# Project export: sendyback

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: Cal Hacks 12.0
- Tagline: sendyback — your receipts get sexy returns, fast.
- Devpost: https://devpost.com/software/sendyback
- GitHub: not linked
- Video: https://www.youtube.com/embed/VUier-fJ5WI?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

✨ Returning items is messy — every store has different policies, deadlines, and methods. Receipts get lost in inboxes or bags, and by the time you realize, it’s too late. We wanted a one-stop “returns wallet” where uploading a receipt instantly shows how many days you have left and lets you start the return in one click. What We Built 🛠 sendback — Returns Wallet is a full-stack app built with Next.js (frontend) and FastAPI (backend). Receipt ingestion: We use OCR (REKA) + LLM parsing (Claude via Lava API) to extract structured fields (merchant, items, purchase date). Deadline calculation: [ \text{days_remaining} = (\text{purchase_date} + \text{window_days}) - \text{today} ] ensuring users always see how long they have left. Policies: A policies.json file defines return windows and links for each merchant, keeping business logic flexible. Challenges & Learnings ⚡ Parsing inconsistent receipt formats reliably was hard — we learned to design strict JSON schemas for LLMs. Next.js App Router introduced quirks (params now resolves as a Promise), so routing to /order/[id] took debugging. CSS traps prevented scrolling in our return flow until we fixed layouts with min-h-dvh and overflow-y-auto. Through these challenges, we learned to integrate AI services with robust backend logic while keeping the frontend simple and user-friendly.

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- Anthropic (technology) — claimed on Devpost, not found in the code
- FastAPI (technology) — claimed on Devpost, not found in the code
- Next.js (technology) — claimed on Devpost, not found in the code
- Node.js (technology) — claimed on Devpost, not found in the code
- Python (language) — claimed on Devpost, not found in the code
- Tailwind CSS (technology) — claimed on Devpost, not found in the code
- TypeScript (language) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.