The AI Skill Gap Is About To Get Brutal

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 Cowork thing.

I just I don't really have the time.

Hopefully this video will help you solve all that.

And this video is gonna 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 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 the 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 Claude desktop app, you will notice it says chat, which is the thing that you are used to.

It also says cowork, 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 gonna ask AI what we should build with AI.

I'm trying to learn how to use AI.

My current AI skillset is I just use ChatGPT and Claude and use the chat feature.

But I recently watched a video that tells me about Cowork and how Claude Code is the best thing ever.

So to that end, I want to learn how to use AI, but I don't want to just randomly try and learn how to use AI by following tutorials.

I actually want to 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 want to 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 Co-Work and Claude Code as well.

Okay, so my business actually does, I guess I would say, 3 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 VoicePal, which is a sort of AI ghostwriter.

We're building an app called Superfocus, which is a sort of productivity thing.

And we are building an app called, well, 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.

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 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 wanna 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 like data collection process.

I'm not gonna 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 like 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 5 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 wanna 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 wanna watch the video itself 'cause I don't wanna 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 'cause 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 gonna start with YouTube.

It's the easiest win.

YouTube has a public API where you can pull videos, titles, thumbnails, view counts, publish dates for any public channel.

You give it 50 channel names and it gives you back everything you want.

That's your week 1 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 could see thumbnails and titles at a glance without watching anything and you could have AI automatically tag the topics so you can spot patterns like 3 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 Claude code because it involves real API calls, real data processing and optionally a real frontend.

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 and 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 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 of these different features that are gonna help you save your 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 are creating and stick 'em 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 wanna 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 Stripe.

So 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 like, 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/aliabdaal, and you can get 10% off if you use the code aliabdaal 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 wanna do is I wanna 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 2 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 like, what does SSH mean?

And like, what, you know, 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, 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 OpenSSH, 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...

into my terminal, I know what that means and I can appreciate 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.

Ah, and Claude is just again, really good at explaining stuff.

Let's go deep.

The problem before APIs existed.

Imagine it's 2005.

You're building a website and you wanna 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.

Ah, 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 the stuff rather than just like blindly do it is because when you start understanding these things, you get, it's like you get a firmware update

in your own brain, which means even if you don't really care about like the history of computing, 'cause you don't find it interesting, it's still useful for you to know that 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 blah, blah, blah.

I wonder if they have an API.

And you Google, does blah, blah, blah 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, this 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, this is 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 2 months.

It's absolutely sick.

I was intimidated by Claude Code because it involved the terminal and I was like, oh my God, terminal.

I'm not like some fricking hacker from the 1990s.

Why do I need to use the terminal?

And then I realized I was a total fricking 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 fricking 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 are 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 wanna 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 2 months.

If you wanna skip this bit in the video 'cause you don't care and you just wanna 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 gonna ask one of my OpenClaw agents.

OpenClaw is kind of like Claude Code on steroids.

I've been using OpenClaw for the last like 2 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 OpenClaw if you feel like it.

But let me tell you about my various OpenClaw agents.

I have Albus, who is my primary OpenClaw 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 Minerva, 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, you know, 6-figure lifestyle businesses.

And then Minerva, 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, you know, get content ideas, and he's the one who helps build out all of these, like, 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 talk 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 5 years.

And so he knows exactly where my lifts are at.

He knows that I had like an, 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, 'cause 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's any of this possible?

Then don't worry about it, just like stop, using AI to teach you what you wanna build using AI that improves your business life or saves you time or makes you money.

And then in the process of learning stuff, and then at some point you can ask Claude being like, hey, I watched an Ali Abdaal video where he talked about having these like 8 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, things like DCG, which is like the destructive command guard that physically stops it from doing anything that

might 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 Albus.

Yo, Albus, I'm actually working on a YouTube video where I explain how to learn AI in a weekend.

And you know, for the last 2 months that we've been building stuff using OpenClaw and using Claude 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 like 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 2 months.

Firstly, a support ticket pipeline.

So within our Lifestyle Business Academy, we have 200 support channels for all of our students 'cause currently we have about 200 students and each student has their own like 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.

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 bunch of custom GPTs.

Like we created custom GPTs for things like niche generation and first draft offer creation and like content and like, you know, 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, are the 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

We've got the course on Circle, and now they have to have an OpenAI 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 like accidentally leak any conversations to Slack.

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 like over 100 of our students send thousands and thousands of messages to Dumbledore, the Slack bot.

And Dumbledore has been trained on our like internal DM methodology for how to sort of convert a cold prospect into a warm lead and get 'em on a sales call so that they can grow their

business.

And so students are like 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 like a prospect and they're like struggling to turn it into a call, they'll just like 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 students sensible advice.

And so if you use Slack in your business or in your work, then did you know you can ask Claude Code 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, Hormozy 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 Hormozy's channel.

So then it prompts us to think, huh, could we like take inspiration from the fact that that video is popping off for Hormozy?

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 9 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 Open Claude, when I'm using Claude, and it all happens through an

MCP server.

Over.

Now that might have been a lot of jargon.

I did not know what any of this stuff meant 2 months ago until I decided to, you know, spend a weekend really just trying to build something useful using Claude Code.

And over the last 2 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 like AI stuff that you, you end up in this, in this zone where you spend so long like building agents that talk to other agents and that like help

you orchestrate other agents that you don't actually end 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 like I didn't want this to be another one of those like 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?

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 Claude 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.

macOS, 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 GUIs 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, dot dot dot.

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 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, 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.

Ooh, this is nice.

A concrete analogy.

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.

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, okay, how do I install it?

Okay, 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.

Okay, so on a Mac, open the Terminal app, hit Command+Space, type Terminal, hit Enter, then paste the single command curl -ssl Claude.ai/install.sh.

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 gonna copy this.

Explain to me what the hell is going on here before I do anything.

Get please...

You don't have to do this with every single terminal command, but like, it's 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

FSSL.

These are 4 flags squished together.

Flags are like settings that modify how the 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/install.sh is a web address, points to a file on Anthropic servers.

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 try 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 wanna 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 this app from Anthropic's website directly where you can verify that it is in fact on Anthropic's 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 like lock down the walls around this and make sure that like what I'm doing is legit,

but you can decide how security conscious to be, uh, or not.

Ah, 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.

Terminal, and look what happens.

Accessing workspace users ali.dal.

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 my God, please run login.

Okay, I need to log into my Claude account.

Let me do that.

Great.

I would like to connect to Proko 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, Anthropic's command line interface for Claude.

Your login was successful.

I can help you with software engineering tasks like writing, debugging, or explaining code, navigating and understanding code bases, running commands and managing files, answering technical

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.

Oh, 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 are 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, 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?

What's the git command?

How does it work?

Then you're gonna go on a rabbit hole to understand that git is this like 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 like document 1, document 2, document 3, v5 final, v6 final, et cetera, et cetera.

So git is like this open source thing that you can install on 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 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.

Claude, watch the permission prompts.

They 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?

Ooh, yes please.

It's so helpful, I love it.

Watch what happens when I attempt this.

Create file claudecodetest.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 ClaudeCodeTest.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 wanna 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 like security prompt before doing doing this.

So here we go.

Write ClaudeCodeTest.txt.

Wrote 4 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 1 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 bash rm /usr/lib/cloudcode-test.txt.

Delete the test file we just created.

Now you might be thinking, what the hell does bash rm 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 ChatGPT 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?

Two things to unpack here.

What bash is and what rm does.

And the second one is worth paying attention to.

Bash is the language your terminal speaks.

The name stands for born-again shell, which is a nerdy joke.

1979, blah, blah, blah, blah, blah.

rm, this is the one you should care about.

rm stands for remove.

It deletes files.

This is the one terminal command where you should always read what comes after it before hitting Yes.

Unlike dragging something to the trash on your Mac, rm does not have a recycling bin.

When it's gone, it's gone.

So rm some temporary file.txt, fine, it's cleaning up a single temporary file.

For example, rm /usr/lib/cloak-code-test.txt.

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.

-r means recursive, go into every subfolder and delete every 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 This would 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'll be harmless things like creating folders, running code, or installing packages.

But rm is the one where you should always glance at what it is removing before you approve.

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 Claude Code test in your home folder.

That's almost certainly a file that Claude Code 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 and 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 gotta 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 all these, I've got the ability to do all these things, but like 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, like, YouTube competitor analysis dashboard situation that we were talking about?

Okay, here's where it gets fun.

3 steps before you start talking to Claude Code.

Create a project folder in your terminal.

You wanna create a dedicated folder for this project.

Think of it like creating a new folder in your desktop, but via the terminal.

So I could do mkdir, which means make a directory.

It creates a folder.

cd means change directory.

Then start Claude Code inside that folder.

Folder.

That sounds interesting.

Let's just do that.

So I'm gonna go on my terminal, I'm gonna get rid of Claude Code.

I happen to know that you use Ctrl+C to like 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 a 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 mkdir.

So let's go in the terminal and type in mkdir youtube_tracker.

I 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 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 Abdaal Ali's MacBook 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 Abdaal, which is shorthanded by 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 'cause 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 gonna be complicated.

Remember how I said API supplier enters the API keys access bridge.

YouTube needs to know who's making the request, people can use it.

The key is free.

Google just wants you to register So go to console.cloud.google.com, create a new project, search for the Data API, go to credentials and create an API key.

It takes about 3 minutes.

And then step 3, tell Claude Code what to build.

This is the magic part.

Once you're inside Claude 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 wanna 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.

Published it.

Store the results in a local JSON file for now.

Here's my API key.

Let's start with just 3 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 wanna understand what it's doing before you approve the step.

And then over time you'll realize that you'll, 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 3 channels.

Get the data pulling working.