The Ultimate Beginner's Guide to Claude Code

There is an incredible piece of software called Claude Code that I've been using for the last three months and it has completely and utterly changed my life. And this video is the video that I'm sending to my friends, my family, my team members who have not yet started using Claude Code. Maybe you're like me a few months ago where you were intimidated by the thought of typing stuff into a terminal. Maybe you're intimidated by the name Claude Code. You're like, oh, but I'm not a coder. I'm not a developer. I couldn't possibly use Claude Code. Maybe you're still stuck in that paradigm of talking to ChatGPT or Claude on the web app and thinking that that is all AI has to offer. Or maybe you're like a lot of people I know and you're like, man, I know I should get into this Claude Code thing or this Claude Code work thing. I just don't really have the time. Hopefully this video will help you solve all that. And this video is going to introduce you to the idea of the AI flywheel. You basically get AI to interview you about what you're doing in your business, your life, your work. Based on that, you get the AI to suggest what cool things you can use the AI to help build that would help save you time and make you more money. And then in the process of getting AI to build those things for you, you are also learning about how the AI works. The more you learn about how the AI works, the more that feeds into giving you ideas. It's like you're getting a firmware update in your brain where now you know what's possible, which means you can then build even more things to help save you time and make you more money. Using these sick AI features, I've built stuff for my business and for my customers that literally add value to our customers every single day, where people are raving about the tools that I've managed to build for them over the last couple of months just by learning how to use Claude Code. The final thing to say before we get into the video is that every single day, the gap between the people that just use the free version of ChatGPT and talk to it on the web versus people that know how to build stuff using Claude Code, even if you don't know how to code. Every single day, that gap is getting wider and wider. And what I hope this video will do is give you a sort of beginner's guide on how to narrow that gap. There are timestamps to everything down below in the video. So let's get started. Okay, so there are a couple of prerequisites that will really help you if you have these downloaded before we try doing this stuff. The first thing is you do not want to be using the web app for something like Claude. Instead, you want to download the desktop app. This is totally free, but when you download the Claw desktop app, you will notice it says chat, which is the thing that you are used to. It also says co-work, which sounds somewhat scary if you haven't used it before. And it says code, which sounds... even scarier if you haven't used it before. The second thing you want to do is you do not want to type. You want to have some kind of dictation software installed that does a speech to text. There are lots of these. In my case, the one I use is called Whisperflow. I'll put an affiliate link or something in the video description if you are interested. And the cool thing about Whisperflow is I can hit FN spacebar and then I can say whatever I want and then it will appear on screen within like milliseconds. Boom. This is how it works. This is a far quicker way of speaking to an AI rather than having to type to an AI. And those are basically the only two prerequisites you need. So step number one is we're going to ask AI what we should build with AI. I'm trying to learn how to use AI. My current AI skill set is I just use ChatGPT and Claude and use the chat feature. But I recently watched a video that tells me about code work and how Claude code is the best thing ever. So to that end, I wanna learn how to use AI, but I don't wanna just randomly try and learn how to use AI by following tutorials. I actually wanna build something that's really useful in my work or in my life. The problem is I'm not really sure what to build. So I want you to ask me questions and interview me and help me figure out within the context of my work, like I wanna build something that'll save me time meaningfully or help me make more money in the context of my business. And in the process, I wanna sort of learn how to use things like Claude Cowork and Claude Code as well. Okay, so my business actually does... I guess I would say three main things. Firstly, we do content. So I have a YouTube channel and I post stuff on Instagram and occasionally stuff on LinkedIn. And the content is trying to sort of help people build a life they love and sort of change their lives and stuff, personal development things. The second thing the business does is we have an online business school called the Lifestyle Business Academy that helps people start and grow. six-figure lifestyle businesses and then the third thing that we do is that we are building various software products we've built an app called voice pal which is a sort of ai ghostwriter we're building an app called super focus which is a sort of productivity thing and we are building an app called a platform called creator grid which is a platform to help creators grow and monetize their audience Now, obviously, all of this is in the context of me owning a business and doing various different things. But in the context of you maybe having your own job, then you can ask it to interview you about what you do in your job if you are trying to go for a raise or just trying to improve your job performance or anything like that. Actually, you know, one thing that I wish I didn't have to do or I wish that my team didn't have to do is that we do a lot of data scraping. So, for example, for YouTube, for Instagram, for LinkedIn, we spend... you know my team spends a lot of time each week looking at analytics and looking at view counts and adding up saves and uh impressions and stuff and then some of that data we need to send to sponsors some of it we use to figure out whether our own social media stuff is going well we also need to do this across our competitors i mean i don't really think of them as competitors i think of them as colleagues but we want to keep an eye on what our sort of friends in the space are doing so that if someone is growing particularly fast or hits on a format that is particularly good, then we can experiment with that format ourselves. And so all of this stuff takes actually many, many hours for my team every single week. So I wonder if there's some cool stuff we can build that will help us automate some of that. Do you think that would be possible? 100% possible, and honestly, this is a great candidate because it ticks both boxes. It's genuinely painful, hours per week of manual work, and it's the kind of thing where you'll learn a ton by building it. Now, this is good. This is asking me really, really useful questions about how we can automate this data collection process. I'm not going to read all the responses. You can pause the video whenever you like just to read the stuff because... I know you can read. Okay, so the current workflow, it's like, yeah, Nicole on my team and Becky on my team literally goes to YouTube Studio or to Instagram Analytics. Basically, they go to Instagram Insights, they write down numbers, and they manually write the numbers into a Google Sheet and then use the sum function to sort of count up impressions this week or something. To be honest, I actually don't know what's available on Instagram Insights. Maybe they don't have to do that anymore. But either way, it's a manual process of copying and pasting numbers into a Google Sheet. Second, how many of these colleagues are you tracking? Are we talking five channels or 50? More like 50. 50 on YouTube, 50 on Instagram, 50 on LinkedIn, that sort of thing. And what does the output look like? It sort of goes into a Google Sheet, but then it sort of goes on random Notion pages that are all over the place. It very rarely goes into slide decks, but yeah, primarily Google Sheets and Notion databases. That's where it goes once it's collected. And then, you know, we always think, oh, it'd be nice if we looked at it more often, but then because it's all over the place, it's kind of hard to look at more often. In reality, what we often do is just chuck it into AI and be like, hey, can you give us some interesting insights? But I think it's the collection of the data itself that like is kind of annoying. You know what? Let's not worry about the sponsor thing. I think let's just focus on the competitor tracking. And what do I want to know? I think, yeah, it's how many views did the recent videos get? It is also what topics are performing well for them. I mean, if we could get a sense of, like if we're thinking about YouTube, I never want to watch the video itself because I don't want to accidentally copy it, but I'm very interested in what the title and the thumbnail was. And if we're thinking about Instagram reels, I, you know, in a dream world, we'd be able to transcribe the reel to get the hook because I'm always interested in what's the first line. But if it's an Instagram carousel, like what was the format? So yeah, the challenge with Instagram is that we've got all these different formats. So yeah, I just don't really know how we would go about that. All right, so this is telling me we're going to start with YouTube. It's the easiest to win. YouTube has a public API where you can pull videos, titles, thumbnails, viewpoints, publish dates for any public channel. You give it 50 channel names and it gives you back everything you want. That's your week one project. Sick. Instagram is harder but doable. Meta's API is more locked down, so we'll need to get a bit more creative here. Here's what I imagine. You open a dashboard, could be a webpage, and you see something like, here are the 50 channels I track, here are the last 10 videos sorted by views, and here's what's popping off this week. That sounds great. You can see thumbnails and titles at a glance without watching anything, and you can have AI automatically tag the topic so you can spot patterns, like three of my colleagues posted about morning routines this week, and they did well. Sick. The beautiful thing is that this is a perfect project for learning clawed code, because it involves real API calls, real data processing, and optionally a real front end, but none of it is so complex that you'll get stuck for days. Does that sound like the right thing to focus on? And do you have a preference for what the output looks like? Would you rather see a nice looking dashboard you open in a browser, or would you rather just automatically update a Google sheet that your team uses? This is so sick. Like, man. Even me reading this back right now, I'm like, wow, Claude has such a good understanding of what I'm trying to do, what I'm trying to build. It's suggesting things that I didn't even think of. What a time to be alive that you can literally ask the AI to... build stuff for you and also teach you how to build the stuff in the process like in the past i paid thousands of thousands of dollars for like you know automation consultants to ask us these sorts of questions to figure out what we can automate in the business and none of what they've said of the 50 000 or so dollars that we've paid to automation companies and automation agencies and consulting whatever people comes close to the level of clarity that claude just got through just a handful of exchanges with me. This is incredible. Now once you get good at using AI to build all these different features that are going to help you save you time and make more money, what you might need is a web host. You might need a place to host the various programs that you're creating and stick them on a website and make them accessible via the web either to you personally or to you and your team or even to the public if you want to like make money from the thing. This is where Hostinger comes in who are very kindly sponsoring this video. Now Hostinger has a bunch of different features that are all super helpful if you are trying to build a business or just improve your life in general. The first one is Hostinger Horizons. This is basically an all-in-one AI website. builder, you basically just describe whatever you want, and Hostinger Horizons will basically code up the app entirely for you. It'll build you a fully working, mobile-friendly web app with absolutely no coding required. And just by talking to it, you can refine things like the content and the colors and the functionality. They've even integrated features that handle user logins behind the scenes in a super easy way, and also billing through something like Stripes. You can even start charging people for the various different web apps that you create. When you're ready to go live, it's just one click, and then you get a domain, you get your email, and you get your web hosting all included as part of the package. In addition to Horizons, there's also the Hostinger VPS service that lets you host a virtual private server, which if you're doing particularly fancy stuff with Claude Code or with OpenClaw, with things like that, you can host it directly on Hostinger. Domains are included with all of the Horizon plans, and you also get free hosting included with the annual plans. Plus, they have a 30-day money-back guarantee, so there's genuinely no risk in actually just giving it a go. So if you want to turn your idea into a real business, head over to hostinger.com slash aliabdal, and you can get 10% off if you use the code aliabdal at checkout as well. But thank you again, Hostinger Horizons, for sponsoring this video, and let's get back to it. Now, at this point, there's also something super interesting that I would love to talk about here. So I happen to know what an API is, I think. But if I didn't know what an API was, it's like my rule for the AI stuff is anytime I don't understand something, what do I do? I ask Claude to explain it to me. Okay, this sounds really cool. But one of the key things I want to do is I want to understand the foundations and the philosophy and, you know... I'm even interested in like history, you know, the history of stuff like this. So when you say API, what does an API actually mean? Can you help me understand what an API is, why it's useful, and how did APIs get developed? Like why are they a thing in the first place? So this sort of thing is how for the last two months, I have felt like every single day I'm learning so much about the world. I'm learning about the history of computing. I'm learning about the history of technology. I'm learning about like random stuff because when something interesting happens and Claude Code or Claude Cowork or Claude or GPT Codex or whatever is asking me to build something or it's running a terminal command that I don't understand. While it's doing the thing, I will just open a separate window and I'll ask it to teach me about the history of the thing. For example, when I was installing OpenClaw and I was trying to do some security audits on it and I was really trying to understand what does SSH mean and how does the terminal work and what's a secure shell and stuff. And I ended up sort of spending half an hour going down a rabbit hole of like understanding the history of like the telegraph and how the telegraph morphed into Morse code and how Morse code then became like telephone lines and how like the US military in the Cold War was worried that like, you know, the telephone exchanges would get bombed by the Soviets. And so they had to figure out this method of information interchange that involved like packets. And so the packets was invented. And that was then this protocol called TCP IP, which was then the precursor for like HTTP, which was the precursor for the World Wide Web. And then when the World Wide Web was invented, there was all these people getting hacked. And there was this student, I think in some university in Poland or something, he was pissed off that his like, university got hacked and so he like coded up this thing called ssh which was like a secure way of transmitting information across packets and then this guy ended up trying to over commercialize it and so someone else made this thing called open ssh which became like a free platform and then this is encryption and public and private keys and all of this sort of stuff and now when i'm typing in ssh dot dot dot into my terminal i know what that means and i can appreciate the history behind it and i can appreciate why it was such a big deal and how it was invented it's just so cool oh and claude is just again really good at explaining stuff Let's go to the problem before APIs existed. Imagine it's 2005. You're building a website and you want to show a map on it. Before APIs, you had two options. Build your own mapping system from scratch. Insane. Or literally take a screenshot of MapQuest and paste it into your page. I don't know what MapQuest is. I might ask it about it. This was the fundamental problem. Software was like a series of walled cities. Each application has its own data locked inside of it, and if you wanted to use that data in your own thing, you had to either recreate it yourself, or do something gross, like write a script that pretends to be a human clicking buttons and scraping the screen. People actually did this, and it was as fragile as it sounds. YouTube changes one pixel on their page, and your whole system breaks. So what actually is an API? API stands for Application Programming Interface, but that name is honestly unhelpful. Here's a better way to think about it. So good. Again, this is the flywheel idea. AI is helping me figure out what to build. In the process of figuring out how to build it, I'm also learning about stuff, so I'm not just blindly writing commands into a terminal and hoping for the best, I'm actually increasing my understanding of it. The reason it's useful to understand this stuff rather than just blindly do it is because when you start understanding these things, it's like you get a firmware update in your own brain, which means even if you don't really care about the history of computing because you don't find it interesting, it's still useful for you to know what an API is and what HTTP requests are because the fact that you now know that those things exist means that you might realize, wait a minute, huh? There's this program that I use in my work called Blablabla. I wonder if they have an API. You Google, does Blablabla have an API? And if you weren't familiar with the word API, you wouldn't have known that you could even ask that question. And then you might find, no, it doesn't have an API, but it does have an MCP server. Now, if you are not at all curious, and you're a total dumbass, and you don't then pull on that thread, you're like, MCP server, oh, it sounds technical. I don't care. But if you're an intelligent person, you would think, huh, MCP server. I think I've heard of that, but I don't really know anything about it. What's an MCP server, Claude? And you understand what an MCP server is, and you realize, wait a minute, there's all these other ideas for things that I could build that will help me save time and make more money that involve MCP servers. Could I build my own MCP server? What about my own MCP client? Okay, that's super interesting. And you start to learn this stuff without even trying to learn the stuff. Like, you never had to sit down and watch a tutorial about, like, what the hell is an MCP server and how does it work? But purely by exercising your curiosity and pulling on the string of, like, huh, APIs are cool, does... Notion have an API. It does, but it also has an MCP server. Oh, that's cool. Like, what's an MCP server? Oh, sick. It's a way for, like, AI things to chat to each other, and it was invented by Anthropic back in, like, 2024 or something. Like, sick. Now, basically, everything has an MCP server, and you can even build your own. Sick. That just gives me so many ideas for, like, other things that I can build with my stuff. Now, we're about to dive into the rabbit hole of Claude Code, which is the tool that I've been spending most... most of my time on practically 24-7 for the last like two months. It's absolutely sick. I was intimidated by Claude Code because it involved the terminal. I was like, oh my God, terminal. I'm not like something hacker from the 1990s. Why don't you use the terminal? And then I realized I was a total fucking dumbass for thinking that. And actually, it's really straightforward, especially if you ask Claude to explain to you how to use Claude Code. And then once you're in Claude Code, you ask Claude Code to explain to you how to use itself, which is freaking sick. But before we do that, we have... dived down into this thing around trying to scrape Instagram and YouTube competitors for social media management. Unless you're a social media manager or your job or your business involves social media in some way, that specific use case is probably not relevant to you. Obviously, because you're an intelligent person, you know that I'm using that use case as an example, and you know that you could obviously just ask Claude to interview you about your own use cases, and it will help you figure out what you should build for your own stuff. But just for the sake of opening your brain up with more examples, I want to tell you a little bit about some of the other tools that I've basically built for my business and my life over the last two months. If you want to skip this bit in the video because you don't care and you just want to get to the Claude Code stuff, there'll be a timestamp, as is the case for every other thing in this video. And in fact, to make this list, I'm going to ask one of my OpenClaw agents. OpenClaw is kind of like Claude Code on steroids. Open Claw for the last like two months as well. If you're just getting started with this stuff, I won't worry about it. I would start off with Claude Cowork or Claude Code initially, and then you can dabble around with Open Claw if you feel like it. But let me tell you about my various Open Claw agents. I have Albus, who is my primary Open Claw agent. This is what Albus looks like. I have Hermione, who is my curriculum architect for our Lifestyle Business Academy. She's the one who helps me basically think through all the different things that we are teaching our students and do research on like what's currently working in the world of building an online business in 2026, et cetera, et cetera. This is what she looks like. I have Minova, who is the vice principal of the Lifestyle Business Academy, and she helps with all of the operational things associated with trying to give our students the best experience to build their six-figure lifestyle businesses. And then Minova, along with Claude Code, essentially helps me build automations that make our lives and our students' lives a lot easier. Next, we have Remus, who is my content buddy. So Remus is who I talk to when I'm on Telegram to get content ideas, and he's the one who helps build out all of these competitor analysis, like dashboards and stuff that we're doing in addition to Claude Code. We have Dobby, who is my general assistant that runs on a very cheap anthropic model called Haiku, whereas all the others run on Sonnet or Opus, and so they're a bit more expensive. So Dobby is like my cheap personal assistant. We have Cedric, who's like my relationships coach. And so I talked to Cedric, and he does research around like homeschooling and like, you know, gives me ideas for like romantic date nights with my wife and stuff like that. So that's cool. And then recently, I added Kaladin, who is my health coach. And so Kaladin tracks my protein intake every day. And he's also my workout buddy when I'm at the gym. He's got access to all of my DEXA scans. all of my like workout history which i exported from the app strong for like for the last like five years and so he knows exactly where my lifts are at he knows that i had like a i broke my arm recently i had a left radial head fracture he knows that he therefore has to modify the exercises based on that and so when i'm at the gym because currently my personal trainer is on holiday so while i'm at the gym kaladin is my personal trainer i'm talking to kaladin to figure out what lifts i should do any modifications i need to make if like my groin hurts while doing squats kaladin will tell me to back off and like do another exercise instead this sort of thing if you're like whoa how is any of this possible then don't worry about it just like stop using AI to teach you what you want to build using AI that improves your business life or saves you time or makes you money. And then the process of learning stuff. And then at some point you can ask Claude being like, hey, I watched an Ali Bell video where he talked about having these like eight different OpenClaw agents that he talks to on Telegram. How does that work? What's up with that? And then Claude will teach you about the stuff. You'll realize that there's a bunch of security risks that you have to be aware of when you are using something like OpenClaw more so than when you're using something like Claude Code, even though Claude Code does have some security concerns. Again, you can just ask Claude about, hey, I've heard that Claude Code has some security concerns. What's up with that? Like, what are the security concerns? Why is it a big deal? Et cetera, et cetera. You'll learn about things like prompt injection and how to protect yourself against it. And you'll learn that there are skills that you can download for Claude that things like DCG, which is like the destructive command guard that like physically stops it from doing anything that might like delete the files on your computer or anything like that. If you're like, whoa, holy shit, you're telling me it can delete the files on my computer? Yes. If you do not sensible things with these powerful tools, it can result in bad stuff happening, but that's why you sort of wanna do it one bit at a time. You wanna make sure you understand what is happening rather than just blindly let the AI agent just like do whatever it wants. So with that digression, I was actually gonna ask Elvis. Yo, Elvis, I'm actually working on a YouTube video where I explain how to learn AI in a weekend. And for the last two months that we've been building stuff using OpenClaw and using Clawed code, can you just give me a list of real business and life use cases that... we have built in our setup that I can show my lovely viewers on YouTube as an example of what we've built. For each one, I just want a quick one-liner. All right, so here's an example of all of the stuff that I've built using Claude Code over the last two months. Firstly, a support ticket pipeline. So within a Lifestyle Business Academy, we have 200 support channels for all of our students, because currently we have about 200 students. And each student has their own private Slack channel where they get added to a Slack channel with themselves. and like me and their coach and like Angus and various other team members where they can post anything they want and we aim to get back to them within like 24 hours ideally. Now previously this was a manual process of like the coaches having to keep on top of like which Slack channel is unread and which one is read and then if a student's replying in a thread you can't see the notifications, you can't see the messages and so what I created in Claude Code is this thing that like automatically creates like support tickets anytime a student messages us in Slack and so that's available in a dashboard and also pings alerts to a sort of private Slack channel that we have in the team which says that hey John Smith posted this support request. It's about to be 24 hours. Someone please reply to him. You know, that kind of idea. On top of that, I created a web interface that the coaches can log into so they can see which Slack channels for which students need responses. And so they're able to then just click a button. It takes them directly to Slack and they can respond to the student there and then. I created a handful of student facing Slack bots. So the problem we were having is that previously we were giving our students a bunch of custom GPTs. Like we created custom GPTs for things like niche generation and first draft offer creation and like content and like giving them feedback on their sales calls and things like that. But the problem we found with custom GPTs is that we couldn't actually see how the students were interacting with the custom GPTs. It was kind of annoying because then I couldn't audit other custom GPTs actually giving the students useful advice. And then the students were coming up with all these things and I was like, wait a minute, where did you get that from? And they got it from the custom GPT and then I can't see like where things went wrong with the custom GPT. And on top of that, we had students who were like complaining that we have like too many... platforms like, you know, some stuff is on Google Docs, some stuff is on Slack. There's a lot happening on Slack. We've got the course on Circle and now they have to have an open AI account and do stuff in a custom GPT. And I said to Claude Code, like, is it possible that we can recreate the functionality of a custom GPT within a Slack bot so that if students are on Slack anyway, they're just able to message the bot and get the same kind of stuff. But then we as the coaching team have access to the conversation so we can see, we can sort of like audit the agents and make sure they're doing sensible things. And so over the course of about a weekend, I coded all of this up using Claude Code, using Python servers, making sure that we have everything in a database that is SOC 2 compliant, so like enterprise level security, so that we don't accidentally leak any conversations that students are having. And so we created a bunch of Slack bots that students have been engaging with and they're having a great time talking to. For example, there is Dumbledore, the DM agent. And so we've had over 100 of our students send thousands and thousands of messages to Dumbledore, the Slack bot. And Dumbledore has been trained on our internal DM methodology for how to convert a cold prospect into a warm lead and get them on a sales call so that they can grow their business. And so students are copying and pasting LinkedIn profiles of their prospects into Dumbledore, and Dumbledore is helping them craft outreach messages. If a student is in a DM conversation with a prospect and they're struggling to turn it into a call, they'll just screenshot the conversation, stick it into Dumbledore, and Dumbledore will give them advice based on our Connect, Understand, Invite framework, for example. So we have Dumbledore, the DM agent. We have Lupin, the LinkedIn agent. We have Sprout, the sales agent. By the time this video comes out, we'll have released Flitwick, who's like the delight agent that helps students like craft a delightful customer experience for their coaching or consulting or service business. And I'm working on a bunch more, which is super exciting. But the really cool thing about this is that the students can give us feedback. I can see the stats on how much people are interacting with these agents. I can literally read the conversations that students are having with the agents. We do flag it to them that like I can read the conversation. So I read the conversations to see like, are the agents giving students sensible advice? And so if you use Slack in your business or in your work, then did you know you can ask CloudCode to help you figure out what Slack bots you can create that make your life easier. We have another Slack bot that's like, you know, alerts us at the start of every day to see like, you know, in terms of like our competitors on YouTube, like who has released videos and what's been their like views in the last 24 hours. So we'll see that, you know, Homozi recently released a video called whatever, whatever, whatever. And that's got 94,000 views in the last 24 hours. And that's like an outlier for Alex Homozi's channels. So then it prompts us to think, huh, could we like take inspiration from the fact that that video is popping off for Homozi. And the thing that I'm working on now is a sort of creator HQ, which is a sort of web dashboard that me and my entire team can use across YouTube, Instagram, LinkedIn, and TikTok, and Twitter that automatically analyzes all of the content that we've put out over the last like nine years on these platforms, figures out what are the things that worked, what are the things that didn't work, generates content ideas based on transcripts from stuff that I've said when I've done workshops for our students in LBA, automatically tracks all of the competitors, and then it helps us surface ideas for better content that we can make that. will just perform better. And on top of that, I've also created my own MCP server, which then Claude and ChatGPT have access to, which means that they can automatically see all of the projects that I'm working on within the business, what my goals are, all of the outstanding to-dos, any kind of journal items that I've put in there because I wanted to have access to that. And so now anytime I talk to Claude AI, the chat, it now has way more context about me than it ever did before. And that context is always up to date because I'm keeping it up to date when I'm using Claude code, when I'm using OpenClaude, when I'm using Claude, and it all happens through an MCP server. Now that might have been a lot of jargon. I did not know what any of this stuff meant two months ago until I decided to spend a weekend really just trying to build something useful using code code. And over the last two months, like every day, as I've done this learning loop, this sort of AI flywheel, I've built more and more things. And there is a danger with all this AI stuff that you end up in this zone where you spend so long building agents that talk to other agents and that help you orchestrate other agents that you don't actually end up... doing anything useful. Useful I would define as it adds value to your customers, it saves you time personally, it makes you money personally. And so I was very mindful of that, that I didn't want this to be another one of those people spending days making Notion setups to theoretically try and be more productive, but not actually being more productive. So going back to our data analytics project for YouTube competitors. Yes, okay, I'm now ready to start writing this thing. Can you help me understand what the hell Claude Code actually is? um i don't really have a background in coding and so i have been intimidated by claude code in the past you know when people when i see people using the terminal with like the black and the green text it feels like there's some hackers out of the matrix and i feel like i'm not tech savvy enough to use called code can you help me figure this out okay let's kill the intimidation now The terminal is not what you think it is. That black screen with the green text, let's demystify it, because before we talk about Claude Code, you need to understand the terminal, because Claude Code runs inside it. Here's the thing, you already know how to use a computer using a graphical user interface, a GUI. You see icons, you click buttons, you drag things around. Mac OS, Windows, your phone, all graphical user interfaces. But GUIs weren't always there. Before 1984, when Apple released the Macintosh, virtually all computers were operated by typing commands. You'd type something like ls to see a list of files, or cd documents to go into your documents folder. That's it. That's the terminal. It is a way of talking to your computer by typing instead of clicking. The terminal didn't go away when GUI's arrived. It just got hidden. On your Mac right now, there's an app called Terminal. This is what it looks like. Boom. There we go. I think on the Mac, by default, it's white with black text rather than black with white text, but whatever. It's basically the same thing. You can type whatever you want. If you open it, you're looking at the exact same computer, the exact same files, the exact same everything. You're just steering with a keyboard instead of a mouse. Think of it like driving. A GUI is an automatic car. The computer handles a lot of the details for you. The terminal is a manual. Same car, same road, same destination. You just have more direct control. And for certain tasks, like the one we're about to build, the terminal is actually way faster and simpler than clicking through menus. So what is Claude code specifically? You know how when you use Claude in the chat, you type a message and Claude responds? Yes. Claude code is the same Claude, the same brain. But instead of living in a browser window, it lives in your terminal. And here's the key difference. It can actually do things on your computer. When you chat with Claude on Claude.ai, it can give you code, but then you'll have to figure out where to put it, how to run it, what to install. You are the middleman. Claude tells you what to do, and you do it. However, Claude code removes the middleman. You say, build me a script that pulls YouTube data for these 50 channels, and Claude code will actually create the files, write the code, run it, see the errors, fix the errors, and run it again, all right there on your machine. You're sitting next to it watching and you can steer it. No, not like that. Do it this way. But you're not doing the mechanical work of copying and pasting code between windows. Oh, this is nice. A concrete analogy. A regular Claude is like texting an architect. They send you blueprints and you have to figure out how to build the house yourself. Claude code is like having that architect standing in the room with a toolkit. They're actually building the thing. You're watching and you're saying, actually move that wall over there and they just do it. Why? It feels like hacking, but isn't. The matrix aesthetic of the terminal is genuinely misleading. When you use Claude code, most of what you're doing is just talking to it in plain English. You type things like, can you create a new project folder for my YouTube tracker? And it just goes and does it. It'll ask you questions if it's unsure. It'll show you what it's about to do before it does it. You can say yes or no. It's a conversation just like this one, except the AI can actually touch your files. Amazing. Like, you didn't need to watch a tutorial to teach you how to do this. All you needed was ask Claude to explain what Claude code is. And now you can ask it, be like, OK, how do I install it? OK, this sounds really cool. How do I install it? You can download it using the desktop app if the terminal feels scary, or you can type in one command in the terminal. OK, so on a Mac, open the terminal app, hit command space, type terminal, hit enter, then paste the single command, curl-fssl, claw.air slash install.shsh. So this is now where it starts to feel like coding. It feels like hacking. It feels like, oh my god, this is intimidating. But super simple thing. I'm going to copy this. Explain to me what the hell is going on here before I do it. Please, dot, dot, dot. You don't have to do this with every single terminal command, but it's a good habit to understand the code that the machine is trying to run on your machine. Good instinct. You should never paste something into a terminal without understanding what it does. Let me break down every single piece. Reading left to right curl. This is a program that's been on basically every computer since 1998. The name stands for client URL. All it does is fetch stuff from the internet. You give it a web address, it downloads whatever's there. It's like a browser, but instead of displaying a pretty web page, it just grabs the raw content. FSSL. These are four flags squished together. Flags are like settings that modify how to command behaves. Fail cleanly, silent, still show errors, follow redirects. Oh, okay. So FSSL together means download this quietly, follow any redirects, and only talk to me if something goes wrong. Claude.ai slash install.sh is a web address, points to a file on an anthropic service. If you're curious, you can actually open that URL in your browser and read the script before running it. Huh, okay. Let's do that. Oh, nice. It's just like some text stuff. And if we wanted to, we could try and like copy and paste this text into Claude and get it to help us explain every single line. To me, that's a little bit overkill. In general, there does come a point where you do in fact have to trust the thing that you are interacting with. Now, in my case, I trust Anthropic, I trust Claude, I trust that they're not gonna do dumb things on my computer because they're like a $400 billion company and it would just be dumb for them to like... put malicious software on my own computer. You might think differently. If you have major distrust of like big corporations, then you are very welcome to go through this line by line and make sure that every single command that's running on your computer, you understand what's going on, you audit it, validate it, make sure it's legit. But like, you know, we all trust big corporations. You probably have a Google account. You probably trust Google with your emails, with your maps, with whatever. You probably have an Apple account. You probably trust Apple with your private photos of like your friends and your family and yourself. Yes, there are security concerns with a lot of this stuff. And if you're downloading a random plugin from some random developer that you've never heard of, then you want to have a higher threshold for like being skeptical or being like security conscious about that. But if you're downloading like the official Claude Code app, from Anthropix website directly, where you can verify that it is in fact on Anthropix website. Calibrate it to your level of risk. The nice thing is you can be as security conscious or as cavalier as you like. In my case, I started out very, very, very security conscious about every little thing, make sure I understand every single command. And then I sort of realized, okay, this is like overly cautious, especially when I'm interacting with local files where it doesn't involve talking to like, you know, customer data or anything like that. I sort of lower my bar for like how much... I think about the security side of things. But as soon as it involves interaction with customer data, that's when I'm like, all right, let's lock down the security walls around this and make sure that what I'm doing is legit. But you can decide how security conscious to be or not. You were right to ask. This pattern of download a script and immediately run it is super common for installing developer tools, but it does require trust. You're saying, I trust that whatever Anthropic has put at that URL is safe to run on my computer. In this case, it's Anthropic, a major AI company, so that trust is reasonable. But as a general rule, never run a command like this from a source you don't trust. Exactly. Great, so then once you've installed Claude, you literally just type in Claude into your terminal, and look what happens. Accessing workspace, uses Aridal. Is this a project you created or one you trust, like your own code or work from your team? So yes, I trust this folder. Great, now you'll see. This doesn't look scary anymore. This doesn't feel like you're trying to hack away in a black and green terminal. Welcome back, Ali. There's a little icon. Opus 4.5, Claude Team, Sparkle Studios. Hello. What the hell is going on here? Coalescing. Oh, God. Please run login. Okay, I need to log in to my Claude account. Let me do that. Great. I would like to connect to Sparkle Studios, which is the name of my business. Yes, I'm happy for it to do stuff. Great. Login successful. Press Enter to continue. Wonderful. Hello. What the hell is going on here? Boom. Hey, you're in Claude code. Anthropics command line interface for Claude. Your login was successful. I can help you with software engineering tasks like writing, debugging, or explaining Claude, navigating and understanding code bases, running commands and managing files, answering technical questions. What can I help you with? We basically have Claude. running inside the terminal that is able to then access files and do stuff on our computer with our permission, crucially. You might be thinking, oh my God, there's all sorts of security concerns here. Ah, I'm so scared about it deleting all my files. If that's the case, actually, you know what? Let's talk to Claude Code. Hey, so this is the first time that I've actually installed Claude Code and I am a little scared. I'm worried about the security implications of having an AI that can touch my files and potentially delete everything on my computer. Can you help me understand what is going on? Totally fair concern. Giving an AI access to your file system is a big deal. Here's what you should know. You're in control. I ask for permission before running commands or editing files. You see exactly what I'm about to do and can approve or deny it. You can configure how strict the permission system is. Commands run in a sandbox by default. This limits what shell commands can do. If you don't know what that means, you just ask Claude, what is a sandbox? What are shell commands? I can't access files outside your working directory without you navigating there. Destructive git commands, like git reset hard, require explicit approval. If you're like, what the fuck is a git command? You can just ask Claude, what is a git command? How does it work? Then you're going to go in a rabbit hole to understand that git is this thing that was created by Linus Torvalds, the inventor of Linux back in the day, because he wanted a better versioning control system compared to having document one, document two, document three, v5 final, v6 final, et cetera, et cetera. So git is this open source thing that's on. that you can install in basically any computer that basically creates a snapshot of files so that if anything goes wrong, you can just revert to the previous version of the file. You might not have known that, but you do now because you're not a dumbass and you know that if you... Claude tells you something involving security on your computer that you do not understand. You just do a little bit of research by asking it to explain it to you. And it will do a really good job of explaining it to you in a very engaging way. What I can't do without you seeing. Delete files, run arbitrary shell commands. What's a shell command? I don't know. Let me ask Claude. Push code to remote repos. What the fuck is a repo? I don't know. Let me ask Claude. Install packages. What's a package? I mean, let's ask Claude. Practical tips. Start in a test project or Git repo so you can revert changes. What's a Git repo? I don't know. Let's ask Claude. Watch the permission prompts. They'll show you exactly what will happen. Type help to see the available commands and settings. the honest truth very ai i'm a powerful tool and with great power comes the need for you to pay attention to what you're approving but the system is designed so you always have visibility and veto power want me to walk through a simple example so you can see how the permission flow works oh yes please it's so helpful i love it watch what happens when i attempt this create file claude code test.txt hello this is a test file created by claude code you approved this action which is why it exists feel free to delete me do you want to create claude code test.txt I can say yes. Yes, allow all edits during the session, i.e. I'm just giving it blanket permission to create files and edit files. Might want to not do that initially if you're new to this sort of stuff. Let's say yes. Terminal would like to access files in documents folder. Sure, that's fine. So even the Mac is giving me an additional security prompt before doing this. So here we go. Right. ClaudeCodeTest.txt. Wrote four lines to ClaudeCodeTest.txt. You should have seen a permissions prompt before that went through showing you the exact file I wanted to create and the full contents of what I wanted to write. You approved it, so now the file exists. Let me read it back to you to show that it works. Read one file. Notice that reading didn't require a permission prompt. It's a non-destructive action, so it just happens. Now let's clean up. Watch the permission prompt again. Okay, so bashRM uses a little bit of alcohol code test or txt. Delete the test file we just created. Now, you might be thinking, what the hell does bashRM mean? And so this is where, especially when it starts to say delete stuff, this is where I would recommend copying the command. pasting it into another Claude window or even a chat GPT window. If you're like, wait a minute, I'm using Claude to tell me about the security settings in Claude. What if the AI goes fucking rogue and like misleads me? If you want, you can use a different AI to do the security audit on the AI that you're using. But again, I broadly trust Anthropic. Let's go into Claude and be like, okay. I'm using Claude code for the first time and it's trying to run this command. What does this actually mean? What is bash? What is RM? I know that I now know because I took the time to understand what is bash and what is rm that oh all it's asking me to do is it's asking for permission to just delete that one file rm r some folder it's deleting a whole folder and everything inside it dash r means recursive go into every subfolder and delete everything still fine if it's a folder that Claude Code just created and then we have the famous command the one that everyone worries about rm rf slash this will attempt to delete your entire computer Nobody should ever run this. Claude Code won't suggest it, but I'm mentioning it so you understand the spectrum. The key habit to build. Whenever Claude Code asks permission to run a bash command, read it. Most of the time, it will be harmless things like creating folders, running code, or installing packages. But rm is the one where you should always glance at what it's removing before you approve it. What does the full command say after rm? I can tell you whether it's safe to approve. I know it's safe to approve, but just for the sake of the argument, I'm going to copy and paste. This is the command. And so then it's going to tell me. Totally safe. It's deleting a single test file called ClaudeCodeTest in your home folder. That's almost certainly a file that ClaudeCode itself created a moment ago to test that it could write files on your machine, and now it's cleaning up after itself. Think of it like someone checking does the pen work by scribbling on a scrap of paper and then throwing the scrap away. Go ahead and approve it. Okay. Oh my god, it's scary. Done. Here's what you just experienced. Action. Write a new file. Yes, you saw the content first. Read a file. No. Permission needed? No, it's non-destructive. Delete a file via bash. Permission needed? Yes, you saw the command first. The key takeaway, you are always in the loop for anything that modifies your system. If you ever see something remotely sketchy in a permission prompt, just deny it. Feel more comfortable now? Any questions about how this works? Mate, our AI overlords are very good at helping us feel good about the commands and the permissions that we are allowing them to have to run stuff on our machines. This is pretty cool. So now what you basically have is, yes, you can chat to Claude via Claude.ai or Claude Chat, but once you have it on your computer, on your terminal, you can also literally talk to Claude Code via your terminal. It's just that the terminal version gives you the option, with your permission, to access your files and add files and remove files. That one's you've got to be careful about and be able to write code, be able to run code. Whereas the Claude Chat, It can still create websites and PowerPoint presentations, but it does it in a web browser. So you have to download the file or it wouldn't be able to actually run a web application for you because you'd have to run it on your computer. So it's sort of like Claude Chat is like, hey, I've got the ability to do all these things, but I can't actually touch your files. Everything just happens in a web browser within Claude.ai. But Claude Code is like, hey, I've got all those powers as well, but I can also make files directly on your computer. Okay, so now I've installed Claude Code. Where do we go from here? Like, how do I build this YouTube competitor analysis dashboard situation that we were talking about? Okay, here's where it gets fun. Three steps before you start talking to Claude Code. Create a project folder. In your terminal, you want to create a dedicated folder for this project. Think of it like creating a new folder in your desktop via the terminal. So I could do MECDR, which means make a directory. It creates a folder. CD means change directory. Then start Claude Code inside that folder. That sounds interesting. Let's just do that. So I'm going to go on my terminal. I'm gonna get rid of Claude Code. I happen to know that you use Control-C to exit out of Claude Code. If I didn't know that, I would ask Claude Code. So now I've exited Claude Code, and I'm now back within the terminal, interacting with my computer directly. So what I could do is I could go on my desktop, I can right-click, I can do New Folder, and I could call it YouTube Tracker. Then I can open the folder YouTube Tracker, and you know how this works. You know how to create a folder on a desktop because you know how to use a computer, obviously. So that would be the manual GUI, Graphical User Interface, way of creating that particular folder. Let's delete that now. But I can do the same thing from the terminal itself. I can use McDer, so let's go in the terminal, and type in McDer YouTube Tracker. I can hit enter, and it looks like nothing has happened, but if I look inside my home folder, turns out there is now a new folder called YouTube Tracker. I was able to run a command from the terminal. The terminal understood what I'm trying to do, and it created the folder for me. Sick. So now it's like CD YouTube Tracker. Okay, let's copy and paste that. Let me make sure I understand what it means. CD means change directory. Okay, yeah, that seems fairly harmless. Boom. And you'll notice that it's gone from Ali Abdaala, Ali's Micro Pro 3 with this little wavy symbol. What's this wavy symbol called? Let me ask Claude. It is called tilde. Okay, fine. So previously we were running commands in my home folder, Ali Abdaala, which is shorthanded via this tilde command, as I've just found out from Claude. And now we are inside the folder YouTube tracker. So then it's telling me, now start Claude code inside that folder by just typing in Claude. Okay, I just typed in Claude. Oh, nice. Accessing workspace, YouTube tracker. Yes, I trust this folder. It's got nothing in it because I just created it. And now I am running Claude code within the context of this YouTube tracker folder. Next step, get a YouTube API key. Oh, God, this is going to be complicated. Remember how to set API supplier entrance, the API key is access bridge. You should need to know who's making the request. We want to use it. The key is free. Google just wants you to register. So go to consolecloud.google.com. Create a new project, search for the data API, go to credentials and create an API key. It takes about three minutes. And then step three, tell Cloud Code what to build. This is the magic part. Once you're inside Cloud Code in your project folder, you literally just describe what you want in plain English. This is like super cool. So I could literally say, I want to build a YouTube competitor tracker. I have a list of about 50 YouTube channel names. I want a script that uses the YouTube data API to pull the 10 latest videos from each channel, including title, thumbnail, URL, view count, and publish date. Store the results in a local JSON file for now. Here's my API key. Let's start with just three channels to test. And then Claude Code will start building. It'll create files, it'll write the code, and probably run it to test. You'll see it asking for permissions along the way. Can I create this file? Can I run this command? And you just approve each step. Caveat, you want to understand what it's doing before you approve the step. And then over time, you'll realize that you'll start to get a feel of what you need to worry about versus what you don't. My suggestion, start tiny. Don't try and build the whole dashboard in one go. Start with just three channels. Get the data pulling working. Look at the output. Then say, okay, now can you make this into a simple web page where I can see the thumbnails and titles in a grid? And layer it up from there. The beauty of Claude Code is that you can iterate in conversation. Actually, can you solve my views? Can you add a column for how old the video is? Can you highlight anything over a million views? You are steering. Cloud code is building. That's the workflow. Again, a digression. It's not really a digression. It is relevant. One of the things that really holds people back from running this AI flywheel is encountering friction and being unwilling to figure it out. Developers don't have this problem. When you're a software developer, you encounter friction all the time. You encounter a bug and the bug shows that something's not working. You try and connect to an API and you realize that the API documentation is out of date. Back in the day, the skill of being a good developer was knowing what to Google. Because it's like knowing what error you Google and what you copy and paste into Google to then go on a website called Stack Overflow, which is like a forum where developers are discussing how to fix things and then figuring out what the fix is that someone else has done and then trying to run it on your machine and seeing if the fix is still valid. And if you're a very good developer and you're good to the developer community, you would then update the Stack Overflow forum. post with what the latest version of the fix is. These days, you don't actually need to do the Google Stack Overflow thing because you can just copy and paste an error message into Claude and it will tell you exactly what to do and then all this sort of stuff. So developers are naturally good at pushing through friction. Most people who are not developers in the context of their work have probably not encountered technical friction unless you're in a particularly technical role. You might have encountered human friction, like what do you do when your boss refuses your annual leave request and then you have to figure it out. But when it comes to doing stuff like this, you will encounter some technical friction. And the thing that will separate you from your grandma is that you are going to be willing to push through the technical friction and figure it out. So getting API keys from platforms is an example of technical friction that in particular with like Google projects is a little annoying and it's a little... it can be a little hard to get your head around. But I trust you, you're intelligent, you will be able to figure this out. And if you can't figure it out, again, you have Claude, you have ChatGPT that you can just copy and paste stuff into to figure it out for you. So let's get a YouTube API key. So go to console.cloud.google.com. Okay, yeah, open link. Create a new project, call it YouTube tracker or whatever. How the frick do I create a new project? Ah, ah, ah, friction, friction. Google Cloud. Okay, maybe if I click here, new project. Ah, fuck. How do I create a new project? I don't know. Ah, complicated. Oh my God. Complicated. Okay. We're going to calm down. We're going to relax. And I'm going to ask Claude. Yo, Claude, I'm on the Google Cloud Console thing, but I can't see a button to create a new project. What the frick do I do? Google Cloud Console is not the most intuitive interface in the world. Let me look up the current layout so I don't send you on a wild goose chase. Thank you, Claude. Very kind. Yeah, Google Cloud Console is notoriously confusing. Here's exactly where to look. At medium, the top of the page. What the fuck does that mean? Click the button directly. Okay. Ah, okay. So if I click on that, I can then type in new project. YouTube tracker test. Okay, yeah, that's fine. Notifications. Create project YouTube tracker test. Okay, cool. Great. Let me click select project. Ah, okay. I just saw YouTube tracker test. You're now incurring charges in your billing account. Uh-oh. That's probably fine. Set up Google Cloud for your organization. Ah, ah, ah. I don't know what any of this stuff means. What are we gonna do? We're gonna ask Claude. So. This is what I like to do whenever I want a page where I have no freaking clue what's going on. I command A, command C, copy, stick it into Claude, help me understand what the fuck is going on on this page, dot, dot, dot. I literally just copied and pasted the entire contents of the website, chucked it into Claude, and now Claude's gonna explain it to me. Hopefully Claude is gonna say, you don't need to worry about it, bro. Like, let's just build your YouTube tracker. But I actually did this many a time. I was setting up Cloudflare, I was setting up like a database thing, making sure it's secure, and... Sometimes the instructions Claude gives are out of date because Cloudflare, which is the security provider, might have changed the way their interface looks. And so I would just end up copying and pasting the contents of the page, or screenshotting it, chucking it into Claude, and then asking Claude, what do I click on? Again, we need to be good at pushing through technical friction if we find it. And then the friction will disappear over time, and it will just become a part of your usual skill set that if something doesn't work first time, you figure out why it didn't work, and you do something about it. Deep breath. You can ignore almost everything on this page. Thank you, Claude. What's happening? Google Cloud Console is designed for enterprise companies running massive infrastructure. Think Netflix deploying thousands of servers or banks processing millions of transactions. So when you create a project, Google assumes you might want to set up Terraform, infrastructure automation, because that billing alert, security policies, identity management, and all this other stuff that huge companies need. You need literally none of that. You are here to get one API key so you can pull some YouTube video data. It's like walking into a car dealership to buy a bicycle and they're trying to sell you fleet insurance. That's quite funny. The good news. Now, you can see it says now viewing project YouTube tracker test at the bottom, which means your project is already created. You're done with that step. Okay, now do this. Look at the left sidebar. Hamburger menu in the top left. Click on APIs and services. Ah, sick. I clicked on APIs and services. Click library. Okay. Ah, love it. I love it when the instructions that the AI gives me actually matches what I see on screen. It doesn't always happen. This is the friction that sometimes you have to go through. Library, okay. In the search bar, type YouTube data API v3. YouTube data API v3. Oh, sick. Nice. The YouTube data vpi is an API that drives access to YouTube data such as videos, playlists, and channels. Sick. Click the result, then hit enable. Nah, it can't be that easy. Can it? Enable. Surely not. That would be too easy for dealing with some Google Cloud stuff. Okay, what's happening now? Okay. Stuff is happening. Ah, okay. Chill out. Let's go back to Claude. Once it's enabled, go back to APIs and services credentials. Okay, well, APIs and services credentials. Okay. Click create credentials API key. Okay. Create credentials API key. Okay. Because BigQuery, oh my God, oh shit. You're like, do I need to use a service account or not? Like what the hell is a service account? Et cetera, et cetera. Like, ah, application restrictions. What should I do? Website. This was my life 10 years ago when I was building my first coding projects back in 2015. I built like this sort of online question bank for medical students. This was the first business that I built that did reasonably well. I say reasonably well. It got to like six figures in revenue and then I sold it a little bit later. But now you just copy and paste all of it into Claude and it. helps you understand it directly. You know what, I'm just gonna copy and paste all of this. It's giving me all these options. What do I type in where, dot, dot, dot. Classic Google, over-complicating things again. Here's what to do. Name, type something like YouTube tracker. This is just a label for your reference so you remember the keys for. Okay, YouTube tracker, thank you. APIs that can be accessed using the key. Where it says API restrictions, click restrict key and then find YouTube data v3. Okay, cool. Okay, that's fine. Everything else, ignore it, thank you. Don't touch application restrictions. Don't trust the service account thing. Don't worry about our websites, IP address, Android apps, iOS, no this applies. Just give it a name, restrict it to data, API v3, hit create, et cetera, blah, blah, blah. It'll show you a long strings of characters. Copy that immediately and paste it somewhere safe. Okay, don't share this key publicly. Don't paste it in a YouTube video. Don't commit it to a public repo. It's like a password. It's tied to your Google account. If someone else gets it, they could use up your free API quota. For the video you're filming, you want to blur it or cut away when it's on screen. Note to editors, please, can you do that? Okay, so I hit create. Great. Now it's given me an API key. I'm going to copy it. Once you've got the key copied, come back and it'll fire up code code and start building. I've got it copied. What do I do next? If you're still with me in the video, this is actually what the process looks like. It's just how it works. And it might seem intimidating right now, but honestly, just give it a day, give it a weekend, and play around with it. Push through the friction. I promise your life will frickin' change. So now... We open our terminal, run these three commands. MakeDirect for YouTubeTracker, CD YouTubeTracker, and Claude. Okay, so I've already done that, actually. Great, so I'm in YouTubeTracker, I'm running Claude. Okay, once Claude Claude code is running, you'll see the prompt paste something like this. I want to build a YouTube MetaTracker, et cetera, et cetera. Let's just copy and paste it. You'll see pasted text lines one to nine. My API key is, and I'm gonna use the keyboard thing here. Then just hit enter and watch it work. Two tips for your first time. Don't try to be perfect with your prompt. You can always say, actually, can you change X afterwards? That's the whole point. It's a conversation, not a one shot. and read what it's doing, even if you don't fully understand the code. I agree. You'll start picking up patterns naturally. And if you see something you're curious about, just ask it. Hey, what does this line do? Write their own code code. OK. So we can see this is what code code is now doing. And I'm like, fingers crossed, what's going to happen? Let's see. Let's see. Listing one directory. OK, yeah. Empty directory. Let me build a tracker, a Python script to fetch data in an HTML page to display it. If I didn't know what Python was, or what HTML was, again, I would just be like, copy into paste. What does this mean? Oh, shit, now there's all this code. Oh my god, intimidating. It's fine, it's fine, it's fine, we don't need to worry about it. Okay, so it's creating a file, fetchvideos.py. Fetch latest videos from YouTube channels using the data API v3. Okay, they're doing all of this stuff, they're writing all this code, API key, base URL, channels, . Cool. Okay, at this point, This will feel like friction, and so people will stop doing it because they'll be intimidated by the fact that it's writing code. The trick is to not get intimidated by the fact that it's writing code. It's only code. If you want, you can look through it line by line and try and understand what the code does. Would I recommend that? Well, I mean, you can do it. It generally is good practice to understand what broadly the code is doing that you're writing on your computer. To be honest, often the way that Claude Code and Codex and these other AI tools like write code, it actually is somewhat human readable. So let's see what's going on here. You'll see that it's even explaining. Fetch latest videos from YouTube channels using the data API v3. Import all of this stuff. It's... Okay, whatever that means. It's setting an API key, base URL, channels, yeah, videos for channel 10. Yeah, I understand what that means. Def API get point. Ah, so then I'm like, huh, this is a comment. Make a get request to the YouTube data API. Okay, so it's doing that. Then find a channel name. Search for a channel name by idea and return its idea and its actual title. Okay, yeah, that seems reasonable. Like, often... As you're browsing code, you don't need to understand what every single line of the code does, but the AI will usually do a good job, and this is what good developers do as well, of commenting the code as they go along. So it'll help someone reading the code further down the line understand the gist of what the code is trying to do. Okay, cool, search for a channel. Get the uploads playlist for each of the channels. Yep, that makes sense. Get the latest video ideas from a playlist. Okay, yeah, that makes sense. Get the full details for a list of video ideas. Okay, okay, okay. Yep, all of this stuff. Sort the videos by view count ascending. Okay, so do I want to create this file? Well, I'm just creating a file. I'm not actually running it yet, so let me just take yes. If I wanted to, I could copy and paste it into Claude and be like, hey, can you explain every single line of the code? The nice thing about Claude Code is that it'll give you little tips for using Claude Code as you go along, like use slash btw to ask a quick side question without interrupting Claude's current work. I use that a lot. Or, I mean, you can just Command Tab into Claude Chat and just ask the questions there. That's usually what I do, to be honest. I get Claude Code to build the stuff, and I use Claude Chat to help me understand things as it's building stuff. Okay, now we're running a bash command. Let's allow it to run the command. Okay, so it's running the command. FetchVideos.py. Let's see what happens. Fetching Aliobzal. Fetching Thomas Frank. Plus five lines. Control O to expand. Huh, what happens if I do Control O? That doesn't matter. All 30 videos are fetched. Okay, now it's going to ask me for more commission. Bash command. Preview top five videos by view count. By view count. At this point, I'm like, okay, I'm just going to proceed because that seems reasonable. Let me verify the data looks good. Working perfectly, here's what was built. Fetchvideos.py. Hits the YouTube data API, pulls the latest 10 videos from each channels. Searches for the channel name, gets it uploads, blah, blah, blah. Index.html, dark themed grid display that reads videos.json. Shows thumbnail, title, view count, badge, channel name, time ago, et cetera, et cetera. Oh, interesting. To view the HTML page, open it via a local server needed for the fetch call to load JSON. Python 3 M HTTP server 8000. Then open localhost in your browser. What would you like to add next? Now I'm like, OK, this is confusing. What the hell is going on here? So I'm going to, you know what? I don't even need to copy and paste it. Wait. Help me understand what this command does. What's a local server? The first time you try creating an HTTP server and running things on localhost, you might be confused as to what the hell's going on. If you just ask it to explain it to you, you'll understand, oh, this is what a local server is. And then you won't need to worry about it again. Good question. Let me break it down simply. The problem, when you double click index.html to open it in a browser, The page tries to load videos.json using JavaScript's fetch. Browsers block this for security reasons when opening files directly from your computer. You know what? Let's test this. If I go on Finder, ah, when I look in my YouTube tracker folder, I see three files. I see fetchvideos.py, I see index.html, and I see videos.json. Turns out I can actually open all these files and I can verify what's going on. So if I open this with, I don't know, like text edit or something, oh, sick. This was the code that Claude wrote for me. OK, nice. If I look at index.html, I can open it in a code reader and I can read like, okay, there's all this HTML code, whatever. And then I can look at videos.json, I can open it with text edit, hopefully that'll load. I can see, oh, it's basically just data. Video ID, title, thumbnail, sick. Okay, channel name from Matty Avella, nice. Channel name Thomas Frank, channel name Ali Abdaal. Nice, okay, it's kind of interesting. So now what happens if I just try and open index.html? Could not load videos, run Python 3 fetch videos.py first. Okay, so it's not working. But Claude already knows that it's not going to work because it knows that this is the problem. So now, Claude is asking me to run this bash command. Python m HTTP server 8000. Okay, sure. Server's running. Open this in your browser, localhost 8000. Okay, let's see if it works. I'm going to copy and paste this URL. Open it in my browser, localhost 8000. Whoa! That was really cool. Look, I've literally just opened this in localhost 8000, and I can see that we've automatically scraped data from Thomas Frank. Matt D'Avella, and me. Ooh, I see that we've scraped some YouTube shorts from me. That was not my intention, but like what else. And then I can filter it. Wow, look at that. We have just created an online dashboard that's running purely on our local machine. No one on the internet has access to this other than me because it's on localhost. But if I wanted to make this accessible via the web, what do I do? Again, I ask Claude. This is really cool. You know what? Let me just talk to it. But this is on localhost. How do I make this accessible on a website so that my team can have access to it? Because this is really nice. And then Claude will teach me all about what deploying stuff to the web means. And then I can ask you more questions about it. And then I can deploy it to the web. And now I have an actual website. And then I might say to it, but like, I don't want anyone in the world to be able to access the website. Like, how can I, you know, how do I prevent people from accessing it? And then it will teach me about authentication and say that, oh, you should just add in a username and password. I'd be like, how do we do that? It'll tell me you can do it manually or you can use Google's OAuth or you can use Vercel authentication. I'd be like, what the hell is Google OAuth? I can understand about that. And now, before you know it, I have coded up a fully-fledged web app that only me and trusted people have access to. Or if I want, I can allow anyone to access it and make an account. I could even get them to pay for it if I wanted to make it paid by just asking Claude, hey, I'd like to make this app available to paid subscribers. I want to charge them $19 a month. How do we make this happen? And Claude will tell me, oh, great way of thinking about it. What you want is a billing API. Make a Stripe account. Go on Stripe.com, make an account, give me the API key, and I'll set it all up for you. Now, anyone in the world can sign up to your app, but they can only use it if they pay you $19 a month. Amazing, you've now built a web app, a SaaS, a software as a service that could potentially make you some money. You have not needed to know anything about how to code in order to do this, because all you've needed to know is how to talk to Claude, how to be curious, how to ask Claude to explain stuff to you that you don't know the answers to, and the little skill of being able to push through the small frictions that you will encounter. Okay, so anyway. How do I make it accessible on the website? Vercel is the easiest thing. One command deploys it to your URL like youtubetracker.vercel.app. Free tier is plenty. Your team just visits the link. Sick. It's even free. I don't need to pay for it. GitHub Pages. Push to GitHub repo, enable page and settings. Free. Okay, nice. Netlify, submit to Vercel. Nice. All three has static files for free. The one thing to think about right now, the data is a snapshot. To keep it fresh, we'd set up a GitHub Action, which runs a script on a schedule and deploys it automatically. Sick. Which option sounds best to you? I'd recommend Vercel. It's the fastest to get running. Nice. And I'd be like, what is Vercel and how does it work? Et cetera, et cetera. You get the idea, right? We're building the thing. And in the process of building the thing, we are learning about how websites work, how code work, how deployments work, et cetera, et cetera. And before you know it, you will be so far ahead of your previous self. You'll be so far ahead in terms of understanding the shit compared to your friends who didn't give it the time that like you will feel like a different person. I feel like a different person now than I did two months ago when I first started discovering this stuff. And I know how to code. I've been coding shit since I was like 13 and like build. software as a service myself wasn't particularly huge, but like, you know, me and my brother had built stuff when we were at university that was making like $150,000 a year in revenue, which is, you know, it's not bad. It's not like zillions, but it's like, it's not bad for like university kids. I knew how to code. And still my mind has been fricking blown by the power of Claude Code, the power of just being able to speak to the AI, to get it to interview you about what to build that saves you time and makes you money, helps you follow your curiosity to understand things like web servers and Vercel and SSH and all this funky stuff. push through the friction associated with dealing with API keys and stuff like that. And before you know it, you've built some really cool stuff that genuinely adds value to your life, your customers' lives, your boss's life, if you want to try and get a raise at work. You can build things that track your workouts. You can build, you know, I've got my Kaladin open claw agent that helps me track my protein and helps me give me like workout recommendations. And every single day, me and my team, at least my team members who are now into this AI stuff, and I hope this video will make all of them into the AI stuff. Actually, I'm going to send this video to literally everyone on my team. You then start realizing all of the cool shit you can build to automate aspects of your life and save you time. It's so cool. Oh, what a time to be alive. Anyway, before we do this thingy, I'm like, okay, I look at this page and I'm like, huh, this is fine, but I don't like the fact that YouTube shorts are showing. Okay, let's forget about the web deployment for now. I don't like the fact that it's showing YouTube shorts. I don't really care about YouTube shorts. I only want to show long form YouTube videos. And let's see what Claude says. I'll filter out shorts by checking video duration. Shorts are 60 or under. I just need to pull content details from the API and skip short videos. Sick. Do you want to make this edit to fetchvideos.py? Okay. Well, okay, now here, green means it's adding it, and red means it's removing the line. So here, it's like fetch per channel 30. Fetch more than 10 to account for short-term filter. Yeah, okay, sure. Do you want to make this edit? Okay, so it's removing some stuff. It's adding some stuff. Okay, yep, seems reasonable. Yes. There's a good meme of what it feels like to be using Claude code these days. Here it is. Okay, rerun the fetch. Yep, that's fine. I'm lollygagging. That's why I like Claude. Claude has personality. YouTube recently expanded shorts to be three minutes long. So let me bump the filter to exclude anything less than three minutes. It figured it out. It took a few attempts to figure it out, but it figured it out. Now, as you're doing this sort of stuff, one thing you'll realize is that, you know, while it's doing things, it's a real challenge to figure out what to do while waiting for it to do stuff. So what you do is you either chill out or think about life or like do some meditation and mindfulness, or you do what all the pros do and you create a second terminal window. So while the first one is working on one feature or one thing, you've got a second ClaudeCode instance that's working on another thing. And then you realize that you still have time on your hands. So then what you do is you have four terminal windows open, each of which are running a different instance of ClaudeCode, and you're working on a different feature for each one. It is annoying if you're trying to work on four terminals for the same feature, because then they start not realizing that each other are working on the same files. There's ways around it, but to keep things simple, you start off with one. you realize, wait a minute, I can just be twice as productive if I just had another window open. So then you make a new terminal window. You like stick it on the side of your screen like this. Boom. You do this one like this. Boom. You then zoom out. And now you've got one terminal window there. You zoom in here because we don't like that. We don't like to read. Type in Claude over here. And now we have another Claude code window here. And then you're doing stuff here. You're like doing stuff here. You're working on a feature here, working on something there. And then you're doing stuff and you're like still got too much time. And then eventually you get into this like four-way setup where you do windows like this. This kind of thing where you have a terminal window here, a terminal window there, a terminal window there, a terminal window there. Everything is a terminal window all over the place. I literally just bought a 52-inch Dell Ultrasharp monitor for the sake of being able to have multiple terminal windows. Because my Max 2D display broke, which is why I'm using my laptop. Anyway. Okay. Open localhost V3 in your browser or incognito window. Let's see what happens. Oh, it worked. Nice. So now the shorts have been gotten rid of. Amazing. That's cool. Sick. GG. I mean, this doesn't do anything. It just wastes tokens, but I like to compliment Claude when it's done a good job. Glad it's working. Let me know when you want to build on it. Things like adding more channels or to refreshing the data or deploying it for your team. Now, this is a very basic use case, but you've just seen without knowing anything about how to code, literally by asking Claude to interview me about what I do that I find annoying, downloading Claude code, trying to understand what commands it's getting me to do. I have just built this dashboard and this is so, so, so. freaking basic. This is like the most basic thing you could possibly build and it's still really cool. And the great thing about this is that, you know, I'm really not sure what I want to build on top of this. Can you ask me some questions and help me figure out like what we should build next? The key thing is when you're building AI stuff, you don't want to build stuff for the sake of it. You want to build stuff that actually helps you in your work or in your life. So for example, you want to build things that add value to your customers or that save you time or that make you money. And generally, Claude is very smart at helping you figure out what that stuff actually is. Here we go, a few questions. What's the goal? Are you tracking competitors to learn from their content strategy, or is it more about benchmarking your performance against theirs? Great question. What decisions does this help you make? When you look at this dashboard, what do you wish you could immediately answer? For example, what topics are trending in my niche right now? Or which of my competitors is growing the fastest? Who on your team should use this? How many channels do you want to track? How often would you check this? Daily, weekly, before a weekly meeting? That affects whether we need auto-refresh notifications, etc. Okay, how is Claude Code doing this session? Good. Very good. Thank you, Claude. I love you. Start with whichever question feels most interesting. We don't need to answer all of them. And again, this is where you just open up Whisperflow and you just... talk, you just spiel out whatever you want to do. And then Claude will do a good job of helping you figure out what feature to build next, and even then build the feature for you. And now before you know it, you've You know, in my team, like Becky, my YouTube producer, has automated like two days a week of her job by just building cool shit and clawed code. And Nicole, our social media manager, is in the process of learning how to use clawed code and clawed co-work to automate, again, hours and hours and hours of manual time that she's spending every week doing this sort of stuff, which means she's then able to focus on more interesting things that are higher leverage, more strategic stuff, coming up with new content ideas and creative things like that, rather than the manual nuts and bolts of pulling stuff from like the Instagram API and trying to like... copy and paste numbers into a Google Sheet. In every person's job and in every person's business, there is annoying, tedious work that needs to be done, which is so, so, so easy to automate these days. Super, super back in the day, if you wanted to automate anything, you had to hire a software developer to do this code. And then no code automation tools like Zapier came about. Later on, at first it was Zapier, then it was make.com, and then it was NA10. And all of these tools were basically like drag and drop interfaces for saying, hey, connect up the data from my Notion, chuck it into Zapier and then connect it to Google Sheets so that I can automate that tedious part of my job. But now you don't even need to use tools like Zapier, make.com and NA10. Like NA10 is so 2025. Now you can literally just get Claude Code to be your full-time genius level software developer. It can create all of this stuff automatically. You can run these things called cron jobs on your own server. You can run them as GitHub actions. You can get it so that every minute it pulls in data from YouTube. Every day it gives you an analysis of your top 50 competitors and what they're doing. You can get it. So if you're running a marketing agency and you're trying to close a new client, it automatically scrapes everything on the internet it knows about your clients. It automatically looks up the meta ads library to see what competitors are out there. It automatically creates for you a proposal that you can record a loom over and send to to the client to try and close them. There's so much stuff you can do with this. It's incredibly powerful. And the way you access this power is that you spend a few hours, you spend a weekend just choosing to go through the friction of like sitting down with a terminal window, talking to Claude and asking Claude about how it can help you make more progress in your job or in your life, in your business, help you save time, help you make more money. It is an incredible time to be alive. Okay, if you got to the end of this video, I would love to see a comment down below. Did you find this useful? I mean, hopefully you did if you got to the end of this video, but I would really love to know what more would you like to see in our little AI education series? I'm diving deep into all of this stuff. I love doing tutorials about this stuff because this is the future of productivity. Back in the day, it was like Notion. Notion sort of changed the game for people's productivity setups and stuff like that. Before then, it used to be like how to type really fast, but now it's about how to use AI tools to... save you time and make you money. It's just absolutely incredible stuff. And I would love to make more videos about this, but I would love to know what you guys would find interesting or useful on this front. And if you enjoyed this video and you wanna see another video about how specifically I use AI and a whole suite of AI tools to improve my own productivity within the business context, check out this video over here. Thank you so much for watching and I will see you in the next one. Bye-bye.

Grab 10% off Hostinger Horizons with code ALIABDAAL at checkout: https://www.hostg.xyz/SHJI3

Get the free AI learning guide here: https://go.aliabdaal.com/ytdlearnaiweekend

Apply for the next cohort of the Lifestyle Business Academy - https://go.aliabdaal.com/lifestylebusinessytd
---

MY PRODUCTIVITY APPS
📝 Momentum: Energising Habits (iOS) - Download Here → https://go.sparkle.so/momentum/ytd 
👻 Voicepal: AI Writing App (iOS/Android) - Download for Free → https://go.aliabdaal.com/voicepal/ytd

MY BOOK
📕 My New York Times bestselling book Feel-Good Productivity (2,000+ 5-star reviews) → https://go.feelgoodproductivity.com/amazon/yt

MY COURSES
🚀 Build a $100k/year lifestyle business without quitting your day job → https://go.aliabdaal.com/lifestylebusinessytd
🧠 My Productivity System: LifeOS → https://go.aliabdaal.com/lifeos/ytd
🤑 Grow / Monetise your YouTube Channel → https://go.aliabdaal.com/ptya/ytdd

CONNECT WITH ME
💌 Join LifeNotes, my weekly email where I share what I’m reading & learning: https://go.aliabdaal.com/lifenotes/yt
📸  Instagram: https://instagram.com/aliabdaal
📱 TikTok: https://www.tiktok.com/@aliabdaal
👨💻 Linkedin: https://www.linkedin.com/in/ali-abdaal/
🌍  My website / blog: https://www.aliabdaal.com/

---

Hey friends, there's a tool called Claude Code that has genuinely changed how I work, and this video is the one I'm sending to my friends and family who haven't tried it yet. I'll walk you through the AI flywheel: where you get AI to interview you about your work, figure out what to build, and then learn how it all works in the process of building it. No coding experience needed, just curiosity and a willingness to push through a little friction. Hope you enjoy xx

🔗 LINKS MENTIONED IN THIS VIDEO

- Wispr Flow: http://wisprflow.ai/ali
- Claude desktop app: https://go.aliabdaal.com/claude
- OpenClaw: https://openclaw.ai
- ChatGPT: https://chat.openai.com
- Google Cloud Console: https://console.cloud.google.com
- Vercel: https://vercel.com
- GitHub: https://github.com
- Zapier: https://zapier.com
- Make.com: https://make.com
 - N8N: https://n8n.io

⌚️ TIMESTAMPS 
00:00 - The AI Flywheel
01:34 - Prerequisites
02:29 - Ask AI what to build
09:34 - Learning as you build (APIs, MCP servers, etc.)
14:48 - Real examples of what I've built with Claude Code
23:42 - Understanding Claude Code & the terminal
26:42 - Installing Claude Code
30:07 - Running Claude Code for the first time
37:38 - Building the YouTube competitor tracker
41:09 - Getting the YouTube API Key
48:29 - Building and running the tracker
55:35 - Seeing the dashboard come to life
1:00:54 - Running multiple Claude Code instances
1:02:44 - What to build next & real-world impact

PS: I donate 10% of my income to charity every year. Would you like to join me? Learn more about the 10% Pledge: https://aliabdaal.com/giving-what-we-can/