NEW Claude Code Updates: Context Engineering 2.0!

Today I want to be answering some of the latest questions about our agent operating system, how to get the most out of it, how to connect your AI agents, and also how to sell this to clients. So let's get straight into it. These questions from the AI Profit Board and community, where we help people with AI automation. So if you do have a question, feel free to ask and post this idea.

I create a video tutorial for everyone daily. So one of the first questions we got here was from Faizan, and he was asking about like, what's the best and most efficient way to build websites similar to these? So there's actually a really good skill for this on GitHub, which you can see right here. And basically this works really well with Cloud Code.

So you can use Cloud Code to learn from other websites and then create websites similarly to that. And what you can actually do is just take that GitHub, for example, then you can go into Cloud Code, you can create a new chat, ask it to install that, and then give it the websites you'd like to build similar websites to. So it just works in three simple steps. You install this skill to Cloud Code, then you're gonna give Cloud the websites you'd like to replicate, and any other information about the sites you're building, and then just ask Cloud to use the skill from step one to build it out for you.

Now we've got another question here from Nick, and Nick is talking about how to build an agent AI operating system for his client who owns a fitness. His client also wants to be able to access it on a VPS. So this is the prompt that he's asked us to take a look at. I would actually say at this point, it's probably not gonna be just one prompt that builds it, right?

Because it's gotta run in a loop, it's gotta iterate, it's gotta test, it's gotta check its own work, it's gotta keep improving that, and bear in mind, like with an agent OS, you're just constantly iterating and improving it. So our own agent operating system we're building out daily. So what you can actually do instead is you could give the agent that's setting up for you, so let's say, for example, it's Cloud Code that's setting up the agent OS, you can actually use our template inside the AI Profitable, the zip file, give it the details of exactly what the client want, and then use something called goal mode to build it out. Now, the reason I recommend using goal mode is because it needs to run on the loop to build this out, right?

So you can use forward slash goal inside Cloud or Codex, whatever agent you use to build this, give it the zip file of the agent operating system and give it the specifications of the client's requirements. So for example, if it needs a fitness app and a social media app, then you can build it out from there. Then the final step would just be making sure that it actually works and testing it with the client. Now, when it comes to setting up on a VPS, you could use tail scale, or you could use Cloudflare.

I actually linked some examples of clients who've already done that inside the AI Profitable audit. So for example, you see here, John Meza, he created the agent OS on VPS, and the way that he did that was using Cloudflare, as you can see right there, and then he can actually use it from a mobile app, from desktop, but also this means that you can give your client access on a VPS and you can just manage it from there and host it. Now he was posting about Codex having JavaScript now. So if you haven't already checked this out, we've got a full tutorial inside the AI Profitable audit, but basically Codex can now use voice mode, and then you can speak to Codex, get it to operate your computer, and it can also use browser use, it can use all these tools, but basically the voice mode can orchestrate your whole screen.

It's pretty cool. The one thing that I would say is that it's a little bit slow when you're using it. So I can see the future of it, I can see how powerful it is and how useful it could be, but right now, it's still gonna lag, it's still gonna break, it's still gonna struggle on some things, but we do have a full demo testing out, as you can see right here, and when that is actually really reliable, it's gonna be scary how powerful it'll be. This is a really interesting question.

I literally, I had exactly the same problem earlier today. So when I was using Chord Opus 5, it can do pretty good outputs, but it is super slow. Like something that would normally take Fable 5 about 20 minutes, I've seen Opus 5 take about one hour to do. It's crazy.

So it's great that we've got a model that is Fable 5 level and it's cheaper, but right now it's not fast enough to build anything substantial with. So I actually changed all of my settings inside Chord just to switch back to Fable 5. I think that if you do run out of Fable 5 tokens, either just use the credits, because it's gonna save you time anyway, or switch over to Codex, because GPT 5.6 Sol is really good too. But yeah, for sure, Chord Opus 5 is super slow, particularly over the last couple of days.

Reach posted about Obsidian folder structures and the best way to set this up. So basically with Obsidian, Obsidian works really well inside the agentic operating system because you have all of your memories, all of the folders, all of your files set up in a system like this so you can visualize. Now these are just markdown folders and files. The way that we actually set this up is with something I call the infinite context engine.

So our agents upload all of their memories into Obsidian, and then all of our agents across our whole agent operating system can pull in those memories and use them. So for example, we were using Buzz earlier today, and Buzz had instant context of everything that we work on, every project we use, every website we work on, even have, for example, login details to our WordPress websites. As you can see right here, it could post directly to our websites for whenever keyword we give it. So the way that we set this up is we use something called PARA.

This stands for Projects, Areas, Resources, and Archives. It was actually designed by Productivity X so that it can sort information by actionability rather than topic. So there's four different categories to this, and this just means it's really easy for your agents, particularly in a business context, to understand everything about you, your voice, your goals, your brand, projects, and any companies that you have too. So you can see, for example, if you zoom in here, we've got the AI Profit Boarding, we have our Funnel Strategies, we have OpenCore, and all of this links together inside one beautiful system.

So I definitely recommend checking out the Infinite Context Engine system. Also, something that's really cool about this community is people are actually implementing and taking action based on what they learn. So you can see, for example, Mohamed, shout out to Mohamed, he set up three custom GPTs from some of the classes, and that's like three new automations they set up based on what he's spending time on. So imagine, for example, you set up three automations per week, that's 150 by the end of the year.

I don't think you need that many, but even, for example, if you do one a month, it's gonna make a massive difference in terms of the time you save, in terms of the programs you make, and also it's just great to see people taking action. So shout out to Mohamed. Jeremy asks, which brain built your Dashboard Agent OS? So for me personally, I actually used Claude to build it out.

It was actually Claude Fable 5. Claude Fable 5, I think, is a four. And we began it with Claude Opus 4.8 when I began a couple of months ago, because all these five generation models went out. But yeah, Fable 5, Opus 4.8, it wouldn't have been possible to build out the Agent OS system without those.

But the great thing is that everyone inside the community gets access to our zip file to install it. And you can use any of these models set up. You know, you could use CodeXO, you could use Hermes, you could use Claude Fable, Opus, whatever you need. We got another question from, who's basically focused on email personalization.

He was asking like, what's the best way to efficiently personalize the opening line for each prospect that he's reaching out to? So the way that we actually did this is we used a combination of Hunter API with Claude. And it analyzes each of the leads. So we can type in any type of leads that we want, and they will automatically enrich those leads using the combination of Hunter API and Claude.

So if I had to do this all over again, I'd probably use something like Claude, give it the database of leads I'm about to reach out to, and just have Claude write like the first sentence of personalization in the spreadsheet line for each lead. And bear in mind that Claude can create and edit documents, so that shouldn't be a problem. But if you do have thousands of prospects, then obviously it's gonna take a long time, and it's probably something that you'd have it working on hours for. And then the way that I'd set it up on the spreadsheet is I would have a name, the email, and then also the one sentence that Claude can pull in.

Now, if you have more information that you can plug into the spreadsheet to give Claude more context on the lead itself so that it can personalize the message better, that's even better. There's also a couple of skills. So there's something called Lead Generation Strategy on MCP Market, I've not tested out. And there's another one called Lead Research Assistant as part of Awesome Claude Skills.

I've not tested those out, and I think actually what it could do is do the research on the leads, and then use that to write the personalized sentence too. And then when it comes to sending it out, you can just use, for example, Hunter or whatever software you prefer, and just load in the spreadsheet that Claude is fielding for you. And that's basically it for all the questions. So we've answered every single question inside the community.

If you want me to create a video tutorial for you and answer your questions in devs like I did today, you can get that inside the AI Profit Board and just post inside the community. It's also got loads of great training. So all my best trainings on, for example, how to go from a beginner to expert in AI automation, our new daily updates. So we've actually created new guides on Buzz, on Chad Chippity Boys, Claude Ogres 5, how to build an agent operating system and run it for free, Kim K3.

And then we've also got the full agent operating system right here if you want to get it from us. So you update this regularly with a video tutorial full guide, and then there's a file you can install with any of your AI agents. Inside the calendar, you can jump on with coaching calls, ask questions, get help with support in real time. And then inside the map, we can meet people in your local area who are building out with AI agents like you.

So feel free to get that link in the comments description or just go to the AIprofitboard.com. Thanks for watching.