspace. So if I show you an example of this, if we go to the workspace over here and then we see what we've created, we can see everything that we've built and we can preview everything that

we've created previously using this powerful system. And the great thing about this is the HY3 is actually pretty decent when it comes to coding. It's not like Fable 5 level, but is a free API and also the next time something else comes out that's free, you could just swap the APIs and change them around. So the way that you can do this is you get your API key from open router as you can see here. And

then if you've already got codeex installed locally, you can just ask uh codeex listen use tensen hy give it the documentation from this page for openi give it access to your API key and then say give me a version where I can use hy for free with codeex. That's basically what we did. We actually did it with um claw desktop instead cuz we wanted to build it into our agent OS and it was really simple and

easy. Literally all I said was can you set up HY3 free with codeex see the free API on open router put it inside the agent OS. It took the information here as you can see found the free API which was pretty nice. installed codec, tested it out. It actually didn't work first time round. So, I just quality controlled it, but then second time around, ready to go, right? And it's actually working. We can see the preview

here. We can see everything we've created, and we can come back and chat with it whenever we want. Pretty amazing stuff. We also, for example, created a free coder with HY3 here, too. So, it's kind of similar to codeex, but it just runs directly with H Y3. No codeex involved. And then we can prompt it over here. We get the preview over here. We can save build start to our workspace. We see all the conversation history

as well. And the great thing as well is like it integrates directly into our workspace. So let's say for example you're using claude, you run out of tokens. You're like what should I do? Should I stop building? It's like no no no no just take the same project and plug it into HY3 coder or plug it into codeex instead so that you don't stop. And that's the great thing about this. Also what I would say here

is that if you look at the system it it really runs down to like two parts. So you got codeex as a hands right? So openai is coding agent. You give it a task. It writes the files, runs the commands and reports back and the agent itself is free to install and then you've got HY3 which is a brain. So 10 cents do 295 billion mixture of experts model built for exactly this. It's designed for agentic

coding and reliable tool calling. So on open router the 10 cent/hy3 free version cost nothing to use and you can use it until I think it's July the 21st. So it gives you about two weeks to test it out. And then all you do is you swap it inside the config file. Now you could do that manually. For me, I don't personally like to do that myself just because I'm non-technical and I can easily just give

it to Claude and then literally in in two rounds we have it ready to go and implemented. The other great thing about HY3 from Tencent is that you can actually go to Hermes here and you can have a free installation, a free agent profile with Hermes too. And that way you can use it for free in two ways. You use it as a agent profile inside Hermes and also inside codeex and then you can save and

build everything you want. I haven't tested out with goal mode as well, but that would be pretty interesting to use. And also if you run out of tokens or if you get rate limited on HY3, you can also use another free API that plugs directly into it called Omniroot. Now Omniroot is another free API that actually runs through like 93 providers, but either way you can use Codeex for free. We've also plugged it into Claude code.

So we've used omniroot with clawed code and that way we can use the agent harness in the power of codeex and free clawed code but with free APIs and that sort of thing which is pretty cool. So pretty powerful stuff if you're wondering what's going on in the background. So literally you give it a task the profile loads with HY3 it runs through open router and the free API HY3 acts and then you get the projects

back in your workspace. So if we go inside here for example and we give it a task and we can actually switch between omniroot and hy3 in the drop down and we can switch between auto approve ask or yolo mode and so if we ask it a task here like okay just build out a snake game classic sort of task it will start working directly here as well and also we can have that tab running in

the background whilst we go off and do something else. So, it's basically like one of the world's most powerful agentic harnesses with a free brain plugged inside and we actually test it out for like being on a landing page. It looks pretty nice. Again, it's not going to be Fable 5 level, but it looks pretty nice and it was easy to set up as well. If you're wondering how does HY3 perform, by the way, we've got

the output back there. So, this is HY3 and it's pretty strong on a gentic capabilities. Now, if you look at the comparisons here, it's not too far off Opus 4.8. Obviously it's not at the same level but the difference is the opus 4.8 you have to pay for whereas for example HY3 you get it for free right and that's quite a big benefit also HY3 is open it's an open source model whereas for example chat GPT

is closed Now again if you get rate limited on HYI3 no problem you can switch to omniroot as well so you can switch between them and this way as well if you're using a a gentic operating system like we are then you use less tokens or you can just delegate like the bigger tasks to smaller models that are free and that way you don't have to worry about tokens and you can minimize the amount that you

use as You can also, for example, plug into codeex open source projects like headroom, caveman, and ponytail. They're all ways to reduce the amount of tokens that codeex uses. So you can code code code for more with free models. And so if you look at the old ways, like you know, every task was metered. Uh Codeex runs usually on paid models only. You kind of have to ration what you do because you don't want to run

out of tokens. Free models particularly usually run out on the loop and testing a new model means adding new keys and everything else. Right? With this new setup, you have one profile. You can switch between these two free models. And anytime you get rate limited, you can switch between them. Plus, everything you create, you can preview inside the chat. And also you have the workspace for everything you've created over here. Also you might say okay well

what happens when HY3 runs out? Well then you could use omni route or there'll be another free API by that point. If you've seen anything this year you know for example like our alpha was another free API this year. So every single month there seems to be something new that's a free API you can test. So if you want to get my full set up with the agent OS we got free claw code plugged in there.

We also have local models. We have omniroot, hy3 coder, etc. and codeex. So you can use these models for free. You can get that inside the air puffer broom link in the comments description or go to the airpuff.com. We also have a memory system plugged in here and loads of cool custom workflows for Hermes so that you can use for example the Hermes Oracle or Hermes Astros or the Hermes outreach tool as you can see right

here. So that's all available inside the air profile bomb community link in the comments description or go to the air profile.com. Inside the community, you can ask questions and I personally answer them with video tutorials every single day. Inside the classroom, you can get access to all of my best training. So, if you're a complete beginner, you can go from beginner to expert over here. And if you want our new daily updates, you can get them

over here as you can see with new daily tutorials and our full agent OS system. We also update the agent OS daily and you can get the zip file to install over there. Inside the calendar, you can jump a week of coaching calls, get help and support in real time. inside the map. You can meet people in your local area who are building with AI agents like you. And that's all available inside the airport for boarding

link in the comments description or go to the airport for bomb look. Thanks for watching. Bye-bye. All right, that is it from me peeps. Thanks everyone who joined today. I will see you on the next one. Cheers for watching. Bye.