Building 5 AI Apps In 30 Minutes (ChatGPT + Lovable Tutorial)

In this video, I'm going to go over five AI projects that you can start building today using ChatGpt and Lovable. I tried my best to pick a diverse range of projects, including a web app, a dashboard, internal tool, mobile app, and an agent. — I've added Call Mom to your evening routine. I notice you're more likely to complete calls after 7:00 p. m. Should I remind you then? — And for each project, I'll show you three levels of increasing complexity. For levels one and two, with the right prompts, which I'll also show you, you can implement them relatively easily with no code. And for level three, you might need to add a little bit of code to modify things if you're up for it. We'll be using chat tobt to think through what we want to build and to craft the initial prompt. Then we'll be using lovable to implement. As per usual, it's not enough for you just to listen to me talk about stuff. So there will be little assessments throughout the video as well. — Hey Fern, I know we're going to do

today. All right. So before we dive into the nitty-gritty of each of these projects, I do want to do a crash course of two frameworks that are extremely helpful for building apps using any type of AI assisted coding. The first framework is called the tiny ferrets carry dangerous code framework. And it's dangerous because you could potentially mess up, reveal sensitive information, accidentally expose your API keys, lose over your work because you don't understand version control, etc., etc. So pay attention. Tiny ferrets carry dangerous code. Stands for thinking frameworks, checkpoints, debugging, and context. Thinking as his name suggests means thoroughly thinking through what it is that you actually want to be building. And the best way of doing this is coming with a PRD, a product requirements document. Or actually what is more fashionable these days, we call it a PRP, which is a product requirements prompt, which you'll be inputting into your AI assisted coding tool. Anyways, doesn't really matter. And what goes into your PRP includes the target audience of the app you're building. What's the customer experience supposed to be like? What are the core features? Potentially a couple mock-ups. What's the vibe you're going for? What's the text stack? Basically, the more effort that you spend thinking through what you want the app to feel like for your target audience, the clearer it is that you can communicate this with your AI and get better results. And step number two is frameworks. Chances are, whatever it is that you want to build, some variation of it has already been built before. And there already exists very efficient and robust packages and frameworks that have been developed to build these things, which by the way, your AI coding tool has been trained on as well. So instead of forcing the AI to come up with something like completely from scratch, it's actually much better if you can point the AI towards the appropriate packages and frameworks for it to build whatever it is that you want to build. For example, React for front end, Tailwind for styling, and 3. js for 3D animations and graphics. Don't worry if you don't actually know what the frameworks are. The prompts I'm going to be showing you later also walks you through these steps. But let's finish the rest of these steps first. Step number three is checkpoints. Always use version control. Some apps already have version control built in, but again, GitHub is considered the gold standard. Then there's debugging. You'll be spending a lot of time debugging, so be prepared for that. You want to be make sure that you're copying the detailed error messages into the AI and be methodical and patient with the fixes. And the last part of the framework is context. When in doubt, always try to add more context. More context, more specific, more desirable results. This includes mock-ups, examples, screenshots. Whenever you have an error, provide the AI with highquality, clear context to get the best results. The second framework I'd like you to realize is that you're ever only in two modes when you're doing AI assisted coding. And that's either implementing a feature or debugging. And when you're implementing a feature, you want to be providing context, mentioning frameworks, and doing incremental changes. And when you're debugging errors, you want to be understanding the structure of your codebase, providing error messages, and additional context like screenshots. Got it? Okay. I'm

going to put a little assessment on screen now for you to answer. And by the way, don't worry if you don't exactly understand what I mean by all of this because I'm going to be showing you what these frameworks look like in action throughout the rest of this video. And if you actually do want a much deeper explanation and more thorough explanation of these framers and a lot more, you can check out the video that I have linked over here that goes into a lot more details. — Calculations complete. — The calculator.

— Project one is called the everything calculator. You may not have thought of this before, but a surprising number of things in life can be boiled down to a calculation like your net worth, how much you should be saving, mortgage rates, renting versus buying a home, workout plan, how much to eat, what to eat, travel budgets, how much to charge for a freelance project, how much wood you should be cutting if you want to build a cabin in the woods for some reason, how attractive you are and what you need to do improve it, etc., etc. You get my point. So that's why our first project is building a web app where anybody can come in and build any type of calculator for anything they want. It's useful for your daily life and for work if you ever need to repeatedly calculate something. And if you have clients, for example, you're like a freelancer or you just, you know, have clients at your job. Instead of people repeatedly asking you questions to calculate something, you can instead point them towards a calculator so they can do it themselves and leave you alone. Level one of this web app simply allows the user to describe any type of calculator that they want and the AI will instantly build it with a clean interface. Level two increases the complexity a little bit because we don't want to just have one of these calculators. We actually want to create a platform where people can add all types of calculators. We want people to be able to browse the different types of calculators, save the calculators that they like, and read the calculators in a community marketplace where there are user accounts. We want users to have their own login, their own personal accounts where they can go in, create the calculators that they want, browse the different types of calculators that other people create, save their favorite ones, and rate calculators in a community marketplace. And level three, we're going to make it even more complex by making it also a social calculator platform. We want people to be able to share their favorite calculators across social media by using the links or even a QR code. We also want to be able to embed them into different websites. Maybe you're writing a blog article and you want to have like a specific calculator as part of that blog and maybe even build a creator following of their favorite calculator. You're like a calculator creator. So to create these things, we are not going to actually jump into it and just start building immediately. We want to go through that first step of the tiny ferrets carry dangerous code framework which is thinking specifically coming up with a PRP that basically lists out all the different components very clearly to build this app. This will help both us and the AI be able to conceptualize exactly what it is that we want to build. And we're going to do this by using chatbt. Okay, so hopping onto chatbt here. I'm going to make it a little bit bigger. Okay, so this is actually a meta prompt, which is the prompt that's going to help you develop the product requirements prompt. You with me? Okay, so the reason for this is because yes, you can technically, you know, make your own product requirement prompt, but I find that if you use a prompt like this, it guides you step by step to answering all the questions that you need in order to finally output a really good product requirements prompt to use as input into your AI coding tool, lovable in this case. I promise this is all going to become crystal clear in just a moment. So this prompt says, "You are a friendly AI product strategist inside Lovable, the collaborative AI product builder. Your job is to help someone, usually a founder, developer, or a product thinker, clarify their product idea. You'll do this by asking one question at a time in a supportive, casual way. The goal is to co-create a clear product requirements prompt that lovable can turn into a scope plan for development. " I will link this metaprompt in the description as well. So it's just going to introduce yourself and it's going to ask me, "What are you building? " Level one, I want to build an everything calculator. where the user can describe any calculator they want and it will be built. Then I'm going to put level two. I want it to be an universal calculator platform where users have their login and can browse, save, and rate calculators in a community marketplace. Then I'm going to put level three. I want the ability to share the calculators via social media using links or QR codes also to embed on websites and even build a creator following. And for level three, I'm going to put for future because we just want to start off with building level one and level two. Remember that framework, we're either in implementing mode or we're in debugging mode. Right now, we're in implementing mode. And one of the tenants of implementing mode is that you want to be incremental in your changes. So that's why we're only going to try out with level one and level two. In fact, if this doesn't work out, we would actually just go back and default back to level one. I find that levelable can usually manage level one and level two at the same time. But for some reason, if it actually can't do that, I would actually just default back to level one. What problem does this solve? What's the user journey like? What are the key features starting with level one? What platform it is? This was actually really helpful in helping me refine what it is that I wanted to build and it helped me think through what are the key features that I wanted in the minimal viable product. And in the end, Chajipy was able to give me this PRP, the everything calculator. It includes the idea, which is a cozy AI powered web app that lets anyone describe the calculator that they want and have it instantly created. It's perfect for freelancers, individuals who do repeated calculations or want to share tools with clients. It has the user journey and the core features of level one and level two, which is what we're going to be starting off with, and with level three for the future as well. It also gives us a suggested stack with the front end being React, Vite, and Tailwind. So this is actually the stack that lovable uses and AI is going to be open AI which loable also has an integration with the math logic. So there are the packages I was suggesting and for O and DB it's going to be superbase for O storage and edge functions. Again there is a integration within lovable already and state/ UI is going to be stat and shad CN UI for cozy styling. These are also well optimized in lovable. And now we're going to hop into lovable and go into the implementation mode by pasting this initial PRP and getting started. Remember in the build mode we want to be providing context, mentioning frameworks and making incremental changes and these are all incorporated already into our PRP. I also do have agent mode turned on. We want to connect to Superbase which is the back end and it will allow us to have tables to store information and also do things like authentications and lay the groundworks for AI integrations. Now we're entering into the debugging mode which is actually going through and making sure each of the features are actually working the way that they should be. Remember, in debugging mode, we want to be understanding the structure of the project, providing error messages and screenshots when something doesn't work. Lovable does actually have a code viewer, so it's actually really handy to understand the structure of the project and how all of the files are fitting into each other. You don't actually need to write the code yourself and really like know exactly what's happening, but it's really helpful to understand how things fit together when you're debugging. What also helps is that you can actually turn on chat mode and then ask lovable could you describe the structure of this project to me that is what the files are and how they are fitting together at a high level and it will show you things like what the code entry points are which each of these files mean what are the files relating to styling and design which are the ones for pages and routing utilities at hook and config files and also shows you how everything fits together as well. This is really helpful in learning how app development works and I really wish I had this when I was learning how to code. Anyway, so you keep going through this process and in this case lovable asks us to check over some of the SQL code before it continues. This is also a great chance for use the chat function where you can ask it like what is it that the SQL is saying here and we notice that it has all of the like AI features involved in it but doesn't have all the calculator stuff implemented. So that's why I also ask it to include all the calculation logic in the SQL. And once we connect that, fix a couple errors. Lovable was pretty good at figuring out how to fix it itself. And voila, you have a functioning web app. I hope the process of how you build these applications starts making sense now. Also keeping in mind the principles of good AI assisted coding, the tiny ferrets carry dangerous code framework. Now at this point where we have a functional app, this is where the checkpoints part of the framework comes into play. So lovable is great because it already has a relatively robust version control system, but the best practice is still to use git and github which lovable also has an integration with. So it's super simple. All you have to do is click on the GitHub button. Just follow the flow to get the

integration. Moving on to project number two, a freelancer toolkit. — Bam. Whoops. What the invoices, receipts. — Invoice 1347/2, amount $3. 88. Check number8429 clear. Invoice number 1347/3. If you have ever done freelance work before, you will know that just like the admin stuff actually takes a significant amount of time. Things like writing proposals, generating invoices and payment links, and following up on the payments when people decide to not pay you. That is why we're going to build our very own freelancer toolkit. Level one is just to be able to generate the proper documents. We want to start off at being able to generate professional proposals, contracts, and invoices from a simple form where we describe the kind of contract work that we're doing. Level two is when we want to make it into a client management system. So, we want to be able to store all these documents that we generate. We want to store client history, track invoice status, manage project timelines, and generate Stripe payment links for people to pay these invoices. And level three, adding on even more complexity, making it actually a smart freelancer assistant that's able to go in and analyze everything that you've done and give you suggestions like, you know, there's a hole in the contract over here, maybe you're undercharging for your services, and send you reminders when people don't pay you. and maybe even have it automatically send out an email and reminding people to pay you if they haven't paid you in like a week. After we go through the process of the meta prompt on chatbt, we end up with the freelance toolkit product requirement prompt for level one is a document generator and it has the basic features like generating proposals, contracts, and invoices via simple form inputs. Level two including the client management system. and level three for the future, the smart freelancer assistant where there's going to be more complexity with it. Gives us the user journey and I suggest the stack that we're going to be using. Copy that. Go into level and get started. We have a nice looking UI now and go into building mode. We're going to connect superbase as the back end. So, we're able to have authentications and be able to store data in the databases. One of the features that we want to implement is the Stripe integration. Specifically, when we send an invoice to a client, we also want to attach a Stripe link where they can directly pay. Levable does have a Stripe integration as well. So, all you have to do is ask it to connect to Stripe. And we're following the flow over here to get the payment links and we're embedding that into the invoices, which is pretty cool, isn't it? Actually, if you've ever made your own products before through like normal coding, you know that implementing like monetization and these kinds of integrations actually usually takes a significant amount of time. So, this was genuinely pretty impressive that we could just integrate Stripe and have monetization like that. But don't forget to connect to Git and GitHub so we have checkpoints and version control going on. So, at this point, I'm also going to go in and change the UI a little bit as well. especially since this is an internal tool that we're using. I don't really care that much about the way that it looks as long as it functions, which is why I'm waiting a little bit later until I get it to work. This is actually a general tip as well. You usually want to get the whole thing to like actually work properly before you go in and start fixing all the little details of things. That's just good engineering practices. To change the UI lovable, it's actually really simple. All you have to do is click the edit button and you can actually select like where it is that you want to change. Ask for a quick change. Make this button purple. Press enter and yay button is now purple. Now we can keep developing adding more features from level three and you want to ask Lovable to add the feature where you have an OpenAI AI assistant that's able to comment on all the information that's in your database to give you those smart suggestions. We want to connect to Google Calendar so we're able to sync the calendars and have the invites send automatically as well as sending reminder emails when people don't pay by going through the Gmail API. This will be best done by using Superbase Edge functions. This allows you to connect to the Gmail API and be able to schedule reminders for people. You can actually also connect to the calendar API too where you can actually put in calendar invitations like little automations that run in the background of your app without you having to build out an entire intense server. Edge functions are really helpful. Anyways, we can prompt lovable to do this for us and also connect to OpenAI as well if we want to generate some AI powered insights to help us in our freelance management like being able to flag projects that might be at risk or predicting payment delays or even giving us suggestions if we might be undercharging. And voila, here we have the application. That is pretty freaking cool.

Next project, we're going to do something a little different. We're going to be building a mobile app, specifically a mobile drawing coach. I have always wanted to learn how to draw, but every time I try to draw something, like I find it very discouraging because it just looks terrible, but I don't exactly know how to fix it either. I watch a lot of YouTube tutorials and I can kind of like replicate whatever it is that they are drawing, but I find it very hard to like implement these things to something that is like even slightly different than whatever it is that they're showing me. Like I want feedback that is specific to what I'm drawing, like a personal art teacher that's able to look specifically at my work and teach me how to improve. And the reason I wanted this to be a mobile app is because I want to be able to like take pictures of the things that I'm drawing or even just like you know showing it even having like audio communication without having to like show it to my laptop for example. I think it works it just works a lot better as a mobile app. So level one is just going to be a simple drawing evaluator. Being able to take photos of my drawing and then getting AI to give me specific feedback on it and also having like YouTube links for tutorials for me to look at. Level two is going to include a progress tracker. I want the app to be able to save the drawings that I've done so that I can see the improvement over time to be able to see how my skills are changing, being able to assess my skills and help me craft specific drawing goals as well. And level three, I wanted to be even more interactive instead of just like taking the photos and getting feedback. It would be really cool if it has like real-time speech function and also like a video function. So, it's able to coach me through exactly what I'm drawing as I'm doing it. I wanted to also be able to directly analyze my drawing and annotate on top of it. like being able to say things like in this portrait that you're drawing, the nose is a little bit crooked over here. So, we wanted to like, you know, tweak that slightly. This one is quite ambitious. I'm going to need the help of some extra APIs and tools, I would think. All right, going through our meta prompt, we end up with this PRP called Sketch Buddy, a mobile app where beginner anime artists can upload their drawings and get AI powered feedback, track their progress, and build confidence through a cozy sketchbook experience. I did start off with anime specifically cuz I wanted to get that like specialized thing to work first. Also because I like anime, not going to lie. Okay, so we have the user journey where the user opens the app, takes a photo of their drawing, gets personalized AI feedback, rates their mood and confidence, receives progress insights and earns achievements, sets drawing goals and tracks growth over time and can log in to save data and optionally share progress on social media. So this is going to be levels one and two, which we're going to start off with. So we have the target audience that we thought through the core features including mobile camera upload, open AAI vision API feedback, mood and confidence check-ins, goal setting and achievement system, visual progress tracker, secure user login with superbase o and social media sharing milestones. And we have the tech stacks over here including median. co for the mobile app conversion. You have superbase open vision API, mobile camera API for capturing the sketches and a progress tracking engine. And for level three for the future, we also have things like web speech API for voice feedback, Canvas API for being able to annotate voices directly. Copy that and start that off. So this one did take a little bit more time because it has all these like API integrations which took a while to debug and make sure that it's working. Switching over to code view and then seeing that it's actually implementing things that it says that it's implementing was really helpful. And I use median. co to be able to convert it to a mobile app. And voila. Don't forget the checkpoints. Connect to get and GitHub. Then if you want to level up to level three and have that like realtime interactive functions, we need to go back into build mode and prompt lovable to connect that web speech API and the canvas API for the AI to be able to annotate directly. I am very grateful for the OPI integration. — Hello. Welcome to your interactive drawing coach. I'm here to help you improve your drawing skills. I can see you're drawing a house. That's a great choice. I notice you have a nice triangular roof and what looks like a door. Your basic house structure is solid. Try adding some windows to make it more complete. And consider making your lines a bit more confident and steady. — Ooh, spreadsheets. Yum, yum. I included some timest. Next project is a personal

finance dashboard. I know, I know you might be thinking, "Oh my god, Tina, that is so overdone. " And okay, you're right. It kind of is overdone, but hear me out, okay? This is going to be specifically for people like me that have a lot of trouble having the discipline to track things and being able to like look at spreadsheets. Like, I hate spreadsheets. I also need a lot of motivation for me to like get my personal finances in check. Like, I need to have like the goals visibly there and constantly being reminded of these to be able to be like, "Okay, fine. " like I'm working towards a goal. That's why I have to like keep doing this. So, I guess I want to make a personal finance dashboard for people with poor impulse control, hates spreadsheets, and has terrible memory. Let me know in the comments if you relate to this. Anyways, so level one is going to be a simple statement analyzer. We want to keep this feature super simple, just the ability to upload any statements, be it bank statements or credit card statements, and for AI to be able to analyze our spending and give us some personalized advice. Like, Tina, why is it that you're buying another keyboard? because it's white and glowy. Moving on. Level two is a real time tracker. So, in addition to having that statement analyzer, we want to have a database that can maintain all of the past records and be able to get real-time information from our bank statements and our credit cards as well. So, we don't need to like actually upload these anymore. We also want to have some dashboard vibes like having some breakdowns and visualizations of our spending patterns and some push notifications that can give us reminders and information about our spending, too. And finally, level three is when we want to have something that is even more personalized, a actual AI finance coach. We want to get daily spending summaries delivered straight to our WhatsApp so we can consider our choices more carefully and have conversational finance advice and be able to talk with our AI and try to understand like where it is that we can be improving. Okay, so after going through our meta prompt and thinking through everything, we have this PRP for a product called Spend Buddy, an AI powered ADHD friendly web app that makes budgeting fun by turning your bank statements and live spending data into cozy gamified insights and personalized financial advice. User journey involves user landing on the site, uploading a bank statement, AI analyzing the spending, categorizing transactions, and giving clear tips. User sees a cozy dashboard with breakdown, spending trends, and gentle advice. Gentle, gentle. They're invited step by step to connect their real bank account via plaid. So, we want things to go really, really slowly. Once connected, they get live transactions, tracking, and updated visualizations, push reminders, nudge users when they're approaching category limits, and optional budget goal suggestions pop up based on spending habits. Going through this process helped me realize that I wanted the push notifications to be the way that you guide somebody into connecting their bank accounts and doing things step by step. as opposed to just having like everything there like some of the other like finance apps that are there which is like really overwhelming in my opinion. We want to ease people in. So yeah, you got your core features and the text stack suggestions here. So lovable superbase for o database and edge functions. Open's vision API for the PDF and image statement analysis. Plaid API for the real-time financial data. Recharts for spending visualizations and push notifications for timely nudges. This is also going to be done using superbase as well and post hog where we're plausible for lightweight analytics. We copy this. We paste it and we get started. So we're going to build mode and we're connecting superbase for database authentication. And in this case we want to prioritize the push notifications as well using the superbase edge functions. Now going to debugging mode fixing a few errors making sure that everything is integrated and implemented the way that it should be. And I noticed that initially if you upload a PDF with your statements, it doesn't actually give you the information that is in that statement. So I double check that the OpenAI integration was actually integrated properly and ask it to actually use it to be able to analyze that data as opposed to just make something up. See, in debugging mode, you really have to be very systematic and thorough to make sure that things are working the way they should be. We also want to connect the Plaid API to be able to get real-time data. And we're using Rechart to generate some graphics. And voila, a functioning app. By the way, I recently did a free webinar called How to Prepare for Careers in the Age of AI in collaboration with IBM Skills Build. So if you want, if you feel like it might be helpful, you can check it out at this link over here.

Next project is going to be a full-blown AI agent, specifically a task manager AI agent. I am a rather chaotic person. If you're into MyersBrig, I am like P to the max. That is why things like to-do list don't tend to work very well for me. I will write down the things that I should do and then proceed to not do any of them. It also doesn't help that my job is also like very free flowing. Like there's a lot of creativity that's involved and I need like specific energy levels to be able to do certain things. and my schedules are also not set. Like things just kind of like pop up all over the place and my day-to-days don't really look the same either. So that's why I want to have an AI manager agent that I'm able to just like brain dump all of my problems to and for it to like use data about me like my energy levels like what's happening and like a lot of like different data and factors to help me prioritize like what it is that I should be doing. It give me suggestions for how to manage my energy throughout the day. Now if you have watched my building agents video and if you haven't it's linked over here you will know that you can think about agents as having six different components a model tools memory and knowledge audio and speech guardrails and orchestration. I don't know this is like just like a Asian thing where we do this as six orchestration to be more clear. And our AI task manager agent is going to have all of these components. Level one we're going to keep things simple and just going to be a smart task list as the core feature. We want to have people be able to type things, but also through audio and speech be able to just like dump everything to the AI model and for it to be able to take that information and come up with the specific task with some priority suggestions as well. Like what is actually important and what is not. Like for example, filming this video is probably more important than buying an orchid. Level two, we're going to start integrating additional data sources. For example, like health data like from Apple, like how many steps you've already walked today, mood check-in, energy pattern analysis, and all of this. Of course, like you know, we want to collect all of this data through time as well. So, AI is going to be able to give you good suggestions for which task would be able to fit you depending on your mood and your energy levels, both physical energy and mental energy. Actually, speaking of which, a lot of my friends have aura rings now. Let me know in the comments that you do. Like I wonder if I should get one of those and integrate it as well cuz that seems to have a lot of data sources within it like sleep data like energy, mood, I don't know what is that the aura ring tells you but I feel like that would be quite helpful to integrate as well. Anyways, that will be level two. At level three, we want to have a full-blown productivity coach. We want to be able to have real-time conversations with the AI in addition to just like audio inputs. And we want to integrate our calendar as well. So it's able to take calendar information with the meeting information that's there and also be able to time block for you too. All right, same as last time, we're going through the meta prompt. Although, specifically this time, I also did mention the six components of an AI agent. So, we're making sure that we have all these six components as well. And we ultimately end up with this PRP called Brain Dash, a smart adaptive task manager that prioritizes your to-dos based on how you actually feel, not how you should feel. Holy it just got really dark. Apparently, it's like rainy season in Hong Kong. I've never actually experienced this before. That's scary. I'm going to go turn on the lights. Okay, I am back. It's like literally 300 p. m. right now. Very interesting. Okay. Anyways. Okay. Yeah. Yes. So, I had target audience user journey. Your user opens the web app. They dump tasks via text or voice. The AI categorizes and prioritizes them into a smart task list based on energy type and urgency. Users can optionally log their mood or energy for better suggestions. The dashboard shows a reorganized energy aware to-do list with helpful nudges. A level two user can connect health data like sleep, steps, etc. for smarter suggestions. So it has our core features and the suggested stack over here. So front end we have the lovable web app developer. So AI we're using open GPT4 AI integration. Voice input will be the web speech API. Uh backend and o is going to be superbase and health data will be apple healthkit and Google fit API. Data logic and external call superbase edge functions. So this will be for the calendar integrations. What is cool is that levelable actually has a workstream for specifically building AI agents and orchestration projects and it goes into a lot of detail as well for how it is that you can build AI agents specifically. So we are going to paste our PRP and have it start doing its thing. Continuing on with implementation mode, the key things here is having that voice function using the web speech API and the open GPD4 integration. So after alternating between implementing and debugging mode, we have a functional application. Yay. I've added call mom to your evening routine. I notice you're more likely to complete calls after 7:00 p. m. Should I remind you then? All right. Thank you so much for watching until the end of this video. Let me know in the comments which of these projects that you found to be the most interesting or which project that you want to start building yourself. Now, I hope this was helpful. I tried to really show a diverse range of different projects and show you how it is that it works using chatbt and lovable and different integrations as well while always keeping in mind the two frameworks and building it by following the principles of AI assisted

coding. So before I end this video, here is another little assessment. Please answer these questions and put it in the comments below. Thank you so much for watching until the end of this video and I will see you guys in the next video or live