Qwen 3.8 Agent OS Just Changed AI Agents Forever!

And the 3.8 Max is one of the most powerful models in the world, and you can now plug it into an agentic operating system to build and automate anything that you want. Now, the reason that you do this is number one is 2.4 trillion parameters. Number two, it's actually beating Fable 5 on many of the benchmarks. And number three, it's really powerful when I've tested it out.

So today what I'm going to walk you through is the open source Quen machine for agentic operating systems. So you can build and automate anything you want using Quen and you'll discover how to plug it in into your existing workflows and systems. So you can get the most out of it and have it working and orchestrated directly alongside your AI agents. Now you might say, why would you use this?

Again, it's a 2.4 trillion parameter giant that you can plug into your dashboard. This is an open source agent. Bear in mind, it's self-improving as a model. So it's actually getting better and better all the time.

And so you can plug this into your chat, your memory, your tickets, your builds, and you've got your agentic operating system. Then you can have all of your workflows in between, and you can plug in Quen 3.8 Max into this. So let me show you an example here. So we have, for example, Hermes agent when 3.8 plugged into our Hermes agentic operating system.

And so what that means essentially is like we can switch between models when we want to do different things. We can also have Hermes directly orchestrate all of our other agents or other agent profiles. We can spawn sub-agents of teams. And then also we can, for example, get our agents to automate anything.

So for example, here we said forward slash learn, and then we've given it a guide and it's actually created a custom guide and skill locally using this system. Now one of the other benefits of Quen 3.8 is it's actually pretty fast and it's designed for agentic models. And also you can't use, for example, Claude CLI with this system. But if you have a coding plan with Quen, you actually can plug that into Hermes agent.

Now also what's really good about Quen specifically with agentic operating systems is that it's designed to code for hours, autonomously alone. So you can plug it into a goal system, as you can see right here, and then you can walk away, leave your AI agents building for you, and you can come back to a history of the goals here. Now one of the reasons you would do this is because if you have a big task that needs to operate autonomously and you don't want to babysit it, you can just have it looping over in the background. And that way you don't need to prompt your AI anymore.

The other thing that I like about Quen is that it's very good at core tooling. So for example, if we use something like Obsidian inside Quen 3.8 Max's agentic operating system, then it's very good at looking at our context, understanding our memory systems and then updating that with new things it actually does. So for example, here you can see agentic OS memories and it's pulling in the latest information, updating our agentic memory system. And from there that gets plugged into Obsidian.

You can also use this for lead outreach. So what we have over inside the outreach section here is a system where we've plugged in the Hunter API key. We can use Quen 3.8 Max as a brain and we can find new leads around anything that we're searching for. So if I type in, for example, like SEO agencies that are interested in white labeling backlinks, it will find me a list of relevant leads and reach the leads automatically.

And then we can actually draft an email campaign, send out the email campaign and schedule it and also manage your inboxes using Quen 3.8 with Hermes directly there too. So the great thing about that is the even lead generation can be handled inside a custom workflow where it feels like a SaaS tool, but actually what it is is Quen 3.8 Max with Hermes agent, just with a nicer UI. Now, additionally, you could use this inside other agentic harnesses. So let's say for example, you're not a big fan of Hermes agent.

Instead, what you could do is use Claude code and then you could switch the brain over to Quen 3.8 Max and start coding with Quen 3.8 Max as a brain, Claude code as the agentic harness. And then you can see and view all of the builds you've created over here too. So we've even created like full games using this system, full websites, etc. And it looks absolutely amazing and it's very nice at creating different things like this.

Then what I also like to do here is I will plug in open source projects into the system so that I can basically have custom workflows ready to go if I find something useful. So let me give an example. We found Open Design, which was a GitHub project, open source. And so we plugged that into our agentic operating system so that we can create beautiful designs whenever we want to.

You can see some examples of what we've created over here. So we can create these amazing looking websites. We can custom design them. We avoid like the AI slop of normal design.

If you have a look at these websites, they look super nice, but they're easy to build because we've got it inside a custom workflow using Open Design. We could even plug in free models. So what you could have, for example, is you could have Paperclip with Hermes and Quen 3.8 as the CEO inside your team, which we can have over here. And then we can have local models actually doing the work as sub-agents underneath.

And so the great thing about that is that Quen is then used as a brain, as the orchestrator, as a frontier model at the top of the chain, but it can use free APIs or local models to orchestrate the actual work to do the actual hard stuff underneath. And then also what we can have over here inside our agentic operating system is we have a group chat. So what this means is like we can have Hermes with Quen 3.8 plugged in, but we have all of our other agents inside a group chat too. So we can tag, for example, Claude, or we can ask Hermes to build something out.

So it's a really powerful system. And bear in mind like the output and the quality of Quen 3.8 Max is just very nice in general. So you can see an example of a build that we've created here, like the UI is nice, the design is nice. It creates fun stuff and it's easy to use.

Here's another example of like a flight simulator style game. We even created, for example, Minecraft, as you can see right here. It looks pretty cool. So let's talk about the layers of your agentic operating system.

If you want to build something where you can automate anything with Quen 3.8 and it's ready to go whenever you need it. So this is the exact system and the layers stacked into it. First of all, you've got the giant. So Quen 3.8 Max, 2.4 trillion parameters, open source, million token context window, and that's the brain of your whole engine.

Then you have the socket. So if you need something that does the work, that could be Claude code, it could be Hermes agent, some sort of agentic harness. And that is layer number two. Layer number three is that you have the actual UI that you can flick between your custom workflows.

So you've got the brain, Quen, the hands, which is Hermes or Claude code, and then you have the separate workflows. Like for example, Hermes Oracle. What Hermes Oracle actually does is it tracks it over time and it looks at the latest trending news. It runs on a scheduled task and it pulls in the latest information from social media, gives us the most important updates in our field.

And you can customize this to your industry. We can then from there draft a social media post or publish to our WordPress websites directly on that particular topic. Makes it super easy to just click one button, create content and have it focused on the latest news. And bear in mind like 99% of your competitors do not have access to this, but it's very easy to use because you just click a button.

Now to actually build it, it can take like three to four hours per day to build something like this. If you just want to get my setup, you can get it inside the Air Proffle Boardroom. Link in the comments description or just go to the airproffleboardroom.com. But this is how you squeeze the most out of Quen.

Most people are just going inside Quen here and then they've got Claude code somewhere else. And then they have chat GPT. Doesn't sync together in terms of the memory. Doesn't have a good agentic harness.

You lose everything that you've created as well. So you can't really find your builds. It's very difficult to really have that running on a loop, right? You have to go back and forth inside the chat and agentic operating system solves all of those issues in one swoop.

So we also have the memory loop so that every exchange auto saves to the obsidian vault. So the giant brain reads your business context instead of starting from zero. And then finally you have the work surfaces. So you have the chat.

We have, for example, a wake word with Hermes where we can say, Hey Hermes. And it just wakes up and listens to us. We also have, for example, the voice agent here that can respond to us in real time. This Hermes Apollo and we can see all of our builds with Hermes Apollo over here as well, which is super nice.

Cause then we can look back at our work. We can pull up a project really quickly and it's super easy to navigate as well. So the work surfaces, the chat, the wake word, the Kanban boards, the workspaces, all of that is integrated into one beautiful system too. And so before most people would have like a chat tab, right?

And they just start from zero and it's a mess because you've got one browser tab logged into someone's chat site. Like for example, chat.quayne.ai. You have to re-explain your business every single session. You're copying and pasting answers by hand.

You're losing all the work that you've created. There's no tickets. There's no builds. There's no voice agent.

It's just typing. And it's a closed off model, right? You can't really edit or customize chat.quayne.ai. But what you can do with this system, this machine is that you have the giant living inside your dashboard next to every other agent.

It reads your obsidian memory. So it knows the business from cold. Every exchange is auto searchable forever. And there's a chat, there's a voice, there's a wake word, there's a Kanban board.

There's custom workflows built in and it's open source as well. Now you might say, okay, I already use chat.qpt, I already use Claude. Why would I switch over to, for example, Quent? But you can have all of these running side by side inside your agentic operating system.

And the great thing about this is you don't need all these subscriptions. You can just pick one or two that you actually use. You also might think, well, do I have to pay for the Claude API to use this? No, because you can plug in your CLI into the system as well.

Now, some people say, well, you know, the best models are closed. But actually if you look at Quent 3.8 Max, it holds its own against Fable 5. We've got side-by-side comparisons on goldiebench.com. But the point here is like Quent 3.8 Max actually outperforms in some places Fable 5 and GPT 6 Sol.

Sorry, GPT 5.6 Sol. Other people say, well, wiring a model into a dashboard, isn't that a developer's job? It used to be, but now you can easily get this done. I mean, for example, we share our agentic operating system inside the Airprofit boardroom.

We've got over 207 pages of wins and testimonials and loads of people have set this system up without being technical. So you don't need to be technical to use this and it's not a developer's job anymore. It's just you describing your vision and you can even just get our setup ready to go. And some people say, well, I should wait until the models settle until there's one declared winner.

Honestly, the operating system is built for swapping out models because there's going to be a new model tomorrow, next week, next month. And it all changes all the time. So the great thing about having an agentic operating system is it doesn't even matter what model comes out. You've still got the systems.

And it's the systems that matter the most, not the models. So if you want to get this exact setup, you can get it inside the Airprofit boardroom with a zip file to install our setup, ready to go. And all these systems, we improve it daily and you can get new updates all the time. This also comes with an amazing community where the goal is to learn, save time and grow with AI automation.

Now, if you want to get the agent OS, I've just shown you, you can grab it over here in this section and you get the video tutorial on how to set up the last update date, a full setup guide and the zip file to install it. And then we add new tutorials as new cool stuff comes out as well. Inside the community, you can ask questions and I personally answer them along with the whole community. And then inside the calendar, you can jump a week coaching calls where you can share your screen, ask questions, get help and support in real time.

You can also meet people locally near you inside the map, and that's all available inside the Airprofit boardroom link in the comments, description, or just go to the AIprofitboardroom.com. Thanks for watching.