Testing Fable 5, Hermes Update, and AI SEO Strategies

Fable 5. >> He's back in the house, my friends. We're going to be testing out today, seeing how it performs. And uh get into this. Going to have to restart Claude, I think. There we go. >> Also got a new update from Hermes today. V 0.18. So, we're just going to get straight into this. It's all of my life. I' was just I'm soh. Brad says, "Yo, this live is insane. Always, mate. Always. Elias says, "What

are you building. So, right now we are building out some tests with Fable 5. We're going to be running through the latest update on Hermes as well. I'm actually just going to update Hermes now to the latest version v 0.18 came out. We're going to be talking about how to use Fable 5 AI SEO as well. running through clawed agent operating systems and also comparing Fable 5 versus Mixer agents versus Fusion as well. So, running through

those Lego Fast says, "Julian, did you hear that Fable 5 debugging uh doesn't work so well?" Yeah, I heard about that. I think I saw uh as well that it just redirects sometimes to Opus, which is kind of annoying. So, we'll see how it does. We'll see how it does today. Also, it's not cheap at all. I think the token limit goes pretty quickly. Ran, what's it saying so far? All good. Randall, what's up, Julian? Good

to see you, Randall. Thanks for joining. >> All right, let's get this updated. All night long. Oh my. Hey. Hey. Hey. Make sure you add the creations inside the Fable 5 part of the claude workspace as well. I love you. Heat. Heat. Hallelujah. Hallelujah. Let's go. Just testing out now. Back in a sec. I love you. Hey. It's not looking good here. We got model overloaded. Nine tries out of 10 so far. This is not so

good. What we might do is just start a new chat with uh Fable 5. And we got service busy from Opus here. I think we'll have to stop that. Look at this. Even uh Opus doesn't work properly. Says model overloaded. This one too. Seems like only Fable 5 is working. Actually, Opus 4.8 doesn't seem to work. Hey. Hey. Hey. Oh love. the Heat. Heat. N. I love you. Heat. Heat. N. Falling around. Hey hey hey. Heat.

Heat. Hey hey hey. Today we're going to be answering the latest questions on our agent operating system. How to build them, what to use, how to set up Hermes, etc. And I'm going to run you through step by step everything that we've learned so far based on the questions from the community today. So you can see this is an agent operating system where we have like our memory plugged in. We have all our agents working together.

We can add new features. For example, like notebook just dropped short videos yesterday. We've already plugged that into the system. We have all sorts of cool stuff here. Even a music agent and a video agent and everything else plugged into this system. So, we're going to get straight into some of the latest questions we've had and see what we've got here so far. So, one of the first ones we got actually was uh what are people

using Fable 5 for? So, one of the first things I'd say here is like Fable 5 pretty limited. I saw like some people posting that they used about two prompts and then it ran out of credits. So, I think the token usage on it is pretty limited depending on what plan you're on. So far, what we're actually doing is running the goldie bench tests for Fable 5. So, that'll be interesting to see what comes out in

a second. And we'll be updating our leaderboard based on where it gets placed. It'll be interesting to see whether it actually outperforms Fusion, a mixture of Asians from Hermes as well, and also how it performs if you combine it with other models too, if you get even better outputs. So going to be testing out today. The other thing that I've noticed is that we kept getting bugs with Claude today. It kept saying service was busy every

time even when we tried to use Opus 4.8. So that's something to be aware of too. It's like it might be limited, very limited at first. And also it's only available until July the 7th on the existing subscription. The other final thing that I saw is that people are getting gated. So what happens essentially is they try and use Fable 5 and then it redirects to Opus uh 4.8 pretty quickly as well. So hopefully that doesn't

last too long, but it seems to be a bit of an issue. But if you're wondering what you can build with it, you can see like we're building out some some games with this and that sort of thing. Um, we'll be testing out more and more. We got Fable 5 showcase here of some example stuff that we built with it. Usually it looks pretty nice, so we'll see how it performs. It's definitely the most intelligent singular

model, but I'm interested to see will it outperform panels of models, too. We got another one here which is from James Lee and James was asking like how can you link two uh separate clawed accounts to an agent operating system. So I've never tested that. I've never tested that to be honest. But what you could try is you could run one version of claw code inside your terminal and then one version inside claw desktop with separate

accounts and try it that way. Or you could have one on a VPS and then one on a separate instance. So two different options. Got a question here from Ilkin who was saying that basically they want to run openclaw and they also want to run Hermes inside the agent operating system but their MacBook is like 5 years old and not able to hand handle them locally. So in that situation, if your laptop setup is not good

enough, you got a few options. So number one is you could set up a VPS and then link them together. Another option is that you could get a Raspberry Pi. Kevin actually mentioned this too. It's like you got two options there. So VPS or Raspberry Pi or you could use tail scale from separate devices as well. For me personally, I run them all locally, but it really depends on your setup. Honestly, what I'd say as well

is like these agents are pretty lightweight, so I haven't seen any issues where, you know, you might struggle to set up. So far, it's been totally fine. Sam was asking for a Hermes desktop masterclass request. So Hermes desktop is a separate app to the agent operating system. We actually have a master class on that already over here. So have a full video tutorial, step-by-step guide, etc. and a 30-day road map. So, we've got the full guide

already, but for me personally, I don't use Hermes desktop that much because I find the agent operating system is a lot better. But if you do want a full step-by-step guide, all our prompts, uh 30-day plan for implementing it, etc., you can get that all here. But I think if I have a choice, you know, if you're watching this, you're like, do I use Hermes or do I use Hermes desktop or should I use a agent

operating system? I honestly think the best option here is an agent operating system because then you can pull out all the most useful parts and also you can't really customize the Hermes desktop in the same way that you would customize your own agent operating system. This is pretty wild. So, a lot of our members, they use our operating system, but then they customize it as I was mentioning before, like exactly how they want it. So what

you can see here is this is basically a system that Robbie set up where you can basically look through the latest jobs and then there's an approval queue and this basically does outreach for you. And the interesting thing about this is it will analyze, categorize, and triage the job opportunities, look through the latest postings and then forward them into an agent operating system dashboard. You can see right here looks really really cool. It's got like custom

message. It's basically a system that he can actually sell as an agency too and it can work completely offline. Pretty amazing. Plus love the local setup too. got another question about setting up uh agent operating system on Windows. So Ronald was saying you know I plan to use Hermes for my main agent in the agent OS. Should he set up Claude CLI or Claude desktop? And secondly, should he set up Hermes CLI or desktop beginning the

setup for Agent OS? For me personally, I prefer to use Claude to help me set it up simply because it's a lot smoother and it's a lot easier to navigate when you're setting up the Agent OS. So, if you had a choice between the two, I would go with Claude, but Hermes can do a decent job, too. It also depends what API you plug into Hermes, because some APIs are going to be better at setting it

up than others. We got another question here from Dan B. He was asking about our alpha. Now our alpha was a free API that was available on open router previously but now it's been taken down and you can see the details right here. So this was like one of the most popular free APIs on open router previously. So our alpha was actually revealed as longcat by matrien. We've already done a video on it and it's a

Chinese API actually. So if you're looking for free APIs, there's a few options. Number one, you could just type in free on open router and you'll find a bunch of options including gem 4 which is not bad. What you could also do is if you have a for example if you have uh minax or you have a coding plan with kimk7 both of them are pretty cheap you could plug that into your system as well. If

you're already subscribed to Twitter as well, you can use GR build for free with OF2 based on your existing subscription. The final option that you have is using local models. So you could run a local model with these as well depending on your setup. Nvidia also have some free APIs too if you sign up to their platform. They are limited but you get some free options there as well. The second question from Dan is trying to

self-host the agent OS on VPS because his laptop is not good enough. So, we actually have a full VPS tutorial which I'll show you below. I don't personally use a VPS, but if you wanted to, you can see how John did it below. And you can see the details right here. So this is basically uh how John set it up. And you can use a combination of Hostinger with Cloudflare. Michael was asking about how to use

agent OS and cursor. So I've not I'm not really a big fan of cursor. I don't use it so much. But one thing that we did is we used Twitter af with Hermes and then using that system we could plug in the cursor API the fast one. and it's called Composer 2.5 fast. If there's a CLI for cursor though, then you could easily plug that into the agent OS. I think you would just go into claude

or whatever agent you use to set up the agent OS and ask it to use the CLI from cursor. As far as I'm aware, that's what I would try anyway. was asking like which LM or which provider you use in order in order to run open design in agent OS. So I think when we used it we used Miniax M3 because uh Miniax plan is pretty cheap and it's easy to set up but you can use

any model you want as long as it's decent. So Miniax, Kim K2.7, GLM 5.2 these would all be these would all be good options. So, Victor actually set up the agent OS as well and he was asking, you know, like a video series of of all the things that you can do with the agent OS system. So we actually every time we add a new setup inside the agent OS or every time we add a new

feature etc we will plug that into our daily video tutorials so you can run through each step and see the progression of it as well. And also inside the zip file for the setup we have markdown files on each process. So for example like the voice building paperclip each one has an individual markdown file that you can read through as well. So you get the video tutorials and then you also get the markdown files if you

want to read about it too. All the video tutorials are stored over here. So every time we add something new for example like mixture of agents or for example sakana we plug that into the system and then share it as a video tutorial with a step-by-step guide. Alan also posted that there's a new XMCP so you can connect Grock cursor or any MCP compatible AI tool to the X API. One thing that we actually tried as

well is we got Hermes and we use Grock with Twitter OF inside there. So Gro Oof and then the cool thing about that is you can generate videos. You can use the live Twitter search, you can generate images as well. And then we also plugged it into Hermes Oracle so that every 24 hours it pulls in the latest news from Twitter based on what's just dropped, organized it in terms of which one is the most important.

And I think that's probably a lot easier than using the MCP or an API. But either way, it's still pretty useful because then if you're already subscribed to Twitter, you get the images, you get the videos, you can pull in the latest news, etc. And that's basically it for the latest questions. So if you want to ask me questions like this each day I personally answer every question so does the whole community and then also I

create a video tutorial for you daily like this. You get access to our agent operating system if you want it ready made and ready set up. You could create it yourself but I mean I spend about 3 to four hours a day improving and coding it. So if you want my setup you can get it inside the agent OS system. Here you get a video tutorial the last update date. You can see the zip file to

install it and then we actually add new daily tutorials based on what's actually useful as well. And then inside the calendar you can jump on weekly coaching calls, get help and support in real time, share your screen, meet up for members, etc. And inside the map, you can meet people locally in your area who are building with AI agents like you. So feel free to get that link in the comments description or go to the aprofit.com.

I think this 4.8 is just not working. Let's see how it does. There we go. It's working again now. We got the test from Fable 5 coming out as well. Let's see what questions we got here. Anybody else getting redirected to Opus? That seems to be a common theme. I think this is a good idea. I was thinking the same. It's like you just build the plans for Fable 5 and then you you delegate that to

overs 4.5 uh 4.8. Hagati says, "What's even the point of Fable?" Yeah, I think like it's going to be pretty limited on tokens. It is only available until the 7th of July as well on the subscription. Fable 5 is usable right now. Just reconfirming. Sorry to ask, but what are backlinks and why are they so valuable? Um, oh, they're basically like votes of authority to say that your content is good. So the more backlinks you get

from relevant authoritative sources, the more likely you are to rank on Google. All right, back in a sec. Heat. Heat. I feel me. Hey hey hey. Let's see what else we got here. All right. As a senior software engineer, can you persuade me to get your agent OS? What makes it different? Um, I mean, that's up to you. So, I'm not I'm not going to do like a a pitch or anything like that, but if you

see it and you like what you see, feel free to get it. If you don't like it or you don't like what you see, you know, feel free not to get it. So, it's up to you. I mean, like for me personally, I just I don't really I would just do your research, right? Um I mean, like if you look at all the testimonials, we've got like 194 pages of testimonials and wins and people saying how

amazing it is. I would just look at that and think, okay, is it for you or not for you? And if you don't feel like it's for you, that's okay. What else we got here? Light speed. Not sure what your question is, but feel free to clarify what your question is and then I can answer it. Yeah, 100%. We We just built out a bunch of cool stuff here. It's looking pretty cool. Some of it is

not not as impressive as I would like. Some of it's broken. Let's see how it does. I love you. Heat. Hey. Hey. Hallelujah. Hey hey hey. I feel heat. Falling in love. Uncle says, "What you building?" So, right now we're working on this website as you can see um which basically takes all my case studies and then plugs it into like a beautiful website which uh should be pretty good for SEO. It's another experiment I'm working

on in the background. And uh we're running a bunch of tests for Fable 5 as well on Goldie Bench. which I'll be running through later today as well. Thank you. Yeah. So, we put the agent OS system inside the AI profit boardroom. So, if you want to get the the system that we build daily, you can get that inside the AI profit boardroom community. So, we have a brand new update from Hermes today. Hermes Agent V0.18,

the judgment release, and we're going to run through exactly what it means, how it works, show you examples of how it actually can be used in practice, and some of the systems that we've built around this. So, this is the new update that just dropped a few hours ago. And if you're wondering, okay, what does this mean? So, essentially, we're going to get straight into this. There's a bunch of new updates. The first one that's a

big highlight here is mixture of agents. And this is a model that you can pick. So, this is a new system, right? You see, uh, mixture of agents is is now a first class model you can pick. Bear in mind, like mixture of agents, not really a model. Um, but they describe it as that. It's more like a system. So, let me show you exactly what that means. and how that works in practice. What you can

see over here is that we have the mixture section inside our agent OS. And so mixture of agents is basically a way of getting better quality outputs by combining multiple models together. So for example, here we have Claude Opus 4.8 and GPT 5.5 working together. Now if we give the panel a prompt, what's going to happen is it will fuse the answers of two different models together to create a better output. And the idea here is

like two minds are better than one. So you can see some of the stuff that we've created directly here. So we created like our own OS with this system. We created um like a Minecraft alternative. We have generated all sorts of cool stuff like even games and that sort of thing. And it was pretty good. Like it's it's doing pretty well. I'll also show you on the benchmarks how this performs. So, if we go to Goldie

Bench where I personally show all the tests that I've run and how it performs side by side, you can see here that Hermes mixture of agents is right at the top. We're actually testing out Fable 5 today. But from what I've seen so far from Fable 5, I would say that actually Hermes Mixture of agents outperforms it in many ways. So, you can see Fable 5 down here compared to everything that we've built with Hermes Mixure

of agents. The other thing to note here is that this is basically one shot because you don't go back and forth with Hermes mixture of agents inside a pan uh inside a chat. You would just use it combine all the models. It would take about I don't know 10 or 15 minutes to get an answer back to get something decent and then it's going to go into your workspace. So it's not like for example claw CLI

where you go back and forth because you have to wait so long for these outputs to come back. But once they come back they look super nice. So that is one of the biggest updates and it's really good. It's kind of like an alternative to Fusion from Open Router, but if you're using Hermes anyway, you might as well just stick to using the mixer of agents instead of using theirs. But we've built in Fusion Sakana Fugu,

which is another system for this, and then Hermes mixture of agents directly into our agent operating system. Next up, you can see every model's reasoning and watch the answers come back. Not really too interested in that to be honest with you. I don't think that's so exciting. You've also got a system where it verifies its own work. So this is something called for/goal, but they've improved the forward slashgo system. Now we've got that built into our

agent OS as well. So we have goal mode over here. And what that essentially means is it's kind of like a a loop system. So you don't prompt the agents. You give the Hermes agent a task and then it loops around. A separate judge will judge the quality of the outputs and then it loops round and round until it's fully completed. This is something we also built in with the loop engine over here. And so what

we can do is define our definition of done. We have a builder API over here. We have a judge API over here. We can set how many rounds that iterates for. What that means is if the work from the builder is not good enough because it's been judged by the judge as low quality, it will loop round and round for as many rounds as you allow it. And you set the rounds here and you can decide,

okay, uh, when does this stop and how many times you want this to go around and it's autonomous because it's not running, it's running without you. It doesn't require you to check the work or anything like that. It's just a loop system that goes round and round without you, which is pretty nice. and it saves a lot of time especially on quality control and that sort of thing. Now one thing I will say here is like

if you're just using Hermes inside the terminal it's not going to look like this. So if you're using the terminal here this is why I don't use anymore is like it's just very difficult to see everything you've created it's very diff difficult to segment everything inside Hermes and what I prefer to use personally is an agent operating system where if I want to chat with Hermes with different profiles I got that over here. If I want

to for example use a Hermes Oracle to get the latest news I can do that over here. If you want to use mixer agents, no problem. We've got that here. If we want to do lead generation and outreach, no problem, right? And it's kind of like you create a separate SAS tool or mini app for each part of Hermes. We've got the full setup inside the air prof. But if you wanted to to get the most

out of Hermes, I would say that's much more powerful than just relying on the terminal where you can't really see anything that you've done previously. Next up, we have for/arn. This is pretty cool. So what forward/learn means is basically you can take a guide and you can go into Hermes and say okay learn this system or learn this guide. So let me show you an example of that in practice and I just want to show you

examples of every part of this in practice. You can actually see how it works in reality. So here we said forward/arn and then we gave it the link of the guide and it says inside the chat here learned it and saved it for future sessions. So you can see here that basically it takes the guide that we've fed to Hermes. We type in for/arn and then we get a full breakdown of what it learned and it

saves it as a skill so we can recall that skill in the future. So if you're trying to make Hermes learn something, even if it was like a GitHub repository or something like that, you could type in for/arn inside the chat and then it will go off and learn that particular skill, which is super powerful when you think about it because your Hermes agent basically has the superpower to learn anything in like 5 minutes. This is

interesting as well. So there's something called forward slashjourney, and this is a playable timeline of everything that Hermes has learned about you. And so you can type in forward slash uh journey. It's not something I've actually tested yet, but we can try it right now. So we can type in forward/journey like so. And then that should come back with a full journey of what's happened here. Now, if you want to update, that's one thing I should

mention, too. If you want to update, there's two ways to do it. So, oh, there's three ways actually. You can just go inside the chat and say update to the latest version. You can also go to your dashboard, scroll down, and then go click on update Hermes. So that's option number two. And the other option, of course, is like you can go into your terminal like so and just type in Hermes updates. There's three ways to

update to get the latest version as you can see right here. Pretty simple and easy. There's also something called background fan out. So you can delegate a task and now sub agents will run in the background asynchronously so your chat doesn't get blocked which is pretty useful as well. The other thing that I'd recommend just going back to for/journey, you can also use Obsidian. So, we use Obsidian's update, but that basically has the same system where

you can go back and see a full memory of what you've done. So, if we go to our memory section here, we've got all of our memories plugged into a galaxy that we can visualize. And then if we go to the recent section here, we can see all the recent conversations we've had with Hermes. And it's all plugged into our system so that we can see and look back on everything that's done. And this is another

positive feedback loop because Hermes will update the memory with obsidian that improves the galaxy and then also when we're asking questions of Hermes, it will come back to us inside the chat as well. Now, if you're wondering, okay, how does the delegate tasks feature work? Here's how it works. So, basically, you can say, okay, run the SEO funnel for how to build an AI agent, and you'll have multiple sub agents that work underneath each other, basically

building an out, and it it works automatically. You don't need to type like delegate task. It picks it up automatically as a skill. And then the great thing about that is you can have like a full team of sub agents working on a task. You could if you were doing this for SEO, you could give it one keyword and it would work on five articles at parallel. Deploy them and then you don't need to do anything

from there, right? Uh so there's quite a few use cases for that. So basically, you know, if you have a job that requires a team of agents, this is awesome. So it could be for SEO, it could be for videos, it could be for content, it could be for creating a website, whatever you want to delegate a pile of work to, you can do that right there. What else we got here? I think that's pretty much

it. It is apparently it's a lot cheaper and more efficient. I've noticed that in the updates like it gets faster and faster. But but those are some of the big updates I've seen recently. I'll also show you some of the other things we've done with Hermes. So if we have a look here, and by the way, we've got the full journey here. So it gives us a journey and a breakdown of everything that's done recently. But

yeah, the mixture of agent system is pretty good. And if you want to check everything that we've done with that, you can check it out on Goldiebi Bench. But yeah, it creates some amazing stuff. The the quality of this stuff is actually better than Fable 5 when I test it out. It looks pretty good. Now also we have this proof of work before it's done. Okay. So basically if you've used agents for anything like real, you've

probably hit the situation where the agent says done or fixed and it actually isn't. And there's a big gap between I think I fixed it and the tests actually pass. So with this new update in v 0.18, Hermes now records evidence for coding work and decides it's finished by actually running project checks, not by just claiming it's it's been successful. And so that's one part of this update. And then you have forward/goal, which basically has uh

completion evidence. So you state what's done up front. The standing goal loop keeps judging it work against that evidence instead of stopping when the model is like, "Oh, we've done it." So it's pretty good. So that's basically it. Now if you want every feature that I've discussed broken down into different segments like we've done inside the agent operating system here. We've got Hermes plugged in. We can chat with it. We can talk with it. We've got

a voice powered agent over here. We have Hermes Oracle with the latest news. We can automatically create content, social media, and a website like you can see right here based on the latest trending news. We have a studio where you can generate images, video, and voice with Hermes agent. Everything we've created with Hermes is plugged into our workspace over here. Um, we've even set up an outreach tool so that you can generate leads just by typing

what you want. Then you can send email campaigns with the system too. And you can automatically get the AI to write it for you. Plus, we've got the mixture of agent system over here, which is pretty cool. And then we have the MCP section as well. and goal mode too. And then also you've got the memory plugged into Hermes along with a group chat where you can manage all your agents inside the agent mastermind council and

it's basically one place where you can plug in it. So if you want to get all of these systems you can get it inside the AR profit boardroom link in the comments description or go to the profit.com. You might also say okay this stuff sounds technical but you can see here like so many of our me members we've got 194 pages to win. So many of our members are winning with this stuff and learning and growing

that if they're all winning with it and they're non technical and I'm nontechnical then I think at this point anyone can use AI agents and get the most out of it. So feel free to get our systems inside the profit boarding we have loads of trainings on Hermes agent in particular. So for example if you want to learn more about mixture of agents we've got a tutorial on it here. If you want to learn more about

for/ learn we've got a tutorial here with a full step-by-step guide. If you want to use the email and lead generation agent with Hermes we've got that here. And that's all built into our agent operating system with a video tutorial. You can see the last update date. You can get a zip file to install it. And inside the community, you can ask questions. I personally answer the questions daily with a video tutorial. And then also there's

always people online because there's 3,900 members inside here, which means you can get help and support 24/7. And people are sharing like amazing stuff they're building with their own agent operating systems as well. Inside the classroom, you get access to all of my best trainings. If you're a complete beginner, you can get our section right here uh that takes you from beginner to expert in just 6 weeks. Inside the calendar, you can jump a week of

coaching calls, ask questions, get help and support in real time. Inside the map, you can meet people in your local area who are building with AI agents. And that's all inside the AI profit boardroom link in the comments description or just go to the arrum.com. Uh for me, so a good question here is like for the agent OS, you know, do you use paid or do you use free APIs? I use a combination, but I would

say mostly I would just use like um cheaper CLIs like for example Miniax or GLM 5.2. But one of the questions we kept getting all the time is like how do you use it for free or how do you get free APIs etc. And so that's why I I share that. Nice. Some of us from the boardroom coaching calls are here. Thanks for joining. Let's go. Thanks everyone. I feel Hallelujah. Thank you. It's uh It's our

agent, our music agent inside the uh agent OS. So if you just type what you want and you've connected it and set it up with Suno, then you can create music in like one prompt here and then it'll generate the songs as you can see. So it's pretty cool for generating music. It's better. I mean, it's genuinely better than some like human music that I've seen to be fair. Heat. Heat. So, Fable 5 is back now

and today I'm just going to run through some of the ways that we're using it for AI SEO to rank our websites with Claude Fable 5. And you can see some examples what we're creating here. So this is a website that is on a really nice trajectory here. It's gone from like zero to 275 clicks per day. Here's another website similar trajectory from like zero clicks a day all the way up to 70 clicks per day.

Here's another website and another website all following the same route. Right? Their traffic is growing. They're publishing content. And it's pretty easy and simple to set this up. So, the way that I've done this is basically we use Fable 5 to build the actual tools and the automations, but I wouldn't recommend using Fable 5 for creating the content directly. So, the reason for that is if you're building out a tool, Fable 5 is is really really

good for for building stuff out. I mean, it it can create some amazing things. However, it runs out of tokens very quickly and it's only going to be available on the subscription plan until the 7th of July. So if you're thinking about using Fable 5 for SEO, I would just build the automations whilst you can build the systems now with Fable 5 because it's one of the best coding models, but then use uh Claude or for

example Hermes to actually generate the content. So a lot of what you can see right here was generated with Fable 5 and and Claude itself. And then also we've we've ran some really nice tests on it. It can create some awesome stuff as you can see right here. Um, but the main point to note here is like when you're using it, it's going to run out of tokens quickly or it's just not going to be available

um for a long time. We've also plugged in our memory system into Fable 5 as well so that we can generate better, more unique, more personalized content because it has all of these memories and understanded of me, my goals, what I work on, my businesses, etc. And then it can use that to to build systems that create better content. So, what we've done here is we've built out the agent operating system and then we can pull

in the latest keywords from our Google search console, what we're ranking for, what we could rank for in the future. We've got Open SEO plugged in there as well, which is great for like AI rank tracking and just ranking your content in general. Then you can also plug in a keyword here and take a case study and then deploy that to your websites. Now, when you're doing the system, and I'll show you some examples of what

the content itself looks like when you're actually doing the system. again like use Fable 5 to help you set up and build it cuz it's great for that and great for testing and coding things out and you know taking the ideas from your head and then actually deploying it but I wouldn't use it for for creating the content. So, for example, here, if we go to Fable 5, we're using it inside this system. And you can

see here that it will run out of tokens pretty quickly, I can imagine. Like, this is just the first day we've had it back. And you can only use 50% for your plan on Fable 5 as well. So, it's pretty limited. And then also, the other thing that I heard is like sometimes it redirects to Opus 4.5 when you're using it as well. Now, the other thing that we're using for SEO as well, this is pretty

interesting, is we're creating and benchmarking all of the tests that we do with Fable 5 and then creating a website around it. Now, if you're doing anything related to Fable 5 in your industry, I would document it and put it into a website or get Fable 5 to document and put it in a website for you. So, you can see for example over here, we're using Fable 5 that deploys the tests and the experiments that we

do and all the case studies that I create and then it deploys it to a website where we benchmark everything that we do. And if whatever your industry you're in, if you're doing stuff with Fable 5, like there's a lot of interest right now. A lot of people are excited about this stuff. And so what does that mean for you? Well, it means there's a good opportunity for you to create content around that topic and then

also rank with SEO for it. So if we have a look at this benchmarking website, basically what it will do is it will add all my experiments, plug them into a benchmark website, create the whole thing, design it. I've never logged into this website. It's just fully created with Claude. And then over here it will compare all of the experiments that we've run versus other models. Now let's say for example you had a fitness website and

you were doing a lot of testing with Fable 5 or you could create a website where you showcase all of the things you've done with Claude and Fable 5 and then put it on a website. And also there's a lot of good keywords here where people be searching for example for like Claude Fable versus Opus 4.8. So guess what we do? We create a a page here where it's like Fable 5 versus Opus 4.8. We get

Fable 5 to deploy the content, show head-to-head what we've done. And also the interesting thing about this is it's all unique content to us. It's all addin information gain because these are tests that no one else has done, right? We're the only ones that have tested all this stuff. And so we can showcase side by side what we're working on. It positions us as an expert. It targets the keywords that we want to rank for. And

this works for any industry, you know. Um you could even do like video tutorials about it as well. So it's a really cool system right there. And then the other thing that we're doing is we have a video agent that we got Fable 5 to help us build. And you can see here for example that we've created a full video agent system where it can basically research, write the script, create the content, add my avatar, create

the B-roll, and then put it all together inside one beautiful system. And so we got Fable 5 to design the tool. Again, we don't use Fable 5 for creating the outputs simply because it would run out of tokens quickly. And also like I think if you're going to be using these systems long term like for example Claude we originally plugged in Fable 5 and the CLI into our agent operating system. But the problem with that is

like you're going to run out of tokens really really quickly. So that's why I would recommend use Fable 5 for building but not for implementing because you're limited on tokens. Um unless you're planning to use the API and you just really don't care about tokens at all. The other thing that I would say here is like it's pretty good for planning. So if you were using this for SEO, the other option that you have if you're

finding like you know you're pretty limited in terms of the resources you have is you could use Fable 5 to design the plan of whatever you're going to build and then you get for example Opus 4.8 to build that out step by step for you. So that's another good option as well. And actually there was uh some good research by kilo code where basically what they did is they managed to achieve fable 5 level intelligence on

benchmarks without fable 5 and it all comes down to the plan. If you have a great plan you can get a cheaper or less powerful model to build that. So basically you have the planner which is a genius that plans and decides all the forks in the plan and the choices it would make and then you just get an agent to build it and whether you're using like a cheap agent or for example uh something like

Opus 4.8 you will get very similar outputs because you've got a great plan right cheaper models tend to fail when they are deciding everything for themselves because they make the wrong choices. So it's a pretty good option right there as well. So let's say for example you're building out a website. Well, you could get Fable 5 to plan out all the keywords, the content clusters, how you're going to structure it, the code of the page, the

design of the website as well. But then you get cheaper models, for example, like Miniax or GLM 5.2 or for example even Opus 4.8 to go off and build it for you. And that's another good option when it comes to SEO as well. So I'm going to keep experimenting with it. This is a relatively new website that we built. But it's it's still performing pretty well straight out of the box. All of these websites are doing

pretty well as well. And the system that we're using for this is the agent operate system. It can create SEO content for us. It can deploy etc. Another system that we built with Claude was the Hermes Oracle. And basically what this does is it's Hermes agent with Grock builtin and that runs with Hermes but we built it with Claude. And again, you'll see the theme here, which is Bill Claude, deploy with something cheaper. And so, for

example, if we have a look at this, what we're doing here is we're pulling in the latest news from Twitter. It organized it into a beautiful UI. We can see what's trending right now. And then, if we want to publish SEO content to our website without logging in, we can just click on the publish to WordPress section here. And then you can see all of the pages that were previously created for that particular topic. The final

thing that I was going to say is that we actually have the API from index exceptional plugged into the system. So what it does is it takes index API and it helps you get your content index faster and it's all automatic. You don't have to like manually go into Google search console and index your content which can take absolutely ages if you're creating it across three different websites like so. And you can see the content indexes

pretty quickly as well. So it's a pretty powerful system. When you put it all together, you can get Fable 5 to build it, cheaper models to deploy and implement it, and it's pretty easy and simple to do. Now, if you want to get a free SEO strategy session based on what's working for us, and you want to learn more about this stuff, feel free to book in at goldie. Agency, link in the comments description or go

to goldie. Agency. You can get a free SEO domination plan, discover the secrets, SEO, link building, or answer any questions you have onetoone. You'll learn the best link building strategy for your website, plus how to outrank your competitors with link building and increase your SEO traffic based on what's working for us. And also, if you want to get our agent operating system, plus loads of SEO training, you can get that inside the AI profit boardroom link

in the comments description or just go to the profitab.com. If you go to the classroom here, number one, we have a full set of courses and tutorials inside the AI SEO automation section. And then also over here, we have the full agent operating system with a video tutorial. the last update date, a zip file we update it daily with new guides, and then you can get loads of cool stuff right there. And that's basically how we've

implemented all of these SEO tools and how you can do the same. Thanks for watching. Heat. Hey, Heat. Fall. Follow you. Hey. Hey. Hey. Heat. Heat. N. Hallelujah. Hallelujah. I feel Hey. Hey. Hey. Falling in love. Heat. Heat. Come on. Follow. Let's see what questions we got here. It just says, "Tell us about a problem." Um, well, it's only been out for like I mean, literally, I've just woken up and got access today, so I wouldn't

say we've had any situations like that yet. Uh, how did you get Fable 5 to make your Agent OS work better? I just talked through that about 10 minutes ago. If you want to check that out, um, you can just rewind. But yeah, I talked through all the systems we use for AI SEO. Yeah, but even then it was only out for 3 days, right? It was before it was only out for 3 days and then

also token limits were here pretty quickly as well. Heat. Heat. So, Hermes Mixture of agents versus Open Rooters Fusion versus Anthropic Fable 5. Who wins? So, today we're going to be testing them out. We're actually test them out side by side. If you're wondering, okay, what's the difference between them? I'll show you that in a second. We've already marked them on fable sorry goldie. So, Fable 5 versus Hermes Mixture of Agents versus Open Rooters Fusion. Who

wins? Today, we've tested them out. I'm going to show you the results in a second. This is something we actually built with Fable 5 a few minutes ago. So, let's get straight into this. We've compared them side by side and I'll show you exactly what the difference is. Now, if you're wondering, okay, what is Hermes mixer of agents? This is a way of combining multiple models together to get better outputs you'd normally get with, for example,

something that's frontier. So, for example, if you wanted to create outputs that are better than Opus 4.8, Okay, you could combine GPT 5.5 and Opus 4.8 and that tends to work better. Uh, and that's something that I've tested personally. It's also on the benchmarks, too. Now, Fusion works in a similar way. So, with Fusion, you basically have multiple agents working together as a panel, as you can see right here. Then, a judge fuses all the answers

and they go into one answer. And of course, Anthropics Fable 5 just came back again. And we've tested it relentlessly with 42 different builds, which I'll break down in a second. and you can see how they perform side by side. So, let's get straight into this One of the first things we did was test out a game side by side. So, let's have a look at this. So this is the example from Hermes mixture of agents.

This is from table five and this is from fusion. Now, out of all the tests, we have a look side by side. I would say that Fable 5 actually created the best output so far, right? Bear in mind the other tests with Fusion and Hermes mixture of agents were using nonfable 5 models. So, for example, GPT 5.5 with Opus 4.8. And it's created the nicest output as you can see right here. Next up, we have the

Nordic Crypt game. So, this is from Fusion. Super dark. Pretty hard to see what's going on. It kind of works, but doesn't work at the same time. Like, you wouldn't play that game at all. If we have a look at the output from Hermes mixture of agents, quite nice. Works nicely. Little bit hard to control, but it does work well. I also like the moving background as well. Looks quite nice. Um, good vibe to it. Now,

if we have a look at the one from Fable 5, I would say this is the number one the easiest to navigate. Number two, it's got a lot more to it than the other two. Like the other two seem to be a bit more basic. This has more detail as well and it's easier to navigate and move around. So for the crypt game as well, I would say that Fable 5 is winning right here. So the

interesting thing about this is if you look at Hermes of Agents, if you look at uh particularly Fusion, which Fusion claimed to beat Fable 5 on benchmarks, that's not what I'm seeing so far. Uh, but there's many more tests to try out. Then we've got the orbit test from our Agents 2. So this is with Fusion. Not bad at all. It's a in a solar system orbit. So it's like a diagram of of the planets and

everything else. You can change the speed and the controls over here. Then we've got the version from Hermes Mixture of Agents. And you can also drag and move items into the galaxy as well, which is pretty nice. You can change the speed over here. The controls are good. You can reset it. You can pause it as well. Some good controls on that. Now, if we have a look at Fable 5's output, I would say this is

the most basic. So, it's not always the case that Fable 5 wins on every single test. As you can see on this one, it didn't do so well. I would say Hermes mixture of agents won that So, we have three tests in. Fable 5 has won two of them. Hermes has won one of them. Fusion hasn't won any yet. Next up, we have the landing page test. So, this is with Fable 5. And this is actually

something I've noticed with Fable 5 is like it kind of struggles with UI. So, if you look at this particular output, it doesn't look so nice. It's a little bit messy. The background is moving, but kind of feels weird. Everything's just a bit off in this particular example. Now, if we have a look at Nova, this is the output from Fusion. It's definitely beating Fable 5. So, it definitely outperforms Fable 5 on landing page creation for

this particular test. Now, if we have a look at Hermes Mixture of agents, I would say this is by far the nicest output that we got. So, you see how it's glowing? When I move the mouse, the background is moving, but it still looks quite nice. We can click it and it's got these cool animations as well. And by far, that is the website that I would prefer to use out of all of them. It's still

a little bit messy at the bottom. Like, this is not properly aligned. So, all three of them were not like the best in the world at creating websites, but if I had a choice, I would go with Hermes Mystery of Agents. Now, at this point, you might be thinking, okay, why is Hermes Mix of Agents holding its own against Fable 5 when Hermes is using older models and Fable 5 is a newer Frontier model? Well, I

think this is because every single draft gets a second opinion. You know, when you've got a panel of minds and they're working together, basically, you got one judge that fuses the answers and quality controls it all. Then you've got a chair that works together and basically looks at, okay, what's the best of each? Let's take the best idea. Let's take the best options from each piece of code and then plug them all together. And also when

you've got a panel, so when you have that judge that's looking at the other agents work and the other models work, basically it's rooted by evidence, right? So it will kind of like critique the outputs of the other agents to get better outputs. But let's keep going and see where they perform on anything else. So another one that we created was Dragon Realm. So, this is the version from Fusion. Pretty nice. Looks good. The dragon's a

little bit off in terms of the graphics, but overall it looks really nice. Even like for example the snow that's falling like looks pretty good when you're navigating around. I will say it's a little bit difficult to navigate around. It's like not that smooth but it's pretty good overall. Then if we have a look this is Hermes mixture of agents which is pretty good. very similar to the other one, but I would say slightly better from

Hermes Mixture of Agents just cuz it feels more open, it's easier to navigate. Um, but they're pretty much on par. Then let's have a look at Fable 5. So, this is the output from Fable 5. And again, very similar. The only difference I would say between them is that this has a nicer intro. where it just moves around without you. But overall, I would say that's a draw between all of them. All very similar. Next up,

we have a test with a web OS. So, this is an operating system we created where basically you have all of your applications plugged into one system. So, this is the one from Fable 5. This is from Hermes and this is from Fusion. So, let's try this out. We got a notes app here. Let's test out typing something in, closing it, and then seeing if it auto saves. So, you can see it doesn't save on the

Fusion version. So, it kind of looks nice on the outside, but then when you actually test it, it's not saving anything, right? Um, we actually can't click the file to save section here as well. So, it's not autosaving. If we try and close that, it doesn't seem to be that responsive. The paint section seems to work well. Terminal works okay. And we got the calculator as well, but we can't really use the equals button. like pretty

hard to navigate like you can't just scroll down if that makes sense. So, not bad but not great. Then we've got the version from Hermes mixture of agents now too. This looks pretty good. Let's just test the notes and see if this actually saves. So, it's it's being a little bit buggy. You can see the notes application is moving around the screen, but I'm not asking it to move. Paint seems to work okay. The background is

super nice. I think the UI is actually nicer for Hermes Mixer of agents, but it's not very responsive. It seems very buggy, right? So, if we click on this, for example, or if we try and move the notes, we actually can't. It's kind of broken. Let's have a look at Fable 5 now. The Fable 5 seems to work pretty nicely. Let's have a look at the paint section here. Yeah, it looks good. Let's have a look

at the terminal. Can we move that around properly? Yes, we can. Yeah, all of it is working. It's not buggy at all. So, I'd say in terms of that test, Hermes Mixture of Agents came in last. Fusion came in second, but Fable 5 is by far the best. So if we look at the results so far, we have Fable 5 winning on three different tests, Hermes winning on two tests, and Fusion is not winning on any.

Now we're going to try something called Vauil Craft. So this is a version from Hermes Mixture of Agents and is super buggy. I'm actually going to close that cuz I literally can't navigate and it keeps refreshing. It's crazy. We've got the version from Fusion here. This actually looks really good. That is working perfectly. Um, it's a little bit buggy when you can like fly through the floor and stuff, which is weird, but overall pretty good. Then

if we have a look at this version, this is from Fable 5. I would say it's not quite as good as Fusion. So Fusion won that round for sure. And then we have like a a kind of vibe coded version of kind of like Skyrim style called Frost Fell. And you can see this is the output from Fusion. Looking pretty good. Slightly buggy when you move around, but it feels fairly smooth. big, vast, open world. Looks

really cool. So that's from Fusion. If we have a look, this is the one from Mixture of Agents. I would say this one actually feels a lot nicer, a lot smoother when you move around. It's not buggy. Looks pretty cool. And then this is the version from Fable 5, which is just a slightly bit buggy when you move around, but overall pretty good. Um, I wouldn't say it's as interesting on the landscape, but I would say

they all pretty much tie in terms of Let's try and go in the water here. So, that is a tie. and then we created a vibe coded version of Doom here. So, this is from Fusion. Pretty cool game. Fun to play, easy to use. Feels a little bit like a, you know, an old school Mega Drive game, something like that. overall works. Is a little bit buggy when things move around, but overall good. This is the

version from uh Mixture of Agents from Hermes, which is quite fun to play, easy to use as well. And now we have the version from table five. But the problem here is we can't actually move forward. It won't allow me to move forward. So overall, I would say mixture of agents or fusion one there. I'm going to put mixture of agents. But from what I'm seeing so far, Fable 5 won three rounds. The Crypt Razer game

uh sorry Racer Game and WebOS of Agents won three as well. Fusion came in last. So I mean Fable 5 and Mixture of Agents seem to be the best. I would be very interested to test out Mixer of agents with Fable 5. I think that could be absolutely insane. And the other thing I would say here is that if you're on the subscription plan with Claude, you're probably going to run out of tokens with Fable 5

pretty quickly. So I think that as a good backup, if you need like really good outputs, then using Hermes Mixer of agents as a backup when you run out of tokens on Fable 5 could be a really good option right there. So that's the way that I would do is like I would use Fable 5 as a default. It's easier to go back and forth with Fable 5. You can use the CL CLI. It's easy to

use. you've got everything installed inside the workspace in your agent OS. But then if you're using Hermes mixture of agents for those, you know, 10 or 15 minute prompts where you can walk away and come back later and store everything inside the workspace, I think that's a good backup option. And bear in mind as well, the Fable 5 is only available on the subscription for until July the 7th. So, you know, at that point, you might

switch to something like this. And I know that Hermes are working on Hermes Bench as well, which will be pretty interesting to see. Okay, what do they get back and what can they achieve with cheaper models and which models perform the best depending on the setup. So, thanks for watching. That's basically our system. If you want to get all of this plugged into one system, we have Hermes agent, Hermes mixture of agents over here. We have

Claude plugged in with the CLI. We have all these amazing systems like an SEO agent, a video agent, memory system as well. You can get that all inside the AI profit boardroom link in the comments description or go to the airprofit.com. If you want to compare everything that we've created side by side and see for yourself. Well, number one, I would say like don't listen to to benchmarks. Just test it out yourself. And number two, if

you want to see what I've created, you can check out goldiebench. So, I hope to see you inside this community. Link in the comments description or go to the approp.com. And if you go to the new daily update section here, you can find our full system for the agent OS. You can see the last update date. We've got a video tutorial on it. You can get the zip file for it. And every time something useful comes

out like Mixer of agents, we actually test it and we give you a full guide on how to use it, plus a step-by-step road map. We update this with daily tutorials. Inside the community, you can ask questions and I personally answer them with video tutorials. Plus, there's always people online 24/7, so you can get help and support whenever you need to. Inside the calendar, you can drop coaching calls and then inside the map, you can meet

people in your local area who are building with Hermes and Claude and whatever else right there. So, hope to see you inside there. Cheers for watching. feel. Hey Fire. Fall. I feel Oh, hey. So, I've actually built out 42 different things with Fable 5. Fable 5 just came back a few hours ago, and I'm going to show you exactly what we built, how it performs, uh what I think of it so far, what the feedback has

been like, etc. So, here's an example of a creation we actually made with Fable 5. As you can see right here, um, it can create some pretty good stuff. It's pretty solid on on building things out, which is great. Now, if you're wondering, okay, how should you use it? What's the best thing for using it for? Let me cover that as well in a second. And also how to get access to it. So, if you're wondering

how to get access to it, it's pretty simple. All you do is you go over to Claude like so. And then you can select Fable 5 inside the model list. Now, a couple of things to note here is that number one, Fable 5 is only included in your subscription until the 7th of July. After that, it would be based on paid extra credits, which means that you might as well make the most of it for the

next 7 days and then who knows what's going to happen after that. It may be that, you know, it's only available on outside of the subscription with Claude and therefore you can't get as much access to it. Now, the other thing that I've noticed as well recently is that you can get some pretty similar outputs with other models, which I'll come on to in a second, but it does create some cool stuff as you can see

right here. We also, for example, built out this web operating system, and it created a nice system here where we basically have a complete OS living kind of like Windows where we can use these different apps. We can test them out. We've got the terminal, we got notes app, we have paint over here as well. So you can create some pretty amazing stuff and also it's a lot faster than using some of the alternatives that you

have right now. So for example, one alternative to Claude Fable 5 is that you could use Hermes of agents. If you're not sure what that is, that's basically a panel of agents, a panel of models that work together. Like for example, Claude Opus 4.8 and GPT 5.5. You can ask a panel anything and then you can get your outputs back here. But the thing is these are just kind of like one shot. you you give the

panel a prompt, you come back in 10 minutes and you can't really go back and forth with it in the same way. Whereas, for example, Fable 5 is a lot faster to use. Now, there are some things that I've seen it fall down on. So, if you're thinking about using Fable 5 for web UI is not particularly great at that. So, let me show you some of the other creations that we've done. We go to Goldie

Bench here. We've tested all the models out side by side. So, if we go over to Fable 5 here and we check out the landing page that we built, it looks pretty basic. Like, that is pretty bad. So, it's not great at everything. It It can create some amazing things. It's very good at like coding out uh different projects, vibe coding, cool stuff, but it's not amazing at UI. Now, what I'd recommend is that you teach

Claude or whatever you're using a skill for UI, but we already did that and still we didn't get great output. So, it's something to bear in mind there, too. Also, it can be buggy first time around. So, some of these builds, for example, didn't work first time around. If we have a look at this game, for example, it didn't work first time around. Then, we rebuilt it right here and actually looked a lot nicer on the

second build. But something to bear in mind as well is like it's not going to build out perfectly. It still takes a lot of back and forth. You still have to guide it in the right way. And even for example, when I'm creating like tutorials or blog posts and that sort of thing, from what I've seen, Fable 5, it still struggles at times to get everything right. And it it kind of it's interesting because like I've

custom trained Opus 4.8 eight with a skill for creating guides and tutorials and Opus seems to stick more closely to the rules than for example if we're using something like Fable 5. So for example, we actually asked Fable 5 with a custom skill to create diagrams inside his tutorials and it's the same skill that Opus 4.8 uses. Opus 4.8 seems to do that first time round, but you can see here for example that Fable 5 struggles

at times. So it says like fair catch on both counts. I use the guide skill structure, but I skipped the rule that you have inside your guide. I'm like, wow. Okay. So you're just skipping all the rules that we put in place to avoid skipping them. Makes sense. So there's some things where I'm like, okay, Fable 5 is great. And there's other things where I'm like, you know what? If if I can't use it on the

subscription, it's not a big deal. We've got mixture of agents. We've got Fusion. We've got Sakana Fugu, which are all panel alternatives where you can get agents to work together and then you fuse the best answers. So, it's not a big deal if Fable 5 goes away. The other thing I wonder as well, and I've seen this from some of the tweets online is that a lot of people are kind of frustrated with it, right? So,

you can see for example, this is trending on X right now and it says, you know, anthropics fable model faces backlash over like the blocks and everything else it's got as well. So, here's another problem that has is it automatically switches to Opus 4.8 sometimes, which means like you're in the middle of a chat, you're trying to use Fable 5, trying to use the best model out there, but then it struggles or it triggers something that

it doesn't like and then it automatically switches to Opus 4.8. Also, anything science related will just switch back to Opus 4.8 as well. So, it's great that Fable 5 is back. It doesn't feel as powerful as it was before. I just feel like maybe some things have changed on it. Maybe some settings have changed on it. It just doesn't seem to build as well in the same way. So, let me show you some more examples. So,

we've got some sideby-side tests here of mixture of agents versus Fable 5. And if we have a look at this Neon City one, this is quite cool for mixture of agents. If we have a look at the output from Fable 5, it to be fair that is a lot better, right? Look looks a lot cooler. It's 3D, etc. More fun to use. If we have a look at some other stuff though, for example, like this one

is a a pool simulator. It just doesn't seem to work as well, right? Like it doesn't show the pool Q seems super buggy to use. Doesn't quite work as well. If we have a look at the mixture of agents version, this is way nicer. And you can actually see the pool queue and everything else. So it's not always not always the case that Fable 5 is going to give you the best outputs out of everything available

right there. And then also the other thing I would say here is like when we were using mixture of agents these tests were from last week. So when we use that system we were using Fable 5 uh sorry Opus 4.8 and GPT 5.5 together and they tended to get better results for some tests than Fable 5 which is mind-blowing in itself. So, here's another example. Kind of like a RPG style game. This is from Mixture of

Agents. And then we've got this version from Fable 5. And it doesn't really work, right? There's no main character. It's difficult to control. There's nothing really going on here. The output from Mixture of Agents is way more interesting and actually better. And again, like we tested this kind of Skyrim style game. So this is the intro window from Mixture of Agents. Looks really cool. Super nice. Very smooth when you use it, etc. Pretty amazing. If we

have a look at the version from Able 5 doesn't quite look and feel as nice. Feels a little bit slower. I would say Mixture of Agents did a better job again. So, it's very interesting to see like these panel models outperforming Fable 5 on some tests. It's also not great at following instructions from what I've seen with Fable 5. It can switch to Opus 4.8 sometimes as well. And also, it's not available on the subscription for

too long. So, it's great. It can build some awesome stuff. Probably the mo well is the most powerful standalone model, but I would definitely try panels. I think like you might get better outputs with this. I've been impressed with some of the stuff it's built. Like it's pretty cool. It's just maybe not as good as we were all hoping. And I wonder if as well something happened to Fable 5 between when it got taken down and

when it's come back up that's just made it not as effective in terms of maybe some of the safeguards that were put on or that sort of thing. Now some people say, you know, can you use a cheap alternative like for example GL 5.2? GM 5.2 2 is more comparable to Opus 4.8, it's not going to give you the same outputs as something like Fable 5, but if you used it as a Fusion, whether that was

with Fusion directly or Sakana Fugu, which works in the same way, or for example, even using Hermes mixture of agents, I think you could get outputs. So, we're not too far away from that. So, it's worth testing. And I think Hermes Bench is going to be released soon, which tests combinations of models and whether they can outperform playable 5 or Opus 4.8 on benchmarks, too. So, that'll be fun. So if you want to get this full

system with Hermes mixture of agents, fusion, sakana, fugu, you can see that we've built loads of stuff with fable 5 inside here too. You can get that inside the AI profitable link in the comments description or go to the profitable.com. This is my community to help you save time and scale with AI automation. Inside the community as well, you can ask questions and I answer them with video tutorials daily. You can also go inside the classroom,

get access to all of our best trainings. We have loads of trainings on Fable 5 itself as you can see. So, we have Claude Fable 5 with a full video tutorial, a step-by-step guide, and 100 prompts and also a 30-day road map road map for implementing it. Also, if you're interested in stuff like Fusion or Hermes mixture of agents as an alternative or Sakana Fugu, which are all alternatives, then you can get that inside here as

well. So, we have video tutorials covering each of them, how to use them, and how to use them inside our agent operating system. So, if you want to get the video tutorial for the Agent OS, you can get it here. We've got the last update date. There's a full guide on this. Plus, you can get the C file to install it. You can also jump on four weekly coaching calls to get help and support in real

time. Share your screen, ask questions, etc. And then also inside the map, you can meet people in your local area who are building with stuff like Fable 5 and Hermes and everything else. So, feel free to get that link in the comments description or just go to the aiprofit boardroom.com. L says, "Thoughts on Kimmy as a cheap alternative to Fable 5?" Um, I would say if you had if you wanted to use something as a cheap

alternative, then go with GLM 5.2, but again that's more comparable to Opus 4.8 than it is to Fable 5. Frameworks. Frameworks are just like diagrams and you know stuff that we teach like for example infinite context engine with Obsidian. That is a framework. Heat. Heat. Heat. Hey, heat. Hey, heat. All right, last one for me, peeps. Today I'm going to show you what I'm building with this Claude agent operating system that combines for example Fable 5

uh everything that we built with it. We've got for example Hermes uh voice agent Hermes Oracle that can pull in the latest news a full outreach tool mixture of agents and everything else that we're doing together. And I'm going to show you exactly how this works step by step what we're building with it and the progress we've made so far. So, I started building this out about 2 months ago, and it was really just like a

kind of fun project where I was like, "Okay, let's try and just build out a basic mission control." The reason that I did this is because when we were using this, like if you're using the terminal, if you've got, for example, clawed in another tab, none of it is really linked together. It's all super messy. There's no memory stored between anything. And also, you can't see everything you've built, right? And also, the other problem here is

like I can't customize terminal. I can't make the UI more beautiful, but I can design my own operating system like you can see right here where we've got everything plugged in together. And the other thing that I've learned from this is like because we've built this for AI profit board and community members, every single request that we get is kind of like, oh, that's a new idea. That's something new we could add. That's something we were

missing before. And so every time you build a new feature in, it unlocks another door to something else that you could add on top of that. Let me show you an example of this. So, for example, we built in Hermes agent here. And really right when we began it was just a chat. It was just literally like a chat and then you could have claude CLI chat. And what we did from there is we started building

out separate chats with different profiles. So for example every time something new and useful comes out like for example Quen 3.7 or GR build or Kim K27. We're like let's create a new profile for that so we can chat between them and see what we've created. Now also because Hermes keeps releasing like these new amazing features like for example mixture of agents we like right okay let's plug that into the system as well so that we

can use it whenever we want because again if you were running through the documentation or if you were trying to use those separate features it would be super messy let me show you an example of that so if we go to Hermes mixture of agents and documentation on it it's all like terminal commands it's all coding it's super complicated to use but it's really powerful right like I've actually tested this out versus Fable 5 today. And

on many examples, Heromy's agent is either right up there with Fable 5 or actually beating it, which is incredible when you think about it, considering it's using older models together. And so my point here is like every time we get something that comes out and it's brand new from Hermes Agent, we plug it into this system right here. And I think that's a fantastic way to do it because instead of like going into the terminal and

trying to remember how to use mixer of agents or like losing all the creations that you make with mix of agents because they're in just like a a folder locally somewhere, you can have everything organized. It's neat and tidy and it looks and feels exactly how you want it, right? And so that's what I'd recommend for you if you're thinking about doing this. Segment each piece of Hermes you actually use. Now that is another point too.

You don't want to build too many features into this. You want to keep it simple and easy to organize because for example you might look at this list of CLIs and because I test everything we build in there but actually you might only need like Hermes and Claude. You might only need Claude inside here. You know that's the difference is like you don't need everything. You just need the stuff you're actually going to use. Now something

else that blew my mind is the Hermes voice agent that we have here. This is a voice activated version of Hermes that we can wake up with a wake word. We can use it in real time. If we actually say something to Hermes agent right here, it will actually reply to us as well, which is great. And then also the great thing about this as well is that when we are using this voice agent, it can

also control our browser and also control things locally and it just listens to us in real time. So we can have it in the background on a monitor and it can just talk and reply to us at any point. We can also see the full conversation over here. And you can see that actually just took what I said and then plugged it in. And also everything that we built with this voice activated agent is stored in

one place again. And I think that's good because otherwise what you're going to have is a voice agent. Quite a lot of people have probably seen this before. It's like you build a voice agent but then you never use it because it's not easy to open up and you have to restore it and you have to go back to where you were, etc. Whereas with this system, it's all ready to go. We also have Hermes Oracle

that pull in the latest news. So for example, Claude Fable 5 is back today. That is obviously the biggest news on X right now and actually links directly to the tweet related to that. It pulls in all the latest news. We can publish content. We can draft content for social media and it's all ready to go. Now you might be wondering at this point, how did you build it? Every single feature that we plugged in, we

actually just asked Fable 5 to start building out for us. So for example, the lead generation tool that we've got inside Hermes, you can see right here, we literally built it out step by step with Hermes. So, if you're wondering how to get started with that, then all you do is you go into Claude and you're like, "Right, here's my idea. Can you build this into a beautiful UI?" And then also build on the current mission

control that you have. And if you don't already have a mission control, then you can start from zero and just say, "Hey, build me a simple mission control like this." If you actually have like a screenshot or an idea of what you want to see or the style, even like another website example, you can give that to Claude and say, you know, create a mission control based around this particular style or this particular dashboard that we've

got over here. And that's quite a nice way to do it as well. So then we have these systems for orchestrating our agents because once you start building out more and more, another layer that you probably want to add in is an easy way to navigate between the agents and have them communicate together. So what we have for example inside the agent mastermind section here is a group chat where all our agents can talk and they

can bounce ideas from each other. They actually read our obsidian vault, which we'll come on to later. And then they bounce ideas off each other and once they find something good, they add it into our pipeline so that we can actually implement that and we can see everything that we've built over here. And so you go from idea to actual creation like really really quickly. It's super easy to do and it doesn't take a lot of

work because your agents are coming up with the ideas. They're um replying to you. You just drop a simple challenge like for example, give me a great ideas uh for an SEO app and then it goes off and does it. Now, inside paperclip as well, what you'll see over here is a system where we have a pipeline of everything that our teams have built together. And the great thing about this is that we can build a

full team of agents. There is no other way that I've seen that's actually useful to create an organization of agents like this that work together. So, we got the CEO, then we have like different department leaders, and then we have sub agents underneath each other. Now, you might say, why not just use Hermes? Well, the thing is, if you're using Hermes or Hermes Terminal or Hermes Desktop, etc. Well, you can't use other agents together with that.

You're only going to use Hermes. And so, you're kind of stuck in that ecosystem. And you also can't customize it in the same way. So, if you have Hermes desktop, you can't really build all this stuff into it. You're kind of stuck with Hermes desktop. And it's great, but if you really want to have a team of agents that are all working together, building stuff and doing things exactly how you want them to be in the

way that you want them to be, in the way that you want it to look as well, then the only way to do that is building something like this, right? It's fully custom as a build. You've got all your um agents working together right here with the paperclip system. We have an organization right here. We have a dashboard of everything that we've done. We even got an inbox where my agents can actually message me and ask

me questions or say, "Hey, can you approve this hire of another agent or can we set up this one, etc." And the other benefit of this is that you have all of these different systems where you can see what you've built and look back on it. And I think that's fantastic as well because it's like, oh, where was that thing we created two weeks ago? Oh, there it is. Right. And we can even see how long

ago it was created. So you can see here it says 2 hours ago because we were just building with Fable 5 today. And so the great thing about this is we can look back at our progress from like 34 days ago and see what we were doing before, right? Um, and also like if Claude brings out new stuff. So, for example, you've got Ultra Code that came out, I think it was last month when Ultra Code

came in came out and we could build teams of sub agents like this team of 12 SEO sub agents. We can have them working as a team. We've got them in a separate tab over here. We can come back to that, use it whenever we want. The same with the managed agent section as well. Now, we've got all of our CLI plugged in here. Some things are going to be swapped in and out. And that's a

beautiful thing about this as well. So, for example, we plugged Fable 5 into this originally. Fable 5 gets taken down, no problem. What we're going to do is focus on the system, not the model. So if the model drops or the model's not very good or you run out of tokens or you can't use Fable 5 on the subscription anymore, no problem. You can swap out the CLI and just go back to Opus 4.8 as well.

And so you can be very very flexible with this in a way where it doesn't disrupt your workflows. So for example, we had Fable 5 running inside our SEO content pipeline and for most people it would be really really annoying to like just rebuild everything based on for example having to switch back to over 4.8. But for us literally in like 10 seconds we could say okay take out uh and this is how you do it.

You go into your claw CLI that built it or your agent that built it. You just say hey take out Fable 5 inside the CLI and swap it with the CLI for Opus 4.8. And that way it's really easy just to swap models in and out in like a minute rather than spending a whole day rebuilding everything which would be a nightmare. And then we've got for example another orchestration system here where we can have agents

working together on a cam board. So if we have a look at this video, this video was fully generated with a team of Hermes agents and we have a full system here where it can deploy websites and web pages and everything else. Then also for example like notebook recently came out literally yesterday less than 24 hours ago they came out with a system where you can basically generate short videos for free using the notebooks you've created.

So for example we've got four videos here that we've generated using this system. Now that's pretty cool because as soon as something new like that comes out which is super useful right like free educational videos that you can create with AI in like one click that's pretty amazing. And so as soon as that comes out with the MCP, we just link it and plug it in together. And I think with a combination of APIs, MCPs, CLIs,

and also local models, you can you can basically build and automate anything that you want with systems like this. And then also, for example, you got loop engineering. So one thing that I don't really do so much anymore is I don't really prompt my agents. I actually get my agents to prompt themselves and run on a loop. So for example with Hermes, if you look at Hermes Oracle, it's just running on a loop every 24 hours.

It refreshes itself. I don't have to intervene. I don't have to prompt it. I just come back to the outputs, right? And so I don't have to quality control my team's work anymore. They quality control themselves. I don't have to refresh their work or tell them to do stuff anymore. It all gets built into the system and it runs on loops. And so that's the other thing that we've built in that's really powerful here. So for

example, if you look at paperclip, you can choose when they run on a schedule. So it's just running on a loop for you in the background. The same for example with Hermes with the Oracle that's refreshing every 24 hours. The same with the outreach tool, right? That's just automated where you set up an outreach campaign and then you can actually have the emails sent from Hermes agent automatically on a schedule. And so the thing that I

try and build with this more and more, it's just a loop where everything's a positive feedback loop. It improves itself. It prompts itself and we don't need to manage it. and it's very autonomous. But if we ever do need to start step in or stop something or have a human in the loop, we can easily build that in too. Now the final loop that I would say with this is the memory system. So you can see

here this whole system with thousands of memories, thousands of notes that all my agents uh use and use to give me personalized answers. This was all automated with AI agents. So AI agents like Hermes, like Claude, etc., they add the memories and then they pull that out when they're updating me. So if I go into Hermes or if I go into cla I'm like okay give me a list of keywords for my website it will just

look at my memory system here look at my context and then automatically log into the system the new keywords it comes up with and so it's updating the system but then it's using the system to create content and so that's working in a positive feedback loop as well. So it's a really powerful system here. There's more and more things that we're building in based on what community members want. Like for example even a music agent and

if you want to get this system from me I mean you could build it yourself. I spend about 3 to four hours a day building it and improving it just so that we can help everyone inside our community. You can get that all inside the AI profit boardroom. So if you want this operating system that we've built with Claude and it's just ready to install then you can get that inside the AI profit boardroom. You might

say okay you know this seems great but it might be a little bit technical. So, we've got over 194 pages of testimonials and wins from community members. And you can see as we scroll down here that people are absolutely loving it. And non-technical people, I'm nontechnical myself, can all build and use this and get the full power of it. Right? So, there's so many people just getting amazing results like this. People showing off what they've built

with their agent operating system, how they've built with it, what they've built into it, etc. And so, the great thing about the community is we can all share, learn, grow, and build new things and then share those ideas with the community as well. As you can see right here, like Hobing was saying how it revolutionized his work with AI agents. There's so many wins like this I've seen and it's pretty much an endless scroll of wins

and testimonials and everything else. So, if you want to join us, feel free to join inside the air profum. If you're worried about tokens and that sort of thing, we actually have a guide on how to run an agent operating system for free as well. And inside the community, you can ask questions. I do daily tutorials answering everyone's questions about the agent OS. Inside the classroom, you can get access to all of our best lessons. And

if you want the agent OS system, you can grab it right here with the video tutorial, the last update date, and the zip file. And then we add new daily tutorials as you can see based on what's actually useful and you can implement today. So feel free to get that link in the comments description. We have a beginners to expert course here as well. You can jump on four weekly coaching calls where you share your screen,

wire this in together, ask questions, etc. And then inside the map, you can meet people in your local area who are building with AI agents like you. So feel free to get it. link in the comments description or just go to the aiprofitbomb.com. Thanks for watching. All right, peeps. That is all the questions. I've answered every single comment, every single question, every single question inside the community. Uh we've built loads of cool stuff with Fable 5

as well. Thanks for watching. I'll see you on the next one. Cheers. Bye-bye.