# Project export: ReverseGPS

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: OpenAI Build Week
- Tagline: ReverseGPS turns “What should I do?” into real nearby plans that fit your mood, budget, time, and how you’re getting there.
- Devpost: https://devpost.com/software/reversegps
- GitHub: not linked
- Video: https://www.youtube.com/embed/OuT5Uf7MK3Q?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

We built ReverseGPS for the moments when you have time but no idea what to do. Typical map searches show a list of nearby places, but they do not consider your mood, budget, weather, available time, transportation, or whether a suggestion makes sense right now. We wanted to create an app that answers: “What should I do next?”

### What it does

ReverseGPS creates personalized real-world plans using your location, weather, mood, budget, available time, transportation, hunger, and companions. It finds real nearby places and gives you distinct options with travel time, estimated cost, directions, and weather-aware recommendations.

### How we built it

We built the frontend with Next.js, React, TypeScript, Tailwind CSS, Framer Motion, and interactive maps. The Python FastAPI backend connects browser GPS, weather services, nearby-place discovery, address search, a weighted recommendation engine, and Gemini to create personalized itineraries.

### Challenges we ran into

Live location, weather, and nearby-place services can fail independently, so reliability was a major challenge. We added fallbacks, detailed debugging, secure API requests, weather and late-night safety rules, and diversity checks to prevent repetitive recommendations.

### Accomplishments we're proud of

We created a product that recommends real destinations instead of generic AI activities. ReverseGPS combines live data with a transparent scoring system, transportation-aware travel times, real directions, and personalized recommendations that account for time of day, weather, mood, hunger, budget, and companions.

### What we learned

We learned that AI recommendations are much better when grounded in structured real-world data and clear ranking logic. We also learned how important resilient API design, useful error handling, and thoughtful UX are when building a location-based product.

### What's next

Next, we want to add account-based memory so ReverseGPS learns from places users accept, skip, and revisit. We also plan to expand nearby-place providers, improve public-transit routing, add saved adventures, and support collaborative group planning.

## 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.
- FastAPI (technology) — claimed on Devpost, not found in the code
- Next.js (technology) — claimed on Devpost, not found in the code
- Python (language) — claimed on Devpost, not found in the code
- React (technology) — 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.