Claude 5 + Hermes: Build ANYTHING!

So Claude's most powerful model ever, just dropped today. And I want to show you exactly how you can get the most out of it. Because most people have no idea how to actually unlock its power. And that's exactly what I'm going to show you today.

What we've actually created is five different projects, and even created this video, as you can see right here, demoing each of the projects that it created, which is pretty amazing in itself. And even created, for example, like an orchestration dashboard, where Claude can control all of the agent's delegate tasks. We have a group chat right here. We have multiple other things I'm going to show you in a second, where you can get your AI agents to be commanded by Claude, and then also get way more out of Claude.

Now, the reason you want to learn this today is because this is only available for a couple of weeks. On 22nd of June, Claude Fable 5, which is Miphos level as a technology, will not be available on the subscription anymore. So if you're going to use it, start experimenting with it today. And that's exactly what we're going to show you today.

Now, if you're not familiar with what Claude Fable is, let me just give you the too-long-didn't-read. So on June the 9th, Anthropic released Claude Fable 5 and announced Claude Miphos 5, which are brand-new fourth-model classes above Opus. Fable 5 and Miphos 5 are similar models, but Fable 5 has safety guardrails. Miphos doesn't, and it's restricted to VED partners.

And it's state-of-the-art on nearly every benchmark, scoring 95% on SWE Bench Verified, which makes it super powerful. It's also included inside all Claude plans that are paid until June the 22nd. But from June the 23rd, it needs usage credit. So you might as well start using it now.

And Anthropic have disclosed themselves that over 80% of its own merge code now is written by Claude. So this is a super powerful model that we can use. So let's get straight into this. The first thing it actually created was this whole site, as you can see here.

So it created this full guide explaining what it did, how it worked, what it did, the whole framework, and then included links to each of the projects it created. Now, one of the projects it created as well was basically a website where we asked it to generate a landing page explaining exactly what the agent operating system is. And you can see that here. It's generated this full website and created it with this nice background.

I didn't have to prompt it at all, but it just went off and built this, right? And then it broke down the key concept of the whole agent operating system, how it works, what it can do, all the benchmarks, how the system works, wrote all the copy, and it's a pretty nice design, right? Now, what we also have inside a system is this pipeline where we can generate and build anything on the spot that we have an idea for. So if we have an idea, we can just plug it in here, capture it, it's going to plan it, ask us to approve the plan, which you can see here.

And then once it's done, it's going to implement it. And once it's implemented, we'll see it in the shipped section here. So this is another website that we've built with Claude directly. Now, on top of that, we gave it one idea, which was an agent command center simulator, like a living mission control screen.

So obviously at this point, we've created a full mission control, but we wanted to bring it to life. We wanted to make it more interactive. And we've actually created that here, so you can see. And so we can see what it's delegating, what's being done.

So for example, like syncing to Obsidian, delegating tasks to OpenClaude, et cetera. And then we can actually click into each of our agents inside the system. And we can see what it's done, what model it's running on, what its current assignment is. And we can see all of this in real time, which is pretty insane itself.

Now, the other great thing about all of this that we're doing here is that we can see it inside our workspace. So for example, usually if you're using Claude, like everything gets lost, or if you're using the terminal of Claude code, you can't find stuff that you've previously created. We've got a full workspace here where we can save everything that we've created previously. And so all this cool stuff that we've built, we can come back to later.

We can review it. We can use it for other projects. We can build on it. We can improve it.

And that's because we can see everything in one place, which is awesome. Here's another blog that Claude has created as well, which is pretty amazing itself. So hopefully this is inspiring you in terms of what you can build with it, like a living command control center where you can manage all your agents in one place and you can see them live. That's pretty amazing itself.

Building out nice websites, having a nice workspace where you can come back to, pretty awesome. Then we actually got the agents to work together inside the system. So we opened up a group chat with Claude inside there, Claude 5. We gave it one brief and then every agent actually came up with a new idea.

So Claude actually synthesized all the ideas together, the best of them, turned it into a concept here. And this is the concept. And if we open that up, you can see the game that we've created over here, right? And this is with all of our agents being orchestrated by Claude directly.

So you can build apps, you can build games, you can have your agents talking together. You can have Claude orchestrating everything. So if I show you an example of this, we go to the AI agent mastermind section over here, and then we go to the team brief. You can see that we said, come up with some ideas for the game.

Claude, Hermes, Gemini, Codex, OpenCore, they all came up with ideas together. And we said, brilliant. And then we said, Claude, synthesize all the team's ideas into one final spec that we can actually build. It came up with the idea here, and then it added it to our pipeline so that we can actually build it.

Next up, we actually had Claude Five as a CEO of our Paperclip company. It's a pretty heavyweight. So inside the agent operating system, we've actually built in Paperclip, and then we've created a full AI company called Goldilabs, which is 10 agents with job titles. So you've got a CEO, a CTO, engineers, co-operator, a CMO.

And we gave the CEO, Ada, which runs on Claude Five, one issue. And then we asked it to go off and create everything. And you can see it working right there. And so if we open up the issues board here, you can see everything that's been done day by day.

And then we can see the progress on everything. We can comment on it. We can ask more stuff to be added to it. We can look at each of our agents over here as well.

And so we've got a fully autonomous team of AI agents working together to build whatever we want. Here's another example. So we actually built out a landing page, and then we can open it up, and we've got it ready to go right there. And then the final thing that we actually created, the last one out of the Fable Five, is the showreel.

So we gave Claude Five access to hyperframes, which is a powerful skill for creating videos. And then it actually created the whole thing and generated an awesome video showcasing everything that's created today. And bear in mind, we've just been playing with this and experimented with this today, but you can see how powerful this stuff is, right? It can generate websites.

You can come up with ideas. It can create live living command centers between all of our AI agents. It can talk to other agents, get ideas, synthesize it all, and then build it out from there. It can organize a whole AI team of agents inside a company using Paperclip.

Most people are gonna use Claude Five in a chat tab, but if you really wanna build stuff, then having a powerful operating system like this is gonna help you organize everything. It's gonna help you get the most out of Claude Five before it actually becomes API or usage only. Now, you might be wondering, okay, should you do all of this? Honestly, I would just start with one, right?

Start with one. Don't try and build all of this at one place. Just create one, test it out, see what you think. If you like it, keep building more.

But the point here is definitely experiment with this stuff because it's super powerful and it's easy to organize all of this. Some great ideas have come out of this system. So for example, we've got the studio right here. We've got MCPs that we can plug into our system.

We've actually trained, for example, Hermes to be able to send emails. And we've even got Hermes Jarvis, which we can voice control right here. So when you start building out a system like this, you go from idea to implemented very quickly. And that's really how you can unlock the power of this stuff.

So you've seen exactly how it works, five different use cases for Claude Fable Five. You learned how to turn Claude Five into a builder, how to create a factory where you can take ideas and implement them. You've got a boardroom where your AI agents can debate together and organize each other. We've got the AI agent company built inside Paperclip.

We've got a version of Claude that is trained on creating videos and then demoing the stuff that is created so I can just see a daily report in terms of what's been done and what's been created and sign off on it. And you know why it works, right? It's super powerful. 95% SWE Bench, 1 million token context window, Mythos Class Brain, and it's state of the art on all the benchmarks.

So the main thing I would say here is don't watch a model, actually put it to work today. So if you want to build your own Fable Five like we've done today, if you want Claude Five actually working for you, not just impressing you in a tab, grab the agent operating system inside the Airprofit Boardroom. It turns Claude, OpenClaude, and everything else into one system. And you get the zip file, you can install this, you get the Obsidian memory set up, you get coaching calls where we can wire it together step by step.

And there's actually loads of people building with this stuff. You might think like pulling it all together is complicated, but I've seen so many people get results of this stuff inside the Airprofit Boardroom that I know that it works and I know that people can do this, right? Even if you're non-technical. I can't code, but I can build this out.

So if I can do it, you can do it. And I would say our actual productivity, like with everything we've built recently is absolutely insane, right? Look at all this stuff that we've built recently. This is just a paper clip.

We've got teams ready to go, so they're all organized when we need them. We've got Claude and Claude Five ready to go inside here. We've got the workspace to see everything we've created previously. We've got the pipeline, the agent group.

This is powerful stuff. And I've not seen anyone else organizing it in this way. So thanks so much for watching. If you want to get that, you can get it inside the Airprofit Boardroom.

You could build your own, but if you just want to skip the time required to build that and all the tokens required, you can get the agent OS system here with the zip file at the bottom. We've also got a full masterclass on Claude Fable Five, how to use it, how to get the most out of it, a hundred prompts you can use with this stuff and a 30-day roadmap for actually implementing it. Plus every time we build something new or find something interesting, we create a full video tutorial and step-by-step guide on how to actually implement it. So the other cool thing as well, you can ask questions inside the community.

You can see, for example, other people's mission control dashboards and what they're building now, which is pretty insane. You get weekly coaching calls and a map where you can meet local builders near you. So feel free to get that, link in the comments description or go to the airprofitboardroom.com. Thanks for watching.