PickStreaks started as a personal challenge. I wanted to create a simple daily game that captured the excitement of sports without the noise of betting. The idea was straightforward. You make one pick a day, try to keep your streak alive, and see how long you can last. No money, no odds, just the fun of making calls and competing with friends. Over the years I've created an extensive list of cool app ideas, and have even tried to code some myself, but I never really finished anything. With the massive improvements in AI tooling recently, this felt like a great project to tackle and bring to life.

What made this different from past side projects was how quickly I could bring ideas to life. I started by designing in Bolt, then pulled everything into Cursor, connected Supabase for the backend, and started building. AI played a huge role in that process. I was able to go from concept to working prototype faster than ever before. I was not stuck in static Figma files. I could actually use the product, feel the interactions, and iterate in real time. That level of speed changed everything about how I worked. About 90% of the code was written by AI and 10% was my own adjustments.

As the core loop came together, I focused on making it feel polished and fast. I added streak animations, built in a leaderboard, and created a basic admin dashboard so I could test matchups and logic on the fly. Every piece of the game was built to be simple, easy to understand, and just fun enough to keep someone coming back tomorrow.

The product is still in early testing. Most users today are friends and family, but I am learning a lot from their feedback. My focus now is on improving onboarding and adding features that create shareable moments. I want to build something that spreads because people enjoy it, not because they are pushed to share it.

This has been one of the most rewarding builds I have worked on. It is fast, fun, and it reminded me how powerful it is to go from idea to live product in a matter of days.