I'm Luke. I build tools for people who don't have time for bad software.

Six months ago I was trying to build a custom GPT. That rabbit hole led me to JSON, schemas, APIs. Something clicked.

I built my first real project from scratch: a prop firm comparison site for futures traders. It wasn't pretty. But it worked. And I was hooked.

Since then I've built probably 30 repos. Half of them are half-finished. Ten of them are websites I tried to sell. Until I found out I hate cold calling even more than I hate bad software.

I learned to code by asking ChatGPT and Claude dumb questions. I still do. I don't think that's cheating. I think that's the future.

Software shouldn't require a computer science degree to build or to use.

I believe we're heading toward a world where anyone with an idea can just... make the thing. A business owner who needs a custom tool builds it in an afternoon. Someone who wants a task tracker that works exactly the way their brain works just makes it.

That future is closer than most people think. I'm building toward it.

In the meantime, I build focused tools for impatient people. The ones who don't want to read a manual, don't want to pay for ten features they'll never use, and don't want to be tricked into a subscription they can't cancel.

I'm one of those people. That's why I build for them.

Most tools want your email before you can try them. Then a password. Then a plan. Then a credit card. Now you're locked in, getting promo emails, paying whether you use it or not.

I think that's lazy product design dressed up as a business model.

I'm building the opposite: tools that run on your device, don't require an account, don't store your data on my servers, and charge you only for what you actually use. No subscriptions. No lock-in. No dark patterns.

When you use one of my tools, your input stays on your machine. I handle billing. That's it. I don't want your prompts. I don't want your data. I want to build something good enough that you come back because you want to.

I find trends early. I pick one problem. I build one tool. I ship it in 48 hours.

No team. No investors. No roadmap with 47 items on it.

AI-assisted development means I can move at a speed that wasn't possible two years ago. I use that speed advantage to take more bets, learn faster, and get more shots at building something people actually care about.

The business model is simple: pay for what you use, like electricity. No monthly subscription. No "cancel anytime" fine print. Top up when you want, stop when you want. My tools cost what they cost to run, plus a margin. That's it.

It's a numbers game. I know most ideas won't land. The ones that do will make the ones that didn't worth it.

Marketing. Specifically the social media part: the comments, the threads, the "engage with your audience" grind. I'm working on it.

I'm better at building than selling. Most builders are. The plan is to let the tools speak, let search do the work, and build an audience the slow honest way.

No shortcuts. No spam. Just shipping things worth sharing.

There's a version of Tuesday I'm working toward where I wake up, make coffee, and just build the next thing.

No alarm. No commute. Just the next project.

Modryn Studio is the bet I'm making to get there.