Hey Jarvis, give me the rundown for today. >> Good morning. You're at about 466,000 followers across all platforms, up about 3,000 this week. The latest videos pulling about 4,000 views a day, 17,000 so far. Big story in AI today. US government directive forced Anthropic to suspend public access to its top mythos class. Biggest thing on today's board, cut and ship the Jarvis HUD reveal video. Want me to run the daily inbox audit or do you have anything else in mind? So, what exactly are we looking at here? Well, this is Jarvis, our claude Fable 5 OS. Now, when we say Fable 5, I mean this was built using Fable 5, but it does not require us to have Fable 5 to actually run this. In fact, a lot of what you're seeing here is actually completely local and it can run on essentially any model you want. Now, if you have seen my previous Aentic OS videos, then you kind of know the deal here. We've taken cloud code and we've added another layer on top of it, which gives us some things that you just can't get inside the terminal. Things like visual metrics, things like skills that are turned into buttons. And this isn't a productivity theater thing. This is something that gives us a true boost if we're someone who's operating in a bunch of different domains and is also something we can easily package for clients or members of our team who aren't particularly technical. And Jarvis is just the next evolution of this agentic OS model. Its backbone is still this robust, completely customizable clawed code skill architecture that takes everything you do in your day-to-day, your manual workflows, your daily tasks, and turns those into skills and automations. And it's on top of that bedrock that we build this. And in today's video, I'm going to show you how it works, where the true value lies and how you can create something like this for yourself. And I think there's a lot of things you can take from this project, especially the local voice model dynamic we have going on. Before we dive into all that, a quick word from today's sponsor, me. So, inside of Chase AI plus, you not only have access to my exact setup you see in today's video, you also get the Claude Code Masterass, which is the number one way to go from zero to AI dev, especially if you don't come from a technical background. I update this every single week, and it also includes a codeex masterass. So, if you're someone who's trying to stay on the cutting edge of AI, this is the place for you. We're currently running some deals on the membership. So, if you want to take a look, just check out the pin comment. So, let's begin with a quick lay of the land with Jarvis so you can understand what it is you're actually looking at here. After we do that, we'll take a look under the hood, see how this is actually working, so you understand how to customize it and how to build it yourself. So, front and center, we have the whole voice aspect. Again, completely local, which allows it to be relatively fast and snappy compared to routing this all through something like 11 Labs, for example. And in the beginning of this video, you heard Jarvis give me a whole spiel about what's going on with my latest videos, what's going on with my follower account, AI news, that sort of thing. That is not a hard-coded script. What happens is when I ask Jarvis, hey, give me the rundown for today or what's happening today, it takes a look at the various reports that are automatically generated inside my Obsidian Vault and determines what's actually important out of those reports and what I should know about. As it did that, you will remember there were some various popups. And these little popups are reports or links to things that are relevant based on what it's talking to me about. So remember it said like, "Hey, your last video is doing X, Y, and Z." So it has this latest deploy popup which takes me to video. >> It mentioned stuff about anthropic, you know, essentially getting Fable 5 canled by the government. What does it do? It brings up the source article for that. It also talked about more things related to AI news and what's trending. And that all came from the morning report. So if I click this, you see this full writeup. This writeup lives inside Obsidian. This whole system is linked to Obsidian. So while I can read it right here, I can also click open in Obsidian and it brings up the original report inside of Obsidian. I can click on the different links. So there's there's a whole connection here. You also remember it asked at the end of each spiel, hey, do you want me to do that inbox triage for you? Do you want me to go inside your Gmail and see what's important, what we need to respond to? Well, that is a skill and those skills and automations are represented over here on the right. This allows me to instantly run any cloud code skill or automation with a click of a button. And again, if you remember what we did with our claude OS that we created inside of Obsidian the other week, same exact idea. The value ad here is more for if you're using this with a non-technical team or non-technical client and they want to be able to run skills and automations with cloud code, but they're not the type to ever open up the terminal. This allows them to get all that power with a click of a button and again fully customize. So let's say I did want to get a full inbox brief. If I just click inbox brief over here on the top right, you can see it mentions that it's cued right away. We see it here. And then we also see a new popup showing inbox brief. And we get a little progress bar showing that it's working on said automation. And once it finishes that, it'll not only generate a written report, it can actually give me a verbal rundown of, hey, here's what's going on. Here's what you should care about. >> Inbox brief done. Eight threads, four sponsor pitches led by Outskills paid offer plus Minamax and Liberovo. One fresh agency lead from Tamesai, and three filt. >> So, it gave me the quick verbal rundown of what it found. And then I can see the actual report, which again, as always, is linked inside Obsidian. So, these pop-ups are useful. They're relevant, and they link us to things we actually care about. and at any time I can clear them out. Now let's look over here on the right a little bit more. So kind of already talked about it. We have these different skills that we can change out at any time. One click away it runs them. Below that we have the schedule. So this is just sort of my daily schedule that is linked to my Google calendar. If I click it, it brings up my calendar. We have a little audio section. So if you're paying attention when it was actually talking to us, we could see it kind of just moving up and down and just lets you know if it's actually working. And below that we have a summary of what's going on in terms of AI news. Now everything you see here along with everything we talked about completely customizable. Maybe you don't care about having your Google calendar schedule here. Maybe you don't care about showing the audio or having an AI wire of the news. That's fine. The beauty of these Aentic OS, you know, sort of systems is the fact that it isn't a one-sizefits-all. This is just a set of tools that I'm showing you that you can take and do whatever you want with them. you know, your metrics will be different than my metrics. The sort of things you want to have one click away are going to be very different than what mine are. All depends on sort of your daily workflows and what you or your business do. But the plus size of something like that is like when we talk about creating this for clients or even team members is like you can make it whatever you want it to be for them. And over here on the left side, kind of the same thing. For my vitals, I show things like my subscriber counts, what's going with my latest video. I have a little tracker for my clawed tokens over the last 5 hours and some things like directives. So directives are just like, hey, here's like the top three things you should be working on today. Again, totally dynamic. And Claude Code figures that out based on my schedule. And then I have a little documents trail. So everything that's created or referenced by Jarvis doesn't just come up as a pop-up, it's over here. So if I want to click it again, like the morning report, it's right there. So that's the user interface. That's the visual side of Jarvis. Now, let's talk about the actual nuts and bolts. What's actually going on under the hood here? Because that's what actually matters. Let's be honest. If we kind of just stopped here and it was a fancy UI, well again, we're kind of just talking about productivity theater. If this is to be something that actually moves the needle versus sitting in the terminal all the time, it needs a proper backbone. And that's what we're looking at here. So, let's kind of walk through what happens when you talk to Jarvis and ask it to do something because it can go down a number of different paths. So, here you are and let's say you tell Jarvis, give me an update on today's morning brief. you have some sort of automation that you run every morning. It grabs whatever information is relevant to you and you want Jarvis to tell you about it. You don't want to read it. You want it to actually either run it or if it's already been run, tell you about it. So you audibly tell that to Jarvis, hey, what's going on in today's morning report that voice because again you used your microphone for this. That audio goes to Faster Whisper. Now, Faster Whisper is a free locally sourced program that is going to take what you spoke and it's going to transcribe it. Now, there are a million in one different, you know, local audio transcribers. You can replace this with whatever you want. This is just the one I chose because it works just fine. So, it's taken your voice and it's turned that into a transcript. Now, what do we do with this? Because we've talked about Fable 5 a bit and all these things. Does every transcript then need to get sent to Claude Code and we run Fable 5 and it takes a look at it? No, of course not. This whole thing is Fable 5 built, but most of the stuff that's running under the hood is either going to be Opus or Sonnet or frankly you could use a local model for a lot of these things because Jarvis isn't while it can do it, you can tell it to use Fable and you use it just fine. It's not like you're creating projects out of this. This is more in the personal assistant realm or for a non-technical team that just wants it to do a lot of the similar things all the time with with a nice easy to understand UI. So just that's kind of like big picture. But so we've taken what you've talked about, we've turned it into a transcript. Now we need to figure out what to do with it. And we kind of have three options. Now the first question that's going to be asked is can we route this transcript or this question via regular expressions or reax. So what's going to happen is this essentially script this deterministic piece of code AI isn't involved here. is going to look at your transcript and say, "hm, did it match some of these specific pre-coded phases that we know need to automatically do something?" What do I mean by that? Well, in the intro, what did I say? I said the rundown for today, right? I use the term rundown. Rundown is a specific trigger word, so to speak, that Reax picks up and automatically routes it to do a specific thing. And that specific thing is what you heard in the beginning. take a look at the reports, tell me what's going on, give me a rundown for the day, right? A basic summary. So, it automatically catches that keyword and does a specific thing. We like this because since it is just code, it doesn't cost us any money. AI isn't involved and it's very, very fast, right? In a perfect world, we could do everything like that and we'd have very, very quick responses. But that isn't everything because most of the time what you're telling the AI system to do can be somewhat murky, right? Requires a little bit of intelligence to figure out what to do and how to route it. And that's where option two comes in. And that is where we bring in Haiku. Now, why are we using Haiku? Why are we using the dumbest enthropic model out there? Well, because it's cheap and it's fast. What we're doing here in this whole section is we're simply routing. I'm not doing anything unless it's regular expressions that I know I can route it right away. We're just trying to figure out at this phase where does this response need to go to and who needs to do it. So, Haiku is actually very good at this. It's the most of the things you're going to be asking Jarvis to do are not too complicated. It just needs to understand which path to go down and Haiku figures that out for us. And again, we're talking about fractions of a penny for each request. Now, the third option and one that I include in my system, but you know, it kind of just depends on what you want to do, is to have this be a completely local model. You don't have to use Haiku at all. You can use a model on your local computer, which again leans into the local side of this whole system, and it does the same thing. It's going to take a look at the transcript, figure out where to route it. We're just routing here. So, to recap, you talk, it gets transcribed, and then we either use regular expressions, haiku, or local model to figure out what to do with it. So zooming out here, we've now given drivers that request tell me what's going on in the morning report. So what's going to happen is Haiku is going to say, okay, let's take a look at Obsidian. Does this exist already? If this is a report that's already on the disk, well, that's something we can very quickly and easy take a look at, read, and respond to. If it does not exist inside Obsidian, well, what's it going to do? Well, it's then going to tell Claude code to create the morning report. Now, again, Haiku is routing it, but Haiku is not going to be the one who executes this. We want a stronger model. So, by default, it will be Opus, but you could change that to Sonnet. And if you're crazy, you could change that to Fable 5 when eventually it comes back. So, if it hasn't been created yet, what are we going to do? We have a headless version of Claw Code. It's like opening up cloud code, but it's invisible and it uses -p. Now, of note, using headless cloud code with -p in about a day or so is not going to pull from your subscription. Okay? It's going to pull from that $200 like additional API credits they give you every single month. Can that be a problem at huge scale? Yes. Which is why you want to do a lot of these things with Sonnet. Is it in reality going to be a problem? I would argue not really. What is the purpose of something like Jarvis? It's to act in this personal assistant like task manager. We aren't building Facebook with Jarvis. You know, if you're actually doing that, you would be hardcore in the terminal. This is personal assistant type things, things for nontechnical team members. At a certain complexity, you wouldn't use this. This isn't the tool for the job. That being said, because of that, is it likely you would run through $200 worth of credits if you're using Sonnet? For the most part, I would argue no. Not a big problem, but something to think about. And again, if that is an issue for you, then just don't use cloud code for this. This is called the Fable 5 OS, but let's be honest, you could replace that with codecs. You could replace this entire thing with local models. You know, it doesn't have to be clouded code. The infrastructure is customizable and can be swapped out with whatever you want. But back to our example, we're saying we wanted the morning report. It wasn't inside Obsidian. So now it's going to spawn a headless version of Claude code to create the report for us. That report then gets uploaded to Obsidian. It reads the report and then it generates a response with that summary. That summary goes to Kakoro. But Cororo is another local open-source model that is going to take the summary transcript that Cloud Code has created and turn that into words, turn that into a voice. Think of it as like a mini 11 Labs on our computer. Then Kakoro is going to say, "Hey, in today's morning report, blah blah blah blah blah." And that goes up to you. The voice that you heard today with Jarvis is from Kakoro. That could be swapped out with any voice you want. So again, local customizable, but that's how this whole thing runs in terms of you ask Jarvis to do something and then that's where the rout goes. So to summarize one more time, as I'm sure many of you are very confused, what happens? You ask Jarvis to do something. That ask needs to be turned into a transcript. Faster whisper does this for free. Once we have the transcript, we need to figure out how do we route this? We either use regular expressions, a cheap haiku model or a local model. From there, we usually need to figure out is this something that already exists in Obsidian or do we need to call on cloud code to generate this report, this request for us. Once it generates what it needs to generate, either it's going to create a report inside Obsidian, or maybe it's an HTML page. Either way, it's going to do what it has to do. It's going to send the response to Kakoro, which turns that into a voice we can hear and that comes back to us. Simple enough. Now, going a step further, everything that's actually going on under the hood. When we say morning report, when we say do skill A, B, and C, what are we actually talking about? Well, we're talking about this. We're talking about the skill architecture that really is the backbone of everything. Because what is a morning report? Well, that could mean anything. What that is, that is a skill. is a skill that is made up of other miniature skills that give me a large report saying, "Go check these sources for this information. Go check these social media pages to get this information, yada yada yada." But like I keep harping on, this skill architecture is only as strong as you make it. And how do we make this? And if you've watched my other videos, you know my spiel on this. What you need to do is we need to figure out a way to take your daily workflows. When I say your daily workflows, what am I saying? I'm saying what do you do dayto-day in your personal life or your business? Like what are these common tasks that are repeated over and over and over? Have you someone at this point who probably knows how to use cloud code? Have you actually sat down with cloud code and said, "Hey, here's what I do every day. Can we break all that stuff out in individual tasks and then can we turn those tasks into skills and if it makes sense, turn those skills into automations." That's how you build a skill architecture like this. And this is where all the power of this lies for example. And what you see here is a lot of what I do and my different skills. Something like content research. Again, most of you aren't creating content, so it'll be something completely different. But the point remains, so what do I do for research? Well, obviously I need to take a look at things like YouTube. And so I turned searching on YouTube for information into something called my YT pipeline skill where it takes a look at YouTube videos, sends them notebook LM, and then gives me summaries. I need to be able to do deep research on certain topics that goes beyond YouTube. that takes a look at other stuff whether that's Twitter, the internet at large, etc. Well, I turn that into an entire customized deep research skill. I have an entire graph rag system with light rag which has a lot of information about what I've done in the past. So, what did I do? I turned that entire query system into a skill on and on and on and on. I then repeated that across all the different domains of my personal and business life, whether that's content, my community, my agency, sales, etc., etc., etc. And in practical terms, how you would do that is quite literally you would just open up claude code and you give it a stream of consciousness saying, "Here's what I do every day." And then you'd be like, "Hey, can we turn those into skills?" And inside of JA plus in the link below, I have like a full script that you can plug in a cloud of code and it will walk you through that if you need it. And to sort of tie that all in above, when we talk about these skills, if you then tell Jarvis, hey, do skill X, Y, and Z. and it goes through the transcription process and the routing. The part where we bring up headless claw code, you know, and it's running this in the background to do something. If what it's doing is just a simple skill, you know, you're going to get an output that's a correct and b consistent because you've already mapped out the process. There's nothing really left up to chance. And anytime we're able to create AI systems that are more deterministic in nature, the better, the less we are subject to just the issues of AI in general, like, well, maybe it will do what I want, maybe it won't, right? When we create skills, we've codified certain things. And so, you take that all together and you have Jarvis, you know, and you can see under the hood, it's a lot more than just like a fancy UI with some metrics that are nice that are just nice to have. There's a lot going on underneath it. And again, the true power of something like this, because it is a web app, it's the fact that we can bundle it and share it with team members and share it with clients. They just have to tell you, if you're the one creating it for them, what they want on the customization side. And the real real power is the whole skill architecture and the fact that you're going to sort of walk them through the codifying of different tasks because then they can sit here or anyone could sit in this chair I'm in right here and get like 80 90% of the power of clawed code in the manner that I use it every day which is these different skills and automations. It's literally a click away from them. That's what you really give them. And then if they want something else, you know, we have the whole voice piece of it. But this in the end is a fancy layer on top of all this. So that's the whole system in the nutshell. I really like it mainly because of the customization of it and the fact that we can add a lot of local stuff. So you can get pretty creative with what it's able to do and what it's able to connect to. Again, nothing stopping you from bringing in more outside sources of something like this like turning it into like a Slack Asia and that sort of thing. But that's where I'm going to leave you with this, guys. If you want again my exact setup inside of Chase A Plus, there's a link to that in the pinned comment. But otherwise, let me know what you thought and I'll see you