Adopurr

A cat adoption can get decided in fifteen minutes. That always felt off to me, especially in a world that can already predict the next movie I will watch. If the algorithm is that good at entertainment, why are we still guessing when a cat needs a home?

That question is why I built Adopurr, an AI-driven matching system I have been on for about two years. Freshman year I worked at Mini Cat Town: play with the cats, feed them, notice if they were sick. I could have stopped at cute. I did not. Same breed, completely different personalities, and I kept thinking that if we study human traits to make better decisions, we can study animals the same way. So I started reading the journals, then using things like Monte Carlo and random forest to match cats with the people who will actually keep them. Happy cat, happy home.

I used to hate coding. Both of my parents do it for a living, and debugging never looked like a calling from where I was sitting. Research is what made it click. The work was not the problem. Sitting in someone else's workplace was. That is also when I decided I would rather build something that helps people and animals than work for someone else. Social entrepreneur is the flashy label. I just wanted the matching to be less random.

Getting into the 1517 Fund community changed the pace. We have been in talks with Dallas Animal Shelter, Operation Kindness, and other local shelters, and the work has expanded into dogs: characteristics, emotional triggers, the same matching problem with a bigger animal. Over the summer we planned Paws for Cause, an NPO branch where high school chapters advocate for animal welfare and fundraise. We have already scouted more than 25 chapters, got $400 from national FCCLA to start, and we are raising the rest ourselves.