Splitr

Inspiration The day before the hackathon, our team went out to eat, and we realized it was inconvenient to split the bill... That's when the idea for Splitr was born — a simple tool to take the stress out of bill‑splitting forever. What it does Splitr lets users upload or take a picture of a receipt. It uses OCR to extract item names and prices, then users assign items to members and Splitr automatically calculates what each person owes, handling tax and tip fairly. How we built it React Native + Expo Go for rapid iteration; Firebase Auth for phone‑based sign‑in and future history; Google Vision OCR -> parsed by MistralAI -> Python backend -> app components. Challenges OCR accuracy on messy receipts; parsing inconsistent layouts; wiring image -> backend -> app under time pressure. Accomplishments Reliable OCR pipeline; smooth user flow from image upload to final bill; shipped a functional, useful MVP fast. What we learned Integrating OCR with LLMs; the value of clean UX; teamwork/iteration; keeping a navigable codebase; we should really learn Docker! What’s next Improve OCR with better pre‑processing and prompts; editable receipt step; Firestore history; Venmo/CashApp integration; advanced splitting options; polish UI and accessibility.