Claude Code Masterclass: From Beginner to Expert in 33 minutes

If you just started using Claude Code, or even if you've been using it for a while, you're probably only getting about 10% of what Claude Code has to offer. They've released a tremendous amount of features and functionality in the last 6 months. And in this video, I'm going to cover it all. Whether you've never used Claude Code before or you've been using it since launch, I promise if you stick with me until the end of the video, you'll walk away learning something new. I'm going to go through every single aspect of Claude Code. Plus, I'll show you how to build and launch an entire application with it. Even if you've never coded a day in your life, check out the chapters below. This video is meant for you to jump around if you'd like. And if you're interested in Claude Code, make sure to leave a like or a hype down below so I know you're interested in more Claude Code content, and I'll make sure to make way more videos about Claude Code. Claude Code's the most powerful AI app building tool out there, and I can't wait to show you all about it. Let's get into it. So, let's get into the basics.

After this, we'll get into more advanced Claude Code concepts, and then I'll show you how to build and launch your own app. If you already know the basics, feel free to skip ahead. All the chapters are marked down below so you can jump to more of the advanced stuff you've never heard of before. But let's get started with installation. Today I'm going to install clawed code into cursor. The reason why I'm going to install it into cursor is if cursor ever comes out with more interesting functionality. We'll be able to combine the cursor functionality with clawed code. You don't need to pay for cursor. You can download the free version right now. So make sure to do that. cursor. com. And in here, we're going to install Claude Code. When you're in Cursor, all you need to do is open up a new project. So, you just click open project. You create a new folder in that window that pops up and you're good to go. Claude Code installation. Very, very simple. We take this command right here and I'll make sure to put it down below in the description for you. We go back into cursor. We open up the terminal, which if you're on Mac is control day, or else you can just go to view terminal in your menu at the top. This will pop open your terminal like you see here. I personally like to move this to the right hand side. So we'll do panel position right. Then we close that chat and we move that down below and we're good to go. Then you paste in that command from down below and you hit enter and that is going to install claude code for you. Now all you need to do is type in claude. Once that's done installing you hit enter and now claude code's going to open up for you. You're good to go. You're ready to start building some magical application. So now we're good to go. Let me give you a

quick introduction of the UI here. So over on the left hand side is going to be all the files you're going to create once you start giving prompts to claude code. Over on the right hand side is claude code. This is where you're going to give commands to the AI agent. Build me this, change that, debug this, launch that, and claude code will do all the hard work for you. Again, you do not need any programming experience here. Claude Code's going to do all the hard technical work for you. Before we start building out our application, I'll show you other couple parts of the UI here. uh a lot of the configuration of claude code is done through what's called slash

command. So for instance, if I do slashmodel and hit enter, we're going to get options of different models we can use. Now depending on which plan you're on, there's like I think a $20 version, a $100 version, a $200 version. If you're just starting off and want to experiment, feel free to do $20 version. You probably won't be able to do too much with it. You're going to want to get to the$100 or $200 version if you want to get really serious. $100 is totally fine. But depending on which plan you're on, you're gonna have a few options here. You need to have the $100 option to use Opus, which is their best model. But as long as you're on that plan, you have a few options. I like to use Opus plan mode. And the reason why mode is basically it uses Opus, their best model for all the planning. And I'll show you how plan mode works in a second. And then it uses Sonnet for the execution. And the reason why that's a good idea is Opus is going to make such indepth detailed plans that you don't need the smartest model to do the execution because the plans will be so good. So I like to use Opus plan mode. That'll make the model selection dynamic for you and that's going to be really good. It's also going to save you a good amount of money. So stick with me here. Do slashmodel. Go to Opus plan mode if you're on the$100 or $200 version. If you're on the $20 version, you can stick with Sonnet. You're good to go. That's your model picker. One

last thing I'll show you before we start building out the application and then I get into the more advanced functionality is plan mode. And so if you hit shift tab, you will see a couple things. So first it'll do accept edits on. This basically goes into YOLO mode where the agent will just go and build out anything for you without asking for approval. We're actually going to use that quite a bit. Claude code's really good. I trust it to do whatever it wants. But we're going to hit it one more time. Shift tab one more time. That puts us in plan mode. And plan mode's excellent. You want to be using this a tremendous amount. This is a critically important part. And again, if you're already familiar with plan mode, feel free to skip ahead to the next chapters. But plan mode is really important because this is where you're going to be going back and forth with the AI model without the model doing any coding. So a lot of time before you want claude code or the agent to go and make changes to the code, you want to make sure the agent knows exactly what you want to do, right? And this is where I use plan mode. I confirm with plan mode what the agent's going to do before it does it. So I make sure that everything the agent does is exactly to my liking. A lot of people complain, "Oh, you can't trust the AI agents. They do crazy things. They're not cooperative. They're getting dumber. " No, no, no. Skill issue. If you're using plan mode the correct way, the agent will always do what you want it to do. So, we're in plan mode now. For the example for this video, what we're going to build, we're going to build an advanced notetaking app. So, allow you to do really cool looking notes, AI functionality, a whole bunch of things we're going to build out together. So, let's first do this. Let's go into plan mode and let's ask for a plan from Claude. And I'll put this prompt down below, too, so you can steal it so you can work along with me here.

So, here's the initial prompt I'm going to do with plan mode. This is going to build out the initial code for us. Then we'll go into the more advanced functionality in Claude Code. I can show you some neat tricks. I want to build an advanced note-taking app. The user should be able to take notes in a beautiful, powerful, easy to use editor. Be able to save notes into folders and organize them however they want and even use AI functionality. Let's build a PRD for this app. And what a PRD is a products requirement document which will basically outline everything we want in the application. getting this PRD built out first is really critical because it will give context to the AI on where we're going. What's the road map and what's the end goal we want to get to. So, I'm going to hit enter on that. Again, feel free to steal it from down below and work along with me here. Claude Code is now going to get to work here. You're going to see it working and thinking it is creating a comprehensive PRD for the advanced note-taking application. And it's actually pretty quick. I compare this to other AI app builders out there. Claude code's probably the quickest out of all of them to be quite honest with you. All right, so it looks like Claude has built a plan out for us for this application. Advanced note-taking app, product requirements document. Okay, so it gives us an executive summary of exactly what it's going to build. It talks about the rich text editor, so it's going to allow us to do some very nice editing, make really good-looking documents. The organization system with bookmarks and folders and everything involved. That's nice. Trashing, being able to archive and throw away notes. I like that. AI functionality. So, we can do smart summarization, smart search, autotagging. That's pretty cool. I like that a lot. Grammar and style checking. Listen, the reason why I love making applications like this, people ask, "Oh, Alex, why do you always make note-taking apps and calendar apps? " Because my favorite thing to do is build apps that I use every single day. Rip out those apps I was paying for and use the ones I built and save money. So, if you're working along with me here, you're going to have a note-taking app that you can use moving forward and it's going to be awesome to use. It's going to have collaboration and then it talks about all the technical stuff. So the front end, Nex. js, that's good. Backend, we'll get into that a little bit as well as the infrastructure. All right, so let's do this. I want to keep this simple. So at any point when you're chatting with the AI agent, you can hit the escape button, which will allow you to add more context before it continues. So I'm going to do that. I'm going to say for this first version, let's just focus on the front end and getting a working local version up and running. We can demo. So, instead of spending a ton of time setting up the back end and the database, let's just get a working version running that just uses the front end and we can add that on afterwards. So, I'm going to hit enter. It's going to add that context to the AI and it will update our plan for us. So again, when you're in plan mode, at any point, you can hit escape, you can add more context, you can make different requests, and then you hit enter, and it goes back and fixes whatever it was doing. All right, so we have our updated plan here. Looks really good. I'm going to do one more thing before we execute on it. I'm going to hit the escape button. I'm going to say, let's do this step by step, one step at a time. So let's just start building out the front end. So I hit enter on that. And now the AI agent is going to get to work on our PRD. It's going to start building out the application for us. Now in a second once it builds out V1, I'm going to get into more of the advanced functionality here. But we'll get this started and see what V1 looks like and I'll start showing you some more interesting things you can start doing with Claude Code. as it works here. You can just hit yes if you want to approve this step by step. Otherwise, I just say yes and don't ask again because I I've worked with Claude code long enough to know it is an awesome AI agent and it very rarely makes any kind of critical mistakes. So, I'm just going to give it the go-ahhead to do everything it wants to do. Okay, looks like the agent finished work on our initial app v1. Let's take a look at what we got here. So, let's take a look. It will tell you which local host to go to make your app work. For me, it's going to be 3003 because I'm building a 100 different apps at one time here.

Let's pull it open. Boom. We got an error. This is actually a good thing. This is a good thing. I'm going to show you how to debug. Debugging very, very important with claude code. It's like the number one question I get is what happens when I run the bugs. I'll tell you exactly how to do it here. When you're looking to debug, it's really simple. We're going to lean on cloud code here. So, we're going to take a look at here. our error. I'm going to highlight everything on the screen. You really have two ways of debugging. Way number one, which I'm going to show you right here, is copying and pasting the error in debug. Number two option you have is screenshots. You can also paste images into clawed code. But for these text errors, like you see here, I like to just copy and paste. Let's take this. I went in here. I say I say, hey, let's hold up for a second. It looks like there's an error. And then I'm going to paste in the error. It's just going to say pasted text, lines, whatever. We hit enter on that. It is going to look at the error. It's going to figure out what's going on in 99. 9% of the time where I just give an error to claude code. It figures out how to do it in one shot. So, it is going to start working here and is going to fix our error for us. It is fixing our errors for us. It's deleting code. It's adding code. Great. Now, let's see if we got a success here. All right. Status app working. Let's take a look to see what

we got here. Let's check out the V1. Pull it over here. Wow, look at this note AI. Okay, so we got a whole lot going on here. We have the main editing area which is right here in the middle. This is a test. Wow, that looks really nice. Uh it's a rich text editor, so we have tons of different options. We can do headers, we can do quotes, bullet points, upload images. That is sick. Over to the left, let's see what we got here. We have a folder system, so we can create different folders. We have the notes listed out here, so we can switch between the two different notes. We can delete, we can bookmark. This is awesome. And there's even a settings. This is amazing. This looks really, really good for a V1 for a oneshot. This is the power of clawed code and using the plan mode correctly is you get these types of V1s which is awesome. Tons and tons built out already. We have a lot more we need to cover here and we're going to build this out. So much more. Add a ton more functionality including AI functionality to this app which we'll go over. But I want to go over some more advanced functionality with you now inside Claude Code. Just as a side note, as a small little feature they added over the last couple months, they now have what's called background tasks. You

can see that right here, one background task. And now Cloud Code basically has the ability to run your application on its own and have that go in the background so that as you're building out your application, it can actually read your server logs. Before you actually had to open up a brand new terminal to run your app. Now claude code can do it for you and put it in the background which allows it to monitor your app and do other things while it's building out and do multiple. It's basically it's multitasking ability which is really awesome. So this made Claude code a lot better to use the

background tasks. Let's also talk about claude. md. This is the rules file for the claude agent. So what we're going to do is we're going to go into claude here and we're going to do slashinit. And what slashinit is going to do is create us a claude. md file which is going to be our rules file which will allow us to customize the claw AI agent even further. So what happens when you do slashing is not only creates a claw. md file it actually goes through your entire application everything you built and creates custom rules for you so that claude has more of context around what it's built and what it's going to build. So, this is really important to do after you build out that v1 is to do slashinit to get that new clawed rules file that automatically generates a ton of context for the clawed agent. But what we're going to do in a second is add even more context and more rules that will make the agent even more powerful. So, as you see here over on the left hand side, it created a claw. md file. And what it actually did was it put in a lot of context that's important, right? It has what the app is. It has the entire tech stack it's using. It has all the information around like the data structures and how the data actually works as well as wow everything around state management. Look at all this really nice information it has. That is awesome. It built that out all automatically with this slash in it. So you want to use slashinit the moment your v1 of your app is built. But we're going to add a few more things here. So what I'm going to paste in down below and I'll put this down below in the description as well as a whole new set of rules I want you to put in here. So these are nine new rules which basically guides the agent a little bit more and will prevent errors in the future. And basically what it does is it tells the agent, hey, whenever you run errors, think about it step by step. Always do full investigation before you make any changes. Check with me before you do anything major. And always break problems down into small little tiny steps and never be lazy. And what this will do is prevent a whole lot of errors that the agent might make in the future. Again, I'll put this down below, but I'm going to hit save on that. And now our rules file is good to go. The agent should be even more powerful than it was before. Several more features I want to

go over here with you. Next, I want to talk about the different thinking modes. So, let's do this. I want to add in AI functionality into our app. So, I want to have the ability to talk to an AI and say, "Hey, write out this entire note for me or summarize this note for me. " So, let's plan this out with Claude code. We'll go back in here. Here we'll go into planning mode again with shift tab plan modes on. Now I want to talk to you about thinking modes. So let's first do this. Let's build out our prompt. Again we just give a very simple command on what we want Claude to build. I want you to now add AI functionality that allows us to generate text in notes or summarize notes. Feel free to come up with other ideas. But here is now thinking modes. So with claude you have several thinking modes. I just use three. Think, think harder, and ultra think. So if you in any of your commands use those terms, think, think harder or ultraink, it will actually control the amount that Claude reasons as it's working. Right? So if you say think, you can see it just turned purple. If you say think harder, you can see it turned orange. Or if I say ultra think, you can see it turned rainbow. And that's this super amount of thinking. And whatever term you use is the amount it's actually going to think. So for this one, this is a pretty standard simple kind of functionality. So I'm just going to say kind of in the middle, let's do think harder about this. And it's going to make the AI think harder. So depending on the type of functionality you want to build out. If it's really simple, you just say think. If it's kind of moderate like we're doing here with this AI functionality, I'm going to say think harder. But if it's like a super big maybe if it's even V1 like we were doing before, it probably could have helped if I said ultra think, but you do ultra think for the super complex problems you're looking to solve. These think modes were added a few months ago and they are really, really helpful. Will help you get much better results from the prompting you do with the agent. So, make sure to write that down as well. All right, looks like the planning is done and wow, look at this. It came up with a lot of ideas that it could build out. They came up with like a fivephase system of adding AI functionality. That's because we did the think harder. Let's do this though. Let's keep it simple for now. Let's just get the basic AI functionality in. Let's say this. I just hit escape. This looks great. Let's just implement the basic AI functionality though. And then I hit enter on that and is going to start implementing the basic functionality. But that is the different think modes. really important to use, really important to take advantage of because that's what is going to get you awesome results from the AI8. So, I'm going to hit enter on this and it is going to

implement all that AI functionality stuff in a second. If you're newer to coding, I will show you how to actually implement the AI API. So, you can implement AI functionality into this. If you already know how to do all that, you can skip over to the next chapter. Again, feel free to skip to any of the chapters you want. Also, leave a like down below if you've learned anything at all. So far, it lets me know that you really enjoy Claude Code content and I should make more of it and if you really liked it, make sure to leave a hype. That's I guess the new YouTube functionality and really gives me awesome feedback and helps the video out a ton. So, it is now going in and is building and executing on that think harder plan we did that will add a lot of really cool AI functionality. All right, looks like it's all done. Let's see what we got here. I'm going to pull this over. Let's see what they added. Okay, so we have this new AI functionality here. I click that continue writing improve selected text and summarize notes. So we have three new pieces of AI functionality. We can have the AI continue the writing of our note, improve any text we highlight or summarize the note we have open. All we need to do to get this to work is add the API key. I'll add I'll go through towards the end and add that on and show you how you can add more features and function to that. I want to continue covering the different tips and features of claude code. Before we do that, next

I want to talk about slash commands. So we talked about this a little earlier with slashmodels and slash init. You have a lot of different slash commands you can use inside of clawed code. But what's really cool here is you can actually create your own custom slash commands that do whatever you want. So let's build our own custom slash command. I want to build a slash command that does security reviews. So, I'm going to go and I'm going to say here, I want to build a slash command into clawed code that does a security review. Can you build me a slash security custom slashcomand? And I'm going to hit enter. And now what Claude Code's going to do is build its own custom slash command for security reviews that will review all our code and take a look at security as we're building out our code. So it is going in here. I'm going to hit yes. It is going to build out this command so that moving forward all we need to do every time we make a change is type in slash security and it'll review all our code to check for security issues. And you can do slash commands for anything you want. If you just want to do code reviews, security reviews, if you want to have it improved code, whatever you could think of, you can ask Claw to build out those custom slashcomands for you. I just really like the custom slash command for security/security. So, it's going to build that out for us. Anything you want to build, you just ask Claw to build it for you. So, what you're going to need to do to use the new custom slash command is you're need to refresh Claude code so it picks up on it. So, I opened up a new terminal. I did claude and now we're going to do slash security. And now we have our own custom slashcomand we're using here. And now it's going in and performing security analysis for us which is awesome. So now it is going through and again any custom slash command you can think of any kind of process you want to automate you can do that just by asking claude to build out that custom slash command for you. So this is going to do the full security analysis for us. So the next feature I want to show you is

sub agents. What sub agents allow you to do is basically have your clawed code AI agent spin up other agents to do work for you. And these agents can have very specific roles for very specific things. They get their own context. So it's like your own employees doing work for you. So one very simple sub agent we can have set up is a code review sub agent. And this is a sub agent that will optimize and review all your code for you. And it's going to have its own context. So, it's the context it's going to have for it is basically just everything about your code and how it works. And it'll be focused on just this one task, which makes it super powerful. So, I'm going to go into Claude here and I'm going to set up this sub aent. I'm going to say, can you build me a code review sub agent? This is a sub agent that will review and optimize all my code to make sure it's efficient. And I'm going to hit enter on that. And now Claude Code's going to build out this sub agent for us. And this is a sub agent. It will be able to spin up whenever it wants, whenever it makes changes to make sure our code is as optimized as possible. These sub aents are super powerful. If you're on a marketing team, you can set up sub agents for creating content, for writing emails, for writing blog posts, and these are going to be sub agents that are built just for those specific tasks so they become really good at it. For this example and for what I'm going to show you here, we're just going to build the code review sub agent out. But this is also a great thing if you want to go into Claude Code and say, "Hey, I want to build some sub aents based on what you know about my app. What are some ideas you have for sub aents I can build out? " I love using Claude for that. Just bouncing ideas. What slash command should I make? What sub aent should I make? And going in and having that conversation, having Claude Code build those out for you. As this is building, make sure to subscribe and turn on notifications as well. I put out multiple videos a week about building with AI and I'm sure they will only make you better vibe coders. So, I'm going to hit yes on this and it's going to build out that code review sub agent for us. And now at its own will, it'll be able to spin up that sub agent whenever it makes changes. So, it's always reviewing our code. All right, looks like the code reviewer sub agent is done building. Now, all you need to do to use your sub agent is ask Claude to use the sub agent. A lot of the time it'll use it automatically if it's doing something that it knows would be a good use for that agent. But if you want you could also just evoke it manually just by saying hey use the code review sub agent here. So now you have an entirely new AI agent to do whatever you need that Claude will use at its beck and will or when you ask for it to be used. So that is really awesome. That is sub aents. Again you can just bounce off claude code and say hey what are other sub aents I should build based on my application and it will build it out for you. Let's go into another new feature

that is really cool and that is output styles. This is a brand new slash command we can use to change the output style of claude. So if you do slashoutput style and hit enter on that, you out of the box get a few different output styles you can use. And basically what this does is change the way Claude talks to you when you're working with it. Out of the box you get explanatory and learning. If you are brand new to building with AI, I would highly encourage you to use the new explanatory mode. And basically what that does is it explains everything it's doing as it goes along. So you can learn what the AI is doing. There's also learning mode, which basically challenges you as it works to have you write your own code alongside the AI. Listen, if you want to write code, learn how to write code, go with learning. But I would recommend using explanatory mode. And what that will allow you to do is again claude will handhold you through everything it does so you can learn what it's doing which I recommend if you are brand new to coding with AI but you can also change this to whatever you want. So if I click escape here I go back to output styles you can see output style new. You can create your own output styles. So if you want to create an output style where claude code isn't so chatty and it gets directly to the point you can create a new direct output style. Or if you want to create one where it explains certain concepts in different ways, you can do that as well. This is completely customizable. So any way you want to customize Claude code to talk to you, you can do that. I recommend using explanatory mode, which is the default output style you can change to if you're brand new. But those are output styles. Really, really cool, new, interesting way to have Claude Code interact with you. So, let's continue

building out our app. And I'll give you a few more tips for prompting and how to actually build out the app. What I want to do next is implement the AI functionality into our app. So, I'll show you how to implement AI functionality. Again, in our note-taking app, we have a few different pieces of AI functionality we're going to implement. So, we need an API key from OpenAI to get this to work. So, if you've never implemented an API key before, go to platform. openai. com. Log that. Once you're logged in, go to dashboard in the top right and then go over to your API keys right here. And then from here, you can create a new secret key. Give this a name. We're go note takingaking and I'm going to click create secret key. And that will show us a key you can copy and paste. Once you copy that, you can go to enenv. local and we can go in here and then you just paste your key right here next to next public open AAI API key. Paste that and hit save. Once that's saved, you have plugged in AI functionality into your app and you're good to go. You can start testing this out. So, let's do this. Let's go back in and I'm going to come over here. I'm going to hit the AI. I'm going to say summarize note. Let's see what happens here when I click summarize note. Let's see if our AI functionality works. Summary. And it summarizes our entire note for us. That's amazing. Let's go in here. Let's try a few things out. Here is how the New England Patriots are doing. Now, let's autocomplete this. Let's do continue writing. Let's see what happens now. Let's see what the AI will do. Here's how the New England Patriots are doing. The New England Patriots have shown great resilience this season with their strong defense and precise offensive plays. Despite facing tough competition, they have managed to secure important victories and climb up the rankings. So, look at that. It autocompleted our notes for us. The AI works. It really is that simple. We had Claude Code build out the AI functionality. And we took our API key from OpenAI and we put it in. I like using OpenAI for the API stuff. It makes it really simple to use. I've had very little issues using OpenAI's different APIs. Uh but there you go. That's how you get the AI functionality working in your app. I'm going to give you another tip. When it comes to doing more complex things in your app as well, I found this to work really well, especially when you

get into bigger and more complex functionality. I like to have a co-pilot AI working with me. And this is how it works. So if you go into any AI you're paying for right now, even if you're not, you can use gpt5 for free right now. Go to chatgbt. com. Open up this window, pull it to the side. So you have claude code in one window, you have chat GPT in another window. I like to use a second AI as a co-pilot for everything I'm doing. So if I come back here in a claude code, I go into planning mode and I talk about another piece of functionality I want. Let's say I want the ability to draw in notes. So, I'm going to go in plan mode and send that. I want the ability to draw in notes. What that's going to do, obviously, is build out a plan. But what I like to do for really complex functionality, even though this really isn't that complex a functionality, is I like to take the plans and doublech checkck with a co-pilot AI that plan. And a lot of the time, what's going to happen is that co-pilot AI will actually come up with new and interesting ideas for implementing that functionality. So, here we go. We have a plan built out for implementing drawing inside of our notes. Let's do this. Let's take the plan. Let's highlight it, copy it, and let's go into our AI co-pilot here, and let's explain what we're doing. I am building out a note takingaking app where I want to implement drawing functionality. Here is the plan the AI came up with. What do you think? And I paste in the plan. and I hit enter and I'm just going to have this other AI check it over and sometimes what it does is it actually comes up with recommendations on how to improve the plan, right? The AI landscape is changing all the time. Every other day there's a new better model. I like to open up whatever the best model is at the moment. To me, that's GPT5. And just have them review plans that Claude comes up with. And a lot of times it'll come up with little tiny improvements it can make to the plan. So it says great start. This is a sensible plan using Excel Excaladraw and other plugins is a welltrodden path. And then it gives me a bunch of recommendations. And now here we go. What I change in your plan. We can copy and paste this and take that and paste it in and say another AI came up with some changes. And paste that in. And now we have two AIs working together coming up with better ideas and better plans to build out better functionality. I find that using these two AIs to bounce ideas off of helps the plans improve and helps us get way better code. And yes, it might take a little bit longer because we're doing two AIs here. But I find actually get a lot of time saving by having the AI come up with those better plans. So this is a really important strategic step to use on any of your complex steps. So, a

couple more things I want to go over with you. Let's go over prompting tip. So, prompting is everything, right? If you put in the right type of prompt, if you ask Claude to do things the right way, you'll get much better results. Couple prompting tips here. Number one, be specific, right? So, let's build out that drawing functionality. So, I'm going to say I want to give the user the ability to draw in a note. I want it so they can change the color of the pen as well as the thickness of the pen, too. I'm being very specific. I'm being specific about exactly what I want the change to be. The more specific you are, the better it'll be. And also giving examples is really critical, too. I'm going to say I want it to behave just like Excal. So, Excaladraw is a really awesome app online that lets you to draw on your screen. And so, I'm giving it other examples as well. You want to give it examples of other sites. In fact, you can take it a step further and even use screenshots. So, I pulled open Excaladraw here. If I actually screenshot this so they see what the UI looks like and then I go back into cloud code, I can actually paste in that screenshot and now it's going to have that as context. So when building out functionality, when talking to Claude Code, you want to include as much detail and as much context as possible, including screenshots. Anything you want to build out, if you have examples of what you want it to look like, screenshot it and put it in, and that'll give you way better results. So, be detailed, include context, use plan mode as much as you can, and have that side chat AI up on the side so you can bounce ideas back and forth between the different AIs. Using those tips helped me build Creator Buddy, which now has thousands of users, is at 300K ARR. It helped me build and launch that app completely by myself with no help at all. And now it's production grade and making a good amount of money. You can do the same thing if you use these tips and use all the features I showed you as well. Claude code is spectacularly powerful. And if you learn everything I showed you here, you go back, you review the parts that maybe you don't understand as well, I promise you will come out of this being able to build anything you want. If you learned anything at all, make sure to leave a like and it lets me know I need to build more Claude Code content. And also leave a hype if that's an option for you as well. That helps with the algorithm a ton. Let me know what your favorite features or tips are in the comments section below. I'd love to hear what was the most helpful from this video. All I do is create amazing videos about AI. So, subscribe and turn on notifications.