I used Cursor to build an app on the train, made $30K, and quit my job.

202.86k views2956 WordsCopy TextShare
Starter Story
This is how Paulius Masalskas built a $30K app using AI. Start your 7-day free trial with Semrush →...
Video Transcript:
I prompted my way to $30,000 without writing a single line of code. This guy made $30,000 from an app he built on his morning commute. How?
Two tools, Cursor and Bolt. I think a lot of people make cool stuff with Bolt and Cursor nowadays, but they don't monetize it because they need In this video, we'll go over the wild story of how Polus just built, launched, and marketed a SAS product by himself and got traction in about 30 days. you probably have like a winning idea already that you could just prompt your way and start building.
Why you should definitely tune into this video? Well, I had Polus share with me his exact process on screen of how he builds fast with AI tools, how he creates beautiful designs and how you can too. And how making money and marketing your app is as simple as a couple tweets.
All right, let's get into it. I'm Pat Walls and this is Starter Story. Welcome, Polus, to the channel.
Thanks for coming on. Tell me, what's your story? My name is Polus and I used AI to build an app that made me 30K.
It's an app that matches startups with influencers and I built and launched it 7 months ago. It's got over a,000 users at the moment with over 350 paid users. I used Bolt and Cursor to make it and I use Framer for design.
I did it all myself without needing a team all in my daily commute. Nice. Cool.
Before you made 30K with your app, tell me a little bit more about your background, your story as an entrepreneur. It started when I was 18 and I needed to make money to get my way through college and the only job that I could get was door to door sales and one day I ended up knocking on the wrong door and someone literally grabbed me and held a knife to my throat. After that, I just had enough and I wasn't really employable as a student.
So, I dove into every side hustle that I could. So I did web design, I did copywriting, sales funnels. I became kind of like a generalist.
It paid enough to get my way through university. When I was in university, I did computer game development. But funny story, I actually completely sucked at code.
I was very visual and I just couldn't understand it. But now AI can actually code for you. And so the limitations that I had before are kind of removed.
AI can do the heavy lifting in terms of code and kind of patch up the area where I'm not the best at. Nice. So tell me what got you into building online and and realizing that you could, you know, make money online.
So I was going through kind of a rough patch because I tried all these different business models and I wasn't making enough money to break free from a 9 to5. I got really frustrated one day that none of the things that I did really got me where I wanted to be. So I was pursuing creatorled services and products just work with creators and the idea of a database came to my mind and I just started building it out because it's something I'd use myself and I figured with AI I could turn this into a fullyfledged SAS if enough people wanted it.
So I really just gave it a spin as kind of like experiments and it did pretty good. So tell me what it felt like to finally launch and have this validated idea and have it make its first dollar. Tell me about that.
So for months before launch, I was building this database. It was a lot of effort and I had no idea it would pay off. So when I launched my application, I remember I was sitting with my girlfriend and we were just having dinner.
I pull up my phone. I just see sale after sale. I was like, "Okay, how long is this going to keep going for?
" And that night got about like 20 or 30 different sales. So it was very nice feeling that just motivated me to just keep going and pursue this further cuz now I felt like that was a validation that this could be a real product. Okay.
So can you share your step-by-step playbook on how you build MVPs with AI? If I'm a complete beginner, I would recommend everyone to use Perplexity. It's what I did.
I just asked Perplexity because it has the most upto-ate information. So it has all the documentation, anything that you want to any tool, any library, just tell it you're a complete noob and absolutely don't know how to do anything and it'll give you really detailed step by step because it's deep research. It'll pull up a long document that you can reference and just follow along.
The next step is I'd pull up Bolt and just take it one step at a time as well. So I would implement the first thing that Replexity says. So it could be like the dashboard, importing the project, cloning a GitHub repository if there is.
Once I'm in there, I just keep prompting it and if there's errors, I just throw the error back at the AI. It fixes the error, go onto the next thing, and I use Bolt to a point where I get a nice looking MVP with the functionality. And then I take that, download the project, I put it into cursor.
And here is where I hook up like superbase. So it writes all the scripts to connect the back end. and I get clerk off and that makes it very simple to plug and play the authentication.
And this is all steps that perplexity can provide for you. So you can just ask questions along the way and it'll give you some solutions. Replexi is a great starting point.
Bolt is a great way to make the MVP and then you move to cursor to dial in the details. So you're 80% of the way there and cursor will then just get you to the final finish line. have users authenticating.
You have a backend with real data and with a bit of prompting and some scoring, it'll make it secure as well. Okay, Polus is proof that it's never been easier or faster to build an app in 2025. Tools like Cursor and GPT4 make it possible to go from idea to product in a weekend.
But if you don't understand your customer or what they're searching for and how they describe their problems, then you're just building fast in the wrong direction. That's why we're excited to partner with Seamrush for this video. It's one of the best tools out there for figuring out what people actually want.
You can plug in an idea and see what people are searching for, what's getting traffic, and where the gaps are. It's got 26 billion plus keywords across 140 countries. And yeah, most people think that it's just an SEO tool, but trust me, it's way more than that.
You can use it to validate your idea before you build, find high intent keywords your competitors are ignoring, or even spin up landing pages that match what people are already looking for. I'm going to show you how you can find successful business ideas just like Polus is in Semrush with one search right now. Go to Seamrush and find their topic research tool.
Search any topic or niche. Let's just do Tik Tok influencer since that's kind of similar to Polus' business, but you could literally just search anything. And I'm going to open some of the cards that look interesting like this one.
Tik Tok influencer marketing. On here, you can see all the questions people are literally plugging into search engines. These are the real problems people have and are actively looking for a solution.
I like this one because it's not a super high keyword difficulty and there's high volume of people searching for it. So maybe there's some lowhanging fruit in there. And look right here, Tik Tok influencer search platform.
What's the best way to hire Tik Tok influencers? Polus' business can literally be tied back to a single page in Seamrush. And that's just crazy powerful if you ask me.
Right now, they're offering a free 7-day trial to try out all 55 tools in the platform. Just head to the first link in the description if you want to try it out. All right, let's get back to it.
We talked about the code building an MVP. Let's talk about one thing that I think is really cool about your stuff is how good it looks. How do you use AI to design amazing looking websites?
It's really the simplest it can be. First thing I do is I pull up Framer and I pick a free template. So any template that you see on there that you like.
It's simple enough and clean for you to edit. And then you just have to pick a nice font and a nice button. And then the rest just needs to be simple and clean.
The most important part is just to get out. Focus on just editing the template really quick and just put it out there. Cool.
Based on what you built and what you've learned working on lots of marketing stuff and also on your own, what do you think is like the most important thing to focus on when you're creating a good landing page and a good design? So, I focus 80% of my time on everything that's above the fold. We'd call this the hero section.
This the first thing that people see when they open the website and has to have the your full message just out there and people really need to grab an understanding of what it is within the first couple seconds. Anything that you can save them time with, save them money. Anything that solves a painful problem, you should have in a headline and a subheading, and then just a big call to action.
All right, so we talked about landing page design, which was awesome, but what about UI design? When you're building an app, how do you use AI to design UI and UX? When I'm building it out in cursor, you get the basic thing done and then you add some things to it.
So, the more features you add, the more things you work on, it's got to stay clean. and it's got to stay cohesive and you got to make sense. So for everything UI related, I just ask it to make it clean, functional, and modern.
And I try to have it use like shad CN components and they're all free. But when I have ideas and when you have ideas for how you want onboarding flow to be or some other elements of the app, what I would suggest is just creating something in Figma, you can doodle if you want. You just plug it into cursor and just explain the behavior that you want and then it'll spit out a nice looking page for you.
All right. Well, thanks for sharing that. Let's dive into the marketing side of things cuz uh seems like X Twitter has really been working well for you.
Tell me about that strategy. Show me a tweet that really took off for you and and let's talk about that. So, this post did the most in terms of numbers.
It got close to 500k impressions. And I think the reason it worked is because I found an angle to attach it to trends happening in the space. A lot of people when they're building in public never go viral because they never join the bigger conversation and human attention span is limited.
So it's 100 times easier to just bring your ideas to where the focus is already happening. So this post had you know nice simple visual demo has like real like raw human like reaction but most importantly it tapped into the main debate at the time which was is AI coding actually good enough to build a full SAS. Thanks for sharing that.
I'd love if you just shared a little bit more about the bigger strategy here the bigger thing which is build in public. I love if you just talked about that from you know kind of strategy perspective or what you love about building in public and why it's worked for you. So for me what's worked is just shipping often.
don't just have like one big video release like a lot of VC startups. So, for example, I tapped into the influencer conversation that was happening at the time. I saw Mark Lou posting a similar format.
So, I figured I'd get some inspiration and then convert it into a post for Creator Hunter. What's not worked for me and what I see is there's been like a lot of competitors and copycats that come up, but they never really take off because either they're copying the exact same thing and people see right through that and you need an edge that no one can easily copy with AI tools nowadays. Nice.
That's a good strategy. Okay, so now the exciting part. Let's talk about tech stack.
What tools, languages, or whatever else you use to build this business? And if you don't mind me asking, what are the generally the costs to run this business? What kind of margins are we looking at?
I use perplexity for the game plan, bold for the functional MVP, cursor for making it production ready. I use Versal which is free and then Superbase also free and then API for scraping. In terms of costs and margins, so it's about 90%.
All right. So what I want to ask you is, you know, you you built a bunch of stuff and you finally seeing success with Creator Hunter. What have you learned during that process that surprised you?
I'm getting a lot of questions as well about how I did it and people want the sauce on how to build stuff and build stuff fast. I think you can just start prompting and just prompt your way to making something and sell it. I think people underestimate the knowledge they already have.
So like if you have like a deep domain knowledge, you probably have like tons of ideas already on what to build and you probably have like a winning idea already that you could just prompt your way and start building. I like that. Cool.
All right. Now that you are working on this full-time, tell me what a day in the life looks like for you for now building Creator Hunter. Yeah, so it's a big change.
More traveling and more work. When I was building out the MVP and was at the same time traveling to China, New York, France, and seeing revenue while you're out and about exploring is a nice feeling. It's a real blessing.
But I've been working on it full-time on Creator Hunter since the 24th of December when I quit the job. So some days there's more hours that I put in this than my 9 to5. But I don't feel exhausted at all.
Cool. I like that. Well, the last question that we asked anybody that comes on starter story is if you could give advice to young polus maybe a couple years ago.
What would you tell them? I think never underestimate how much you can do solo. AI as your CTO is like a superpower.
I I don't know how long this period of time will last, but we need to take advantage of it. Whatever ideas you have, you can probably execute it in a weekend. If you just figure out the most scrappy idea possible in the most scrappy way possible, you can get it out there.
And then if you put a buy button on it, share it on Twitter in the most scrappy way or Tik Tok, I think you'll be surprised by the amount of people that actually want to get it. Well, that's great advice. Thanks for coming on, Polus.
I love what you built. You're going to be a massive success. Keep building, keep going, and uh hopefully we'll see you back on the channel.
Thank you. Thanks, Polus, for coming on. I think his story is amazing and it's proof that anybody right now can build anything with AI.
I mean, he just got started. He built a bunch of stuff and throughout that process found the idea that would change everything. I see a lot of people waiting for the right time to start and just sitting on the sidelines while others like Polus are just getting started playing around with these tools, throwing at the wall and shipping stuff every week.
If you got started right now and started playing with these tools and shipping stuff, imagine where you'd be in two weeks. Yes, it's early and not everything is perfect, but the early bird gets the bag. So, if you're serious about shipping, want to build something real and put it out into the world, check out Starter Story Build.
I put the first link in the description. Let's build. Thanks for watching.
I'll see you guys in the next one. Peace.
Copyright © 2025. Made with ♥ in London by YTScribe.com