WEBVTT 00:00:00.160 --> 00:00:34.740 Anthropic is about to kill OpenClaw with their new remote control release for Claude code. And in today's video, I'm gonna show you how you can start to take advantage of this and build your own coworking agent right now. So if you've been waiting, if you were, you know, deterred from trying out OpenClaw or setting up your personal agent, now is the time to do it because we could do it a lot easier with Claude code. If you've been watching this channel for the past few weeks, you know I was absolutely on the OpenClaw train, And I think what OpenClaw did and what it is doing, uh, was incredibly 00:00:34.740 --> 00:00:36.660 important and groundbreaking 00:00:36.660 --> 00:01:06.760 and deserves a lot of credit for getting us to this point where we're at today. But since day one, I knew, and I'm sure just like a lot of you know, especially anybody who's involved in the AI industry, we all knew that this OpenCloud thing was only gonna last for a period of time until one of the big players likely was always gonna be anthropic. Of course, we're we're gonna come in and just release their own release that that took care of this. And that's because a lot of what OpenCloud does is just built on top of, uh, Claude code or or, um, Anthropix models. 00:01:07.000 --> 00:01:22.015 So, you know, it was just a matter of time before that happened, and it happened sooner rather than later. Right? Before we get into this, ignore the crazy mess behind me. I just moved to a new apartment, so it's still a crazy mess. But I wanted to get in here and do this because it is, uh, super exciting. Alright? 00:01:23.135 --> 00:01:24.655 When it comes to OpenClaw, 00:01:24.900 --> 00:01:58.640 you know, I built it. I loved it. I was using it every day. Still still am right now as I'm experimenting with different ones, but it was a nightmare for many people to set up. There are a ton of bugs. It got annoying. A lot of the times, there were really annoying bugs. So, uh, I was super happy to try this out right away, and it's been, um, you know, a really good experience so far with the new Clogcode remote control. And I built my own system inside of it with my own methodology, so that's what we're gonna do today. You're gonna be building this AI coworking agent. Alright? So if we look here at the screen, we can see the ClawdCode docs 00:01:58.880 --> 00:02:15.615 for this new remote control, which allows you to basically continue a local ClawdCode session from your phone, tablet, or any browser using remote control. So like Anthropic always does, there's a lot of developer heavy language inside of their stuff. So you have to you know, for me and my audience of nondevelopers, 00:02:15.695 --> 00:02:22.440 you have to get past that and think about what this actually means for, like, you know, normal people who are not or nondevelopers. 00:02:22.440 --> 00:02:35.175 Right? And when it comes to this, this literally means that you can speak to your agent through your phone. That's basically you could text your agent through your phone. You can control your agent through your phone, and it's super easy to do this because you can do it right inside of the Claude app now. Alright? 00:02:35.415 --> 00:02:47.510 You see when you start a remote control session on your machine, Claude keeps running locally the entire time, so nothing moves to the cloud. You can work from both, you know, devices or surfaces at once, 00:02:47.750 --> 00:02:50.790 um, and it it works really great. Alright? 00:02:51.590 --> 00:03:20.130 Now there's no one way to set this up when it comes to nondevelopment work, alright, when it comes to setting up your CLOD code folder for nondevelopment work. So what I'm gonna show you and give you is how I do it in my day to day work, my methodology that I have been developing for over a year now that always gets plugged into these new tools, and that is how mine runs. So here, if you see in my folders here, I have a Claude agent. This is what it's gonna look like when we get done building it out. This is the folder that we're gonna be operating inside of with Claude code. 00:03:20.290 --> 00:03:30.215 You could see alright. There's a couple of things going on here. Right? We have the Claude dot m d file, which, you know, you are definitely familiar by now. And this is our behavioral 00:03:30.215 --> 00:03:31.095 instructions. 00:03:31.095 --> 00:03:32.455 Alright? So this is 00:03:33.015 --> 00:04:03.245 you know, you're gonna have all of this written for you when you set it up. I'm gonna give you a complete, uh, you know, prompt that you can paste in the Claude code, and it's going to shoot up like a onboarding wizard that you can build out your entire system. And it's gonna write this MD file for you, but it contains all the behavioral rules inside. Alright? And it tells your system exactly how to run and what to look at. Besides that, the next most important folder we have is the, uh, context folder. Right? And I borrowed a lot of these ideas off of OpenClaw. 00:04:03.245 --> 00:04:10.940 That's what's so great about all these different tools and all these different, you know, open source methods being released is that we can build on top of them. Right? So I combine my, 00:04:11.100 --> 00:04:12.460 you know, own methodology, 00:04:12.460 --> 00:04:17.900 my own techniques with what I could, you know, use from OpenClock. And what we got here now are 00:04:18.140 --> 00:04:37.745 three main context profiles that I have built into my system that your agent is going to read and load up every time. The first is the user dot m d, which if you're familiar with OpenClot, you know you know that is a major part of that. This tells your agent everything about you, uh, who you are, what you do, etcetera. 00:04:38.200 --> 00:04:54.235 Besides that, we have a business .md context profile. This one's super important. This is going to detail your business, you know, everything about your business, whatever it is you do, whatever it is you offer, pricing, etcetera. For me, this is, like, detailing all about my LLC, 00:04:54.235 --> 00:05:06.155 about my content business, about my clients, ghostwriting, etcetera, etcetera, so that my agent always knows what our business environment looks like. And then the third most important one is your ICP or your ideal client profile. 00:05:06.610 --> 00:05:22.825 Other words, your audience, who it is that you're targeting. So, you know, this will depend on what your role is or what your work is for me. For example, in my content businesses, I'm targeting nondevelopers who use AI for work, especially digital writing and stuff like this. So that is all detailed in this ICP as well. Alright? 00:05:23.305 --> 00:05:46.555 Now all three of those get loaded into your agent at every session so that it knows all your context. Besides that, we also borrowed from, uh, OpenClot the memory logs so that your agent keeps logging its own memory, and this gets pushed into its session each time, and then a long term memory as well. Alright? So we're gonna set this entire system up, and you're gonna be able to do this in, like, ten minutes. 00:05:47.195 --> 00:05:56.875 Now besides your context folder, which provides all the context to your agent, we have a couple more things here. We have a review folder, which, of course, this is optional, but I built this in because 00:05:57.755 --> 00:06:00.400 here's the deal. Claude is 00:06:00.560 --> 00:06:10.000 are the Claude code remote controls. If you're familiar with OpenClaw, it's not going to be proactively texting you like OpenClaw would through Telegram or wherever. 00:06:10.240 --> 00:06:51.955 So instead, workaround for this kind of is to create a review folder that every time I'm working with my agent and it finishes something, you know, whether that be a newsletter or a YouTube script or thumbnails or whatever, it is putting all of this inside of a review folder. It's organizing it all, I can open that every day and kinda just work down and review what I want and publish, etcetera. So we have a review folder, and our agents gonna automatically know to put this all of its work inside of a review folder instead of placing it, you know, in final locations. I like to throw everything into a review folder. This keeps everything organized, and then leave it up to me, the human, to actually move it to its final home. Okay? And then lastly, we have, of course, our dot clod folder with our skills inside. 00:06:52.195 --> 00:06:55.155 And the only skill I have in this one is my voice profile, 00:06:55.235 --> 00:07:22.255 which I've talked about a lot of times before. This is one of the most crucial skills you can have for any type of, you know, marketing work, creative work, newsletter writing, digital writing, anything like that. You need to have ghost writing, a voice profile so that Claude can write in your voice or a client's voice, company's voice, etcetera. And then we'll we'll put a bunch of more skills in there over time. Right? But this is what the entire system looks like here. Okay? Now to do this, like, to set this up yourself very easily, 00:07:22.495 --> 00:07:30.920 way easier than OpenCLaw. Right? Like, forget about OpenCLaw. This is so much easier. You're gonna need to have Claude code. Okay? So here on the top, you can see my terminal, 00:07:31.080 --> 00:07:33.000 and you are going to 00:07:33.480 --> 00:07:36.600 launch up Claude code. So we have Claude code here. 00:07:37.160 --> 00:07:37.800 Alright? 00:07:37.960 --> 00:07:41.960 And what you're gonna do is grab the prompt below that's in my substack. 00:07:42.295 --> 00:07:53.415 This is a big, like, 400 line, I think, setup prompt, and this is going to set up the entire onboarding of your system. So if we can see here I don't let me see if I can make this a bit bigger. 00:07:54.230 --> 00:07:59.910 You could see here we have, um, a setup prompt to set up a personal coworking agent. 00:08:00.230 --> 00:08:02.950 Alright? It's going to walk through a bunch of questions. 00:08:03.270 --> 00:08:09.865 It's gonna set up all of your different context profiles. So that business profile, that ICP profile, 00:08:10.105 --> 00:08:11.785 and your user profile, 00:08:12.105 --> 00:08:26.720 this onboarding through ClaudeCode is gonna set it all up for you. You're gonna name your agent. It's gonna build everything in a folder, and then you're gonna be ready to go. Alright? So I'm gonna take this prompt. You're gonna grab this below, and you're just gonna paste this into a fresh new quad code session. Okay? 00:08:27.600 --> 00:08:28.240 Now 00:08:28.560 --> 00:08:34.400 let me I can get rid of this now, make this bigger so we can see everything here. 00:08:35.200 --> 00:08:42.305 Alright. Now if you see once you put this prompt in here, you're gonna get, hey. Welcome to the coworking agent setup. 00:08:42.945 --> 00:09:10.505 I'm gonna walk you through setting up your personal Claude code agent in AI that actually knows who you are, what you do, and who you do it for. By the end of this, you'll have a system that remembers your context every time you open Claude code, and then it's gonna ask you questions. It's gonna ask you questions about yourself, about your business, about your audience. Those are what are gonna set up your context profiles. Then it's gonna ask about your writing voice or if you have a voice DNA skill already, and then it's gonna name your agent and build everything for you ten minutes. Alright? 00:09:11.145 --> 00:10:05.515 First question, it's gonna ask you is right here. It's gonna wanna get to know you, so you're gonna tell it about yourself, share whatever feels relevant, who you are, where you are, time zone, background, what you do for work, what your company is, expertise, how you like to work, how you communicate. These are just some things I threw in there just for ideas, but you can be as detailed as you want about anything that you want your personal agent to know about you. Alright? So, you know, uh, one recommendation I would have is to download something like Whisper Flow so you can use voice dictation here. Hold in your little dictation button and just start rambling for ten five, ten minutes, all about your business, all about everything. You know, just vomit all of that onto the chat and let Claude, your agent, do the work organizing that into a profile. You can also drop documents in there so you have documents about your yourself or biographies, your LinkedIn page, social media, anything like that. You can drop all that in as well. And lastly, if you're like me who already has a bunch of these profiles, 00:10:05.755 --> 00:10:17.115 for example, I had the user dot m d. I have the, uh, business profile. You can just drop that as well. Alright? So that's what I'm gonna do. So I'm gonna grab all my profiles I already have here in the downloads folder 00:10:17.700 --> 00:10:30.020 just because this will also save a bunch of time, but you can go through all of this or you can just drop them if you already have it. So I have a user dot m d already. I'm just gonna drop it, give it to Claude so it's gonna be able to read all of this and understand who I am. 00:10:32.065 --> 00:10:33.665 It's gonna read the file. 00:10:35.185 --> 00:10:46.120 Alright. And now it it finished up here and now it knows about me. It knows who I am. Alex Fron twenty eight based in Sao Paulo. Gotta fix that. I'm not in Sao Paulo, but I am in Brazil. Solo operator, 00:10:46.200 --> 00:11:08.145 expert in AI cowriting systems, ships fast, blah blah blah blah blah. So all sorts of stuff about me it knows now. Okay? Now it's gonna ask about the business. Tell me about your business. This helps me understand what you're building. Alright? Business, I'm just gonna drag my business MD file in here that I already have. This is all about my business. This about my LLC structure. This is about my content business. This is about my service based businesses, 00:11:08.225 --> 00:11:12.065 uh, ghost writing, all of that. It's gonna get all of that context here. Alright? 00:11:12.640 --> 00:11:19.600 Alright. So now it has this. It knows my LLC. It knows what I do. It knows my core product is the co writer system, 00:11:20.080 --> 00:11:21.680 um, my funnel, differentiators, 00:11:22.240 --> 00:11:26.400 plans I have for the future. And then lastly is the audience or the ICP. 00:11:26.400 --> 00:11:35.445 So you're going to, you know, work through that interview with Claude or just drop any documents you have here, and this will close out our context profiles here. 00:11:36.245 --> 00:11:46.440 Alright. So you can see it just finished. We've got all three profiles locked and loaded, ready to go. Here's a quick summary of me. You know, it knows my ICP is nondeveloper professionals. 00:11:46.680 --> 00:11:51.320 Core frustration is seeing Cloud Code's potential, but feels locked out because they're not developers. 00:11:51.480 --> 00:12:21.450 The core shift, primary objections, and some language tips. And then lastly, it's gonna ask for your voice. So it's gonna ask you if you have an existing Claude skill for writing your voice, voice DNA or voice profile, whatever you wanna call it. And if you don't, it's okay too because you can just, you know, skip this part. You can tell you don't have it. And as you communicate with your personal agent, it will learn your communication preferences. Okay? It will learn how you talk, and it'll work on that itself. But I already have a skill, so I'm just gonna drag it in here as well. 00:12:22.250 --> 00:12:29.185 Voice profile. Done. It will recognize this. It needs to be in the format of a skill, which it's already built out for Claude. 00:12:29.265 --> 00:12:33.905 So it will just be able to basically just duplicate that right into our new system. 00:12:34.225 --> 00:12:47.240 And a quick note on this, you can have multiple voice profiles. Right? Maybe you have one for yourself, for various clients. You can explain all of that. The system is completely flexible just like any of other ones, OpenClock, etcetera. You can completely customize this. Alright? 00:12:47.640 --> 00:12:55.145 So it has the full voice profile. And lastly, it's gonna ask for a name. Choose whatever. I'm just gonna put Alex agent for right now, 00:12:55.705 --> 00:13:03.945 and that will name the folder that. So the folder is gonna be named to that. The agent is gonna take on that identity. And then going forward, you're always gonna be working in this folder. Alright? 00:13:04.740 --> 00:13:07.300 Gonna give it permission to now create 00:13:07.300 --> 00:13:09.220 the full directory structure 00:13:09.380 --> 00:13:13.060 for this, uh, system, for this agent. 00:13:13.940 --> 00:13:18.420 Alright. So it took just a couple minutes, and it finished less than ten minutes easily. 00:13:18.875 --> 00:13:33.515 And my coworking agent is now set up. Here's what Claude created. We have an Alex agent folder with everything inside of it. Let's take a look here. When you stop, you could see the Alex agent folder now with the entire system built inside of it. We have the Claude dot m d file. 00:13:34.160 --> 00:13:35.600 We have the, 00:13:36.000 --> 00:13:37.760 uh, context profiles, 00:13:37.760 --> 00:13:38.560 the memory, 00:13:38.800 --> 00:13:52.335 and the review folder with a little welcome in here. Okay? So that is now all built out, and we can actually test it out. So now that this folder is built, you know, this is one way you have to look at building these systems, 00:13:52.495 --> 00:13:54.095 uh, with AI. 00:13:54.175 --> 00:14:10.630 You need to start looking at them as folders. Folders of markdown files, folders of skills folders. Because if you start looking at it that way, then you realize it could be plugged into different platforms. So this same folder, we can use it in regular Clawd code on the app. We can make a few adjustments and use it inside of Cowork. 00:14:10.710 --> 00:14:21.735 We can now use it inside of the remote control app or remote control. And then if you really wanna go out there and say you just really hate Claude, you can also adjust this to work for ant Google anti gravity, 00:14:22.055 --> 00:14:29.495 you know, etcetera. So, uh, now let's test this out though. The first way I wanna show you is just is just that. We're gonna go into the Claude app 00:14:30.020 --> 00:14:41.780 and just test out the system, you know, by itself. We have not even we've not even gotten into the remote control yet, which makes it crazy good. But alright. So we're inside of Claude code now, the desktop 00:14:41.780 --> 00:14:45.140 app, and we have this Alex agent folder opened. 00:14:45.535 --> 00:15:01.480 We're just gonna say, hey there. And you're gonna see it is going to read all the context profiles and know everything about me right away. Alright? And that's how this works. Every session you can see is gonna load up the context. So it's reading my user dot m d, business dot m d, icp. 00:15:01.640 --> 00:15:04.120 Uh, it's reading memory. It's reading, 00:15:04.360 --> 00:15:19.515 uh, the skills the descriptions of skills it has. Here you go. Context loaded. Looks like this is a fresh setup day. System just spun up with your context profiles and voice skill. And then we could work right here inside of Cloud Code. So if you just wanna work like this in this familiar interface, 00:15:19.835 --> 00:15:22.475 you absolutely can. I'm sure eventually. 00:15:23.180 --> 00:15:34.380 Of course, there's gonna be way more features coming here. You'll probably be able to remote control this as well. But if we do wanna use the remote control, we need to use the terminal. Alright? So what we're gonna do here is go back to the terminal, 00:15:35.715 --> 00:15:54.840 and we need to we're gonna terminate this one and start a brand new one. But this time, we wanna open it inside of our folder. Okay? So remember, every time that you're working inside of the folder, that is, you know, the the the agent. That is the system. So here we have Alex agent. I'm gonna open a terminal in this folder, okay, and launch it up. 00:15:55.240 --> 00:16:01.960 And now same situation here. Okay? We have Claude code, but now we have it inside, 00:16:02.040 --> 00:16:09.615 uh, the terminal inside of this folder. And same situation here, we can just say, hey there. Get it all booted up here, 00:16:10.015 --> 00:16:15.615 and then we will move on to the coolest part, which is controlling it from your phone. So it's gonna load up its context. 00:16:15.855 --> 00:16:18.415 Same situation, searching for all the files. 00:16:19.215 --> 00:16:19.615 Alright. 00:16:20.780 --> 00:16:27.740 So now you can see our agent running inside of Cloud Code, the our personal agent, and it's a completely fresh, uh, workspace. 00:16:27.980 --> 00:16:32.060 And to to now enable this remote control, we need to put slash 00:16:32.700 --> 00:16:33.180 remote 00:16:33.705 --> 00:16:46.825 control. Right? You see remote control connect this terminal for remote control sessions. You need to do that. It's gonna connect, and now we can open it from our phone once it's done. So you have a couple ways of doing this. You can follow this URL. 00:16:46.985 --> 00:17:03.580 Uh, you can scan a QR code, and you can also just open up your Claude app on your phone, which is what I'm gonna do here. So you can see my phone opened up here. See, can I make this bigger? No. I can't. This is my phone inside of the Claude the Claude app with the Claude code. And now if we refresh, 00:17:03.995 --> 00:17:06.795 we should be able to see the, uh, 00:17:07.035 --> 00:17:07.995 the new 00:17:08.155 --> 00:17:09.435 the new session. 00:17:09.835 --> 00:17:15.435 Alright. I had to close down the app and refresh, but now that it's refreshed, you could see we have this in progress, 00:17:16.010 --> 00:17:19.450 and then this is our current session. So if you click this here, 00:17:20.170 --> 00:17:30.730 this would be on my phone. Right? I could be away from my computer. I could be anywhere. Now you can see that we're looking at the same thing. So now we're remote controlling it. Same idea if you were using OpenCon stuff and you were using Telegram 00:17:31.145 --> 00:17:35.465 to talk to it. It's the same idea now. I could be at the beach. I could be wherever outside, 00:17:35.545 --> 00:17:44.105 and I could be talking to my agent doing work on my computer here. Right? So if you come here and I'm gonna text it on the phone, you're gonna see it work here in the terminal. So I'm gonna say, 00:17:45.610 --> 00:17:47.210 tell me about myself 00:17:48.010 --> 00:17:48.890 and 00:17:50.490 --> 00:17:51.850 your infrastructure, 00:17:52.890 --> 00:17:54.890 and we'll see what 00:17:54.890 --> 00:18:11.495 it can tell us about itself. Now you can see I typed it here on my phone, and if you look in the left inside of the terminal, I'm not touching it. It's doing it itself. Right? So same idea here. We have now bridged the gap between our, uh, device, our computer, and our phone. We could talk to our agent wherever we go. 00:18:12.150 --> 00:18:28.575 And here you could see it popped up on the terminal, and it's probably gonna take a second to pop up here on the phone. And there it is. You're Alex McFarlane, 28, living in Sao Paulo, Brazil, started writing, blah blah blah. You run your LLC with the co writer system, my infrastructure, 00:18:28.815 --> 00:18:29.775 user.md, 00:18:29.775 --> 00:18:30.815 business.md, 00:18:30.815 --> 00:18:31.855 etcetera, etcetera. 00:18:32.095 --> 00:18:45.560 That's to set up what do you want to build, and now you can start building. You can upload your skills to this folder, all of your Claude skills, your writing systems, your whatever work it is you do, and now you have a personal agent that you can take with you anywhere you go. 00:18:45.960 --> 00:19:04.935 Now before closing this out, a couple main main points, of course, that you should know. First, this terminal needs to be running twenty four seven for you to be talking to it through this remote control. You can shoot up new sessions and stuff, but it's good just to leave this terminal running and then talking to it on your phone, um, to avoid any problems. 00:19:05.335 --> 00:19:16.310 And at least that's from my understanding, this might be this might be different. This might be changed. You can comment below if it's easy to launch up a new session, um, from your phone. And then secondly is, 00:19:16.470 --> 00:19:20.310 I'm running this on my main computer right now, my day to day work computer. 00:19:20.710 --> 00:19:25.350 With OpenClaw, if you know, I literally have OpenClaw running on a completely isolated 00:19:25.795 --> 00:19:35.635 Mac mini. Okay? Um, you know, that that whole hype, I did it, and it wasn't hype. It works really well. I have an a Mac mini dedicated Apple IDs, 00:19:35.635 --> 00:19:36.915 um, emails, 00:19:36.915 --> 00:19:58.795 browser control, everything dedicated to one Mac mini that's clean, doesn't have all my, you know, information on there. And I'm gonna do the same thing now with this Claude code agent. I'm gonna put it on its own Mac mini so I don't have to worry about it messing with my day to day work, deleting anything, you know, it can run, it can control its browser, and I can just keep experimenting without any worries. With that said, it's not necessary. 00:19:58.875 --> 00:20:02.395 It's probably not as necessary as it was with OpenClaw 00:20:02.395 --> 00:20:03.115 because 00:20:03.275 --> 00:20:15.360 without a doubt, you know, there's still risks with this. You need to be careful. It has control of your your system. Anthropic itself says to be careful. But without a doubt, this is miles ahead safer than than OpenClaw, 00:20:15.440 --> 00:20:25.840 um, like, a lot safer than OpenClaw. Right? So that's another important point. Feel free to run this on its isolated device. I would always recommend that. But, also, this is safer to run, you know, regularly 00:20:26.255 --> 00:20:30.495 with some, of course, being smart about it and and careful. 00:20:30.655 --> 00:20:33.135 Thirdly is, as of right now, this can't schedule 00:20:33.375 --> 00:20:34.575 jobs. 00:20:34.575 --> 00:20:42.190 So, for example, on OpenClaw, I was having it text me every day and analyzing my YouTube analytics and giving me a report every day, right, 00:20:42.510 --> 00:20:51.390 at 09:00 in the morning, for example. Uh, Cloud Code agent right here can't do this right now. They did just release for co work a new 00:20:51.995 --> 00:21:01.115 a new feature where you can schedule things, but it's not here for this right now. But, you know, that's okay. I'm sure it's coming at some point. They're pushing this stuff forward every day. 00:21:01.355 --> 00:21:17.430 And that's why I have the review folder here as a workaround so that, for example, instead of it, um, messaging me every day, I can just, you know, have it review certain things or have it carry out certain tasks and drop it in the review, and I can review periodically. 00:21:17.965 --> 00:21:25.485 There's probably workarounds to set up jobs. If you know, uh, let me know. Um, but, yeah, that's that's pretty much it. Um, that's 00:21:25.565 --> 00:21:30.205 that's how you set up your own personal agent with Claude code now using the new remote control. 00:21:30.760 --> 00:21:40.920 Pretty pretty sure in my opinion, OpenClaud dead, done, dead in the water. ClaudeCode will take this over. So go build it out way easier if you're ever scared of OpenClaud, 00:21:41.320 --> 00:21:44.325 you know, now is your time to try it out. And 00:21:44.725 --> 00:21:56.485 as always as always, whenever you have all this hype about these these things coming out, for example, Open Claw, I get into the hype. I follow it because this is what I do. Everything I do revolves around AI. But I tell you all the time, 00:21:57.280 --> 00:22:12.160 don't freak out. Just wait for the stuff to mature because it's not gonna take long. And as you can see, this took, like, less than a month for Claude for Anthropy to come out with their own version of something like this and and working towards this. So all you have to do is wait for it to mature. You're not gonna miss out if you don't want to. 00:22:13.075 --> 00:22:21.795 And lastly, grab that setup prompt, subscribe to my Substack, subscribe to this YouTube. We'll be building a lot inside of here because it's just a lot better than OpenClaw in my opinion.