AI Apps Are Hiding This Secret
45sThe hook promises a hidden secret about AI apps that makes viewers curious to learn more.
▶ Play Clip"Delivers on the promise of showing a better way to use AI, but includes a lengthy sponsor segment and some fluff."
The video demonstrates how to use AI directly in the terminal with tools like Gemini CLI, Claude Code, and OpenCode, arguing that this approach is more powerful and efficient than browser-based AI. The host shows how these tools can manage context, create files, and run multiple agents, ultimately giving users more control over their projects.
The host claims that using AI in the terminal is 10 times more productive than browser-based AI, and that AI companies don't advertise this because it's better.
Browser AI leads to scattered chats, lost context, and messy projects, which the terminal approach solves.
The host installs Gemini CLI on Windows with WSL, using a command, and shows how to log in with a Google account.
The terminal displays '99% context left', which is hidden in the browser, giving users awareness of their context window.
The host asks Gemini to research and compile results into a file, demonstrating that it can read and write files directly.
Using '/context' creates a Gemini.md file that stores project context, allowing new sessions to pick up where previous ones left off.
The host shows how Gemini can be used in a larger project to track status and decisions, avoiding the need to re-explain context.
The host introduces Claude Code, which has features like agents and output styles, and is his preferred tool.
Claude Code can run multiple agents in one terminal, each with its own context window, allowing for parallel tasks.
The host demonstrates creating a custom agent for home lab research, which can be used across projects.
Claude Code can delegate tasks to sub-agents with fresh context windows, keeping the main conversation clean.
The host uses a 'brutal critic' agent to review his video outline, providing harsh but useful feedback.
The host runs multiple agents simultaneously, showing how they work in parallel to complete research tasks.
Terminal AI tools can run in headless mode, allowing them to be used in scripts and combined with other tools.
Claude Code has output styles that control the system prompt and persona, which can be customized per project.
The host uses Gemini, Claude Code, and Codex together on the same project, each with different roles, all sharing the same context files.
All the work and decisions are stored in a folder on the hard drive, making it portable and avoiding vendor lock-in.
The host describes his daily workflow of syncing context files and using agents to manage projects.
The host treats his scripts and project files like code, using Git to track changes and history.
A custom agent summarizes the day's work and updates files, making it easy to resume the next day.
The host uses the brutal critic agent to critique his writing and improve quality, avoiding AI's tendency to be too agreeable.
The host creates custom tools with Claude Code, like a video editor that transcribes and gives notes, feeling like superpowers.
OpenCode is an open-source terminal AI tool that supports multiple models, including local models and Grok for free.
OpenCode can use local models like Llama 3.2, giving users privacy and control.
OpenCode allows switching between models mid-session, and all files remain local.
OpenCode allows sharing sessions via a URL, which is useful for collaboration.
The host encourages viewers to try terminal AI, emphasizing that it's not scary and offers more control.
The video concludes that using AI in the terminal is a game-changer, offering more control, better context management, and powerful features like agents and output styles. The host encourages viewers to try it, highlighting that it's accessible and can be used with free or paid tools.
What is the main advantage of using AI in the terminal compared to the browser?
It gives you more control over context, files, and projects, and allows for features like agents and output styles.
00:14
How do you install Gemini CLI?
Using the command 'curl -fsSL https://gemini.cli.studio/install | bash' or 'brew install gemini-cli'.
01:45
What does the '/context' command do in Gemini CLI?
It creates a context file (Gemini.md) that stores project context, allowing new sessions to pick up where previous ones left off.
04:09
What is the 'brutal critic' agent used for?
It provides harsh but useful feedback on your work, helping to improve quality and avoid AI's tendency to be too agreeable.
12:52
How can you run multiple AI tools on the same project?
By using the same context files (e.g., Gemini.md, Claude.md) and working in the same directory, so they can see each other's work.
18:04
What is the purpose of output styles in Claude Code?
They control the system prompt and persona, allowing you to customize how Claude responds.
16:34
What is OpenCode?
An open-source terminal AI tool that supports multiple models, including local models and Grok for free.
26:29
How can you use local models with OpenCode?
By editing the OpenCode config file to specify a local model like Llama 3.2, and using Ollama to manage models.
27:46
What is the benefit of using Git for your ideas and scripts?
It allows you to track changes and history, making it easy to revert to previous versions if something breaks.
21:44
Terminal AI is 10x better
This is the core claim of the video, setting the stage for why viewers should switch.
00:14Context visibility
The terminal shows context usage, which is hidden in the browser, giving users awareness.
02:58Context files
This feature allows for persistent context across sessions, solving the problem of scattered chats.
04:09Sub-agents with fresh context
This is a powerful feature that allows for parallel tasks without cluttering the main conversation.
11:57Everything is files
This emphasizes portability and avoiding vendor lock-in, a key principle for many users.
19:22Brutal critic for self-improvement
Using AI to critique your work can significantly improve quality, a novel use case.
22:52[00:00] You see each of these apps has a terminal version and they make me 10 times I'm getting so much work done and the AI companies are kind of quiet about this. but here's what they're not telling you.
[00:14] You can use them for everything and it's way better than their apps. I'm about to show you why I'm literally writing this video with these tools once you see AI in the terminal, you're never going back to the browser,
[00:31] but hold up before we go there. I know what you're thinking, Chuck. Do you tell me if this sounds like you because this is how I used to use ai. You're diving deep into a project, can't even see your scroll bar anymore,
[00:48] and this is your fifth chat because chat GBT lost its context or it's mine. wasn't lying and yeah, never works. At this point, your project is a mess. Spread over 20 chats,
[01:03] two deep research sessions and scattered notes. There's a better way to do this. Now we're not going to waste any time we're diving straight into the terminal Put those in your pocket for a second and we'll address those,
[01:15] I want you to try it so you can know it's not really scary. The terminal's a fun place and we're going to play with Gemini CLI first. Why? You heard it free and I'll show you claw code in a second.
[01:28] but they share a lot of the same concepts. Let's just get you going. It doesn't really matter where you launch it. Mac, windows, Linux, I'm going to use Windows with WSL or the Windows subsystem for Linux.
[01:45] so I'll launch my Ubuntu terminal, zoom in so you guys can see, and we'll copy and paste this command installing Google Gemini CLI. Ready, set, never checked our coffee and if you run into a scary issue,
[02:01] you can also use Brew Brew. Install Gemini dash CLI. Now it's installed. Then we'll call it coffee project just like this and let's jump in there.
[02:15] You'll see why I did this here in a second. Type in Gemini. One word. Ready, set, go. We're here now first, Now first thing you'll do is get logged in with your Google account.
[02:31] Everyone has a Google account and yes, this can be a free regular Gmail account. This can open your browser. Sign in and I'm logged in. Now don't be scared. ask it a question like how do I make the best cup of
[02:44] I love the little messages that give us herding digital cats. crafting the guide and then it responds just like we're used to. That wasn't so bad was it? But notice some superpowered things. First of all,
[02:58] the browser doesn't show you this 99% context left. The browser hides it from you and the terminal does not. Also,
[03:10] I really want you to find the best way to make coffee research the top 10 sites, and then compile the results into a document named Best Coffee method.md and then create me a blog plan, just an outline. I'll do the writing ready,
[03:25] Do you want me to write a file for you? Do you want me to create a file for you? Yeah, dude, go for it. This thing can do everything a browser can do, it can read and write files like I'm not copying and pasting this.
[03:41] It's doing it for me. I mean look, it actually made files on our computer. There they are. Best Coffee Method coffee blog. Think about that for a second. all your notes because those are just files sitting there on your hard drive.
[03:53] It can do mostly everything because we broke it out of the browser. Anyways, back to the terminal. If we type in forward slash tools and hit enter, but this feature right here is what made me switch from the browser to the
[04:09] Watch this type in forward slash and it just like that go, It's creating a Gemini MD file and in the process it analyzed our project,
[04:21] read our folder, read our files and yes, go ahead buddy. What it just did there was create instructions for itself, Cat gemini.md and while we didn't do much in this project, it knows,
[04:36] it's going to load that file as its context like let's test it. I'll open up another Gemini session in that same directory. It's using our new gemini.md file and I'll tell it this.
[04:53] Write the intro for blog post one and the coffee series. Look at that. Yep, go ahead buddy. I didn't give it any context, I can just ask Gemini to update that file with my thoughts, research decisions.
[05:11] it added a summary to what we were working on to our gemini.md file. I can close all this. Start up a new session. It picks up where we left off. No re-explaining the context, no starting over, no more 20 scattered chats.
[05:25] you're never paralyzed again. Now when I saw this, I'm like, this is it. I finally have control over my context, my files, my projects. They're right here sitting on my hard drive mine, my precious.
[05:43] This is a small example. Let me show you a big one. It describes how I create project status, major decisions I made,
[05:56] I'll launch a whole new Gemini session in this project and I'll ask you for where we're at in the project. Are you seeing this? use Gemini. It's not even close to the best one. Let's look at CLO code,
[06:14] my daily driver. This one's so crazy. Now, real quick time for a coffee break and a bit of a PSA thanks to our sponsor, Now I'm teaching you and millions of other people how to use AI and the
[06:26] which will also give AI access to your computer and all your files and access to Especially scary if they're a remote employee because not only does your remote employee or just remote person that you give access to your lab or your internal
[06:41] network have access to everything over a traditional VPN if that's what you're because that's normally how traditional VPNs work. their computer has access to everything in the network,
[06:56] This is insane and it's why traditional VPNs are dead or at least should be. meaning they zero trust people connecting to your network and you should zero
[07:10] your employee is given access to nothing unless you explicitly give it. So Beatrice here, she's on the marketing team and given access to the nas, but only the NAS and nothing else and definitely not access to the super secret
[07:24] And Twin Gate takes this to the next level. You can make it to where not just any device can connect to your network and you're out of here because iPhones are clearly better.
[07:41] is required and they have screen lock and a firewall and antivirus and their OS All these checks will happen before they're allowed to connect to your network.
[07:54] This is crazy because it's also free for up to five users. If you're a business, it's a no-brainer, but for like a home laber, you seeing this, And speaking of enterprises, if I create a trusted Windows profile,
[08:09] I can connect this to my CrowdStrike, Intune, Jamf one, whatever EDR or EDMI have and have that tell me if that device is secure or if If you're still using traditional VPN, you're crazy, try out Twin Gate.
[08:25] most secure way to access your home lab or your business network remotely. So go check it out, twin gate.com/network chuck or check the link below, They help make my videos possible. I love my partnership with them. Anyways,
[08:41] which is Claude in the terminal for pretty much everything. It's my default and here's why. It has a feature that changes the game agents. Look at this. I have seven agents performing tasks right now in one terminal.
[08:54] that's just one of the seven features it has that keeps me glued to the If you already pay for Claude Pro, which starts at like 20 bucks a month, you don't have to use API keys. And by the way,
[09:10] cloud Pro is the one I would choose, let's get it installed with one command. I already have it installed.
[09:22] It should tell me that or ask me to do pseudo it yelled at me again, I'm sorry, Just type in Claude and your directory. That's it. Yes, of course. No. Again, don't be afraid. Ask Claude a question.
[09:39] I need to find a NAS for my house. Here's my budget. What I want to do, it does have some fun little messages for us. It'll search the web. It's got this nice TUI terminal user interface. Oh, whoops.
[09:54] Now we're thinking and notice it is security first. We can get past that here in a moment if you're feeling dangerous. I am,
[10:06] If I run that same command slash knit, noticing a trend here and it's doing the same thing, trying to figure out what's what and creating a context file.
[10:21] And also similar to Gemini, we can do something like forward slash context, how much we have left and exactly what's using it. But what's funny with Claude,
[10:33] powerful feature agents, let's make a Claude agent right now. It's really simple. We'll do four slash agents just like this. We'll get a terminal menu and let's create a home lab research expert and I'll
[10:48] Notice it'll ask us where do you want to make it? or personal agents that are tied to everything. You can always call them. We can tell it what we want it to be.
[11:03] Notice you can give it access to tools or restrict access. We'll give it everything. Choose our model sonnets, great auto color. Press enter to save and we'll hit escape to get out of that interface and we
[11:18] I kind of feel like we can just ask Claude to do research for us because we literally just did that. You're right, but watch this. We've used 85,000 tokens.
[11:32] It'll figure it out. I'll have a create a document and I'll say, make sure you reference the research we made. I can just do an at symbol and look at the documents in our directory is the NAS
[11:45] rec folder. There we go. Watch. It's going to use the home lab guru agent. Now here's why this is amazing, actually kind of insane. So Claude was like,
[11:57] I'm going to delegate this task to one of my employees or one of my coworkers, He's like, Hey buddy, are you busy? Here's some work to do.
[12:09] He's giving him a fresh set of instructions and get this a fresh context window. You saw just now we have 200,000 tokens in our context window. That means the conversation we're having right now, me and the main CLA guy,
[12:25] I can give tasks to other sub-agents and never have to leave this conversation. he's ready to go.
[12:37] different purposes. For example, here's my YouTube outline for this video. context window can get pretty big.
[12:52] comprehensive review of my outline. I have a brutal critic agent. I can just deploy. Hey, let's have, I'll just do at and call him. There he is, agent, brutal critic, review my outline. And by the way, this is a fun one.
[13:06] It's designed to just completely roast me according to the framework I have and the scripting goals and it just deploys it. My conversation is still sane, but I have a new energized employee, just got a new sub coffee in hand,
[13:18] go and you can run multiple agents like I showed you at the beginning of this Oh, he's still going. We're going to have the best home lab ever and by the way, we can hit control O to see what he's doing. Oh no, I interrupted him.
[13:36] let's open up a new window, jump into our project, which we still have coffee project. It's okay, it'll figure it out. He knows what's going on and let's run this prompt.
[13:50] We'll launch our home lab agent to research the best proximate servers. Texas, right now and then put it all together in a comprehensive report. Let's go.
[14:05] Now that's doing its stuff right now, deploying new employees over here. I feel so powerful right now. This is so fun. Yeah, they're the three agents go. Of course we got to give it permission to search the web and stuff a lot.
[14:21] I'll show you right now. I'm going to actually interrupt them. I'm going to hit control C to get out of there. Control C twice. previous conversation. Yes, you can do that. And then I'll do dash,
[14:37] dash dangerously, dash skip permissions. We can choose that previous chat we had. Let's do this one here. Yes, I interrupted you. I'm sorry. Go ahead and do it again. And notice right here,
[14:50] bypass permissions on go. Now we're cooking, man. Look at this. Three employees, fresh cups of coffee just going. I'll create another tab because no one can stop us to our project Launch cloud
[15:06] use Gemini for research. Yes, because we can run Gemini and Claude and all these terminal tools in headless mode, meaning you don't jump into a TUI, you just run them with one command.
[15:20] It's like Gemini dash P and then here's your prompt. Find pizza. Create a new agent. I'll give it a basic prompt. You are a research expert.
[15:33] You will use Gemini in headless mode to research. Use it like this. That should do it. It's looking back at our home lab guru. He used 40,000 tokens just himself,
[15:48] We only used 4,000 more tokens for that. It was 85, now we're at 88. Alright, now let's find the best AI terminal videos on YouTube.
[16:00] Use the Gemini research agent We're having an AI use in AI right now. see how they're doing. They're still working man. Alright, it finished up.
[16:18] but this next feature is tied with how awesome agents is and I'm embarrassed to say I just found this out while making this video. Now, cloud code, Cloud code has a feature called output styles.
[16:34] We got a few defaults in here and these essentially control the system prompt for claw code, how it's going to respond to you. The persona it has, Let's create a new one. So I'll go back here,
[16:51] I didn't know that. Let's just be simple. You are a home lab expert designed to help me create the best home lab possible. That's it.
[17:06] If I type in output style, there it is, I can adopt that right now or when I back out and I jump back in. I think it should adopt that style by default. Yes it does.
[17:19] You can create output styles that are tied to just your project or as a whole, I'm using the output style right now to make this video. It's pretty intense. Optimize for what I do. Now, honestly,
[17:34] There are so many features like you can do shift tab to cycle between modes. One of my favorites is planning mode, hit shift tab. There were plan mode on then it just does it like there it is and no keep planning or yes,
[17:52] They have prompts, hooks, custom status lines. I don't just use Claude code, I use Gemini. I use Claude code and I use Codex,
[18:04] Let me show you how Gemini, Claude Code, Chad, BTS, codex. I'm using all three right now to work on this video script. How two steps. they're all using the same context. It's the same project.
[18:21] Let's do that right now. Claude Gemini, the second thing I do is I make sure my context files are all synced up. They all say the same thing. So Gemini, do MD, claw MD and Agents md,
[18:37] They're all the same. any kind of project. Watch this, Write it to Authority Hook md.
[18:54] write it to Discovery hook.md and then I'll have Codex review it. And that's normally what I do. I find chat.
[19:06] BTS very good at analyzing things from a high view. They're all using the same context, different roles. No copying and pasting. They can see each other's work.
[19:22] They're working in the same directory. That's awesome. And it's done. Now are you seeing what's happening here? This is the craziest part about this. Everything I'm doing talking with these three different ais on a project,
[19:36] It's just this folder right here on my hard drive. I can copy and paste that folder anywhere. All the work, all the decisions, Nothing annoys me more than when Chad GBT tries to fence me in.
[19:52] Give me that vendor Lockin. So I can't leave. No, I reject that. I own my context. If a new greater, better AI comes out, I will use all ai, I'll use the best ai. No one could stop me.
[20:07] Leading the browser, going to your terminal, puts you back in control and it gives you better features. I want to show you exactly how I run a project like this.
[20:21] Gemini and agent's files in sync and work on a daily basis using a system like This video was made with this process.
[20:33] Specifically my Claude file, my Gemini file, and my agent's file, So if I get back to my terminal here where I was showing you earlier when we had our hooks developed, Claude made one, made one and Codex critiqued it.
[20:48] I rely on Claude to run my agent. That will close out everything. So I'll just normally do this when I'm done for the day. I'll go, Hey, run and I'll mention my agent script session closer.
[21:03] This is one of those agents I keep as a personal agent. I use it for many projects and these agents are just files. They're files inside an agent's folder. I'll cat that file here,
[21:15] but some of the key things it does, I'm going to go and run the agent. We did some stuff, didn't we? everything we did and do a comprehensive summary.
[21:28] It'll then update a session summary file that's specific to just updating what It'll see if any core project files need to be updated. File Claude Gemini agents and then this is probably my favorite part.
[21:44] So normally you would use Git for code for writing and deploying code. I treat my scripts and pretty much every project I work on in my life like code,
[21:57] give a reason for that change so I can see a history of what I did and why I did it. Maybe something breaks, I can go back to that change and reinstate it. That's the power of using GitHub with all your ideas.
[22:11] Now this is killer for me because I'm really bad at documentation. but now I have this help me keep track of things. and my mind is fried, I'm like, okay, tell you what, I'm done. Close this out.
[22:27] It will look through all this stuff. It will figure out where I'm at, end the day where I need to be and then I can start fresh the next day and be like, Hey, where are we at? What are we working on? They can tell me, Hey Chuck,
[22:40] go for it. That's it. The syncing is probably my favorite part. No, no,
[22:52] actually this thing's my favorite part. How it roasts me. I use them to critique me and make me better. So here are my critics. These guys are so stinking mean and I designed them to be they're agents.
[23:07] So I had an issue where my AI was being way too agreeable. I'd write something and be like, oh Chuck, best thing you ever wrote. I'm like, ah, you're gaslighting me. Stop it. I wanted something to be super mean.
[23:20] I knew it. It was good and that's what this thing does. So actually I'm curious if my script right now is any good. I actually have not used it yet on this, which I normally don't do. It's bad.
[23:34] Let's see. I'll say use the brutal critic to absolutely roast and verify my stuff is good and this script, everything's a file local here on my file system.
[23:48] I mean you can just move so quickly and nimbly when you have a system like this what I love about this is while I've been talking with this AI for a minute, If I asked that session to review me,
[24:02] about. I don't want that. I want a fresh cup of coffee credit coming in, going, here's what I know network Chuck needs to have and I'm going to roast his
[24:14] Notice it was really quick editor free stream on that. describe how I create and describe what my thing is, who my audience is. Again,
[24:28] I don't copy and paste. I got context already here. You can reference that. I wouldn't stop telling my wife about it and she was going crazy. Whenever he talks to me, it just goes in one ear and out the other.
[24:42] I'm actually really scared about what it's going to say. Oh no. Okay, let's see what it said, said when I fix it, it'll be good. What did it tell me? Oh, it's an 8.2. It's not bad. Now I forgot I did this.
[24:58] The brutal critic has three personalities or three people that come in and roast I don't like this. I'm not sure I agree with this. We'll see. five to 8% retention drop, which means you'll stop watching.
[25:15] We're currently in segment four. Jump there if you want to. I don't care. but seriously doing stuff like this saves me hours. Now also,
[25:27] I'm doing the writing because I like to keep that. I think that's important now with ai, but I do have AI roast me, I might make some really bad creative decisions that aren't in line with what
[25:41] the point I want to hit home is that I made this for me. This is my own personal software, exactly my use case. you're trying to make happen and this is just one tool I've made.
[25:57] That crazy project I showed you in the beginning was running like seven agents. This is a custom built project just with claw code and I'm going to use it right it's going to transcribe it, read it, and give my editors notes.
[26:13] Hey Chuck repeated himself 17 times in the fourth video and it's a disaster. the tools I create are so powerful for me. I wake up every day feeling like I have superpowers. I want this for you. Now,
[26:29] There's a tool that's actually open source. Now you can use any model you want with this open source alternative and it You also get grok free,
[26:42] your cloud Pro subscription and use it like cloud code. Let's play with it. I'll have all these commands below installing. That was quick and that's it.
[26:56] If I can just launch open code, just type it in like this. That does it. Oh, let me do a source because it edits to my bash RC file. You might have to do this too. Source bash rc.
[27:08] Now let's try it. You can open and close your terminal and do the same thing. Oh, we're here. This is open code. A nice two E terminal user interface. They launched this straight into grok code Fast one.
[27:20] They have a deal with grok AI that allows you to use this for free for a while, so same story. Hey, GR code's helping us even knows like, Hey, can I help you with your coffee project? No mask stuff.
[27:34] I'm going to exit out. We can use local models. This is the killer part. but we have to edit a file talking about nano and I think it's inside
[27:46] that's the directory and then I think the file has to be open code let's do llama 3.2. I think that's what have installed. We'll find out.
[28:01] I'll save that. Let see llama list, see what my models are. Do I have 3.2? I'll pull it down if I don't, what did I break? Lemme fix that file real quick. There we go.
[28:17] I should be able to go forward slash model and change to LAMA 3.2. I can log into cloud with this command, open code auth login.
[28:32] I can choose Aaro with my cloud pro and I'll launch this browser, I just launch open code now and switch models to cloud
[28:47] all our files are local. It doesn't matter what tool we use. It's all ours right here. I can switch models midway. Let's go back to gro. Cool, what's our next step? Cool. While it's doing that,
[29:02] There's models to Claude. I can do sessions, these are my past sessions.
[29:14] We can also share these sessions slash share and watch this. the URL is copied in my clipboard, so I can go to my browser, paste that URL in and I can, I mean, look at that. That's awesome. Wait,
[29:29] is it live? You can share your session with people. That's pretty neat. We can jump back in time and restore. I want that in real life. That's awesome. We can also,
[29:46] if I jump out of there and do open code help, You can attach to headless servers. Export your session is JSO data.
[29:58] I mean this tool is pretty cool and the fact that you can log in and use your that's next level because otherwise you're putting in an API key and you're What's fun is I've been following these guys on Twitter before they started
[30:13] So how do you feel about your browser based gooey AI now? Pretty bad, right? I never know how to say it because now you can control your context.
[30:25] that chat window and don't let the terminal scare you. I mean, If you can get past that, this tool is for everyone. I'm going to make my kids use this. I dunno about my wife.
[30:41] nothing is stopping you from trying this right now. Jim and I see a lie. You can run local models if you're worried about that and while cloud code is paid, it's overpowered, like you saw all those features. I use that every day.
[30:54] It's awesome. do you want to go even deeper? You can add tools, I made a video about doing MCP servers here. You can add it to all these.
[31:11] have you hacked the YouTube algorithm today? Let's make sure you do hit that light button. Subscribe, comment. and also let me know which is your favorite terminal AI tool or if you even
[31:27] care. I'm curious, do you care about this? Because I care a lot, obviously. Tell me below. Yeah, that's it for real. Hey, I like to reserve for praying for you. You are a person. Well,
[31:43] I don't know if you're a person, this is for you. You have a life, You're watching this video because you want to learn something new. This may not be your thing. Totally cool. You can click off, that's fine.
[31:58] The reason I'm doing this is because I do believe in the power of prayer. The reason I do anything on this channel to help people or all the things I'm He's empowered me to do everything I'm doing and I don't know what your beliefs
[32:13] are on that regardless, I just want to pray for you. That's it. I thank you that they are excited about tech and their lives and wanting
[32:25] to do something cool. Otherwise, why would they be here? I pray that you would just fill them with joy about the future that you remove any anxiety that you give them peace that you would bless their families and
[32:38] their lives right now that are really hard, divorce or just any kind of sin that's really bogging them down, Jesus,
[32:51] I pray deliverance over them right now that you give them a path forward and I pray you go before them and make their path straight, God, that you would create opportunities for them and that they would take these
[33:05] skills they're learning and do something really fun and cool with them that will God, and ultimately I pray that all of this will lead them to maybe one day just
[33:18] knowing you more deeply, knowing you better, and knowing that having a relationship with you is the greatest gift, that there's nothing greater you can attain apart from knowing you. Jesus,
[33:31] I thank you for this person and I just thank you for this community and for letting us do this cool stuff. It's a privilege. In Jesus name I pray. Amen. Alright, thanks guys. I'll see you in the next one.
⚡ Saved you 0h 33m reading this? Transcribe any YouTube video for free — no signup needed.