# Project export: Waypoint

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: Waypoint is your AI travel planner. Tell it your style, budget, and vibe—Waypoint finds flights, stays, and experiences, then builds a dynamic itinerary that adapts as your plans change.
- Devpost: https://devpost.com/software/waypoint-oemdt9
- GitHub: not linked
- Video: https://www.youtube.com/embed/6cClwjJco00?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

Travel planning is overwhelming, with too many tabs, too many decisions, and no easy way to match a trip to your personal travel style. We wanted something that feels like talking to a friend who just knows what you like.

### What it does

Waypoint is an AI travel planner that learns your preferences and builds complete, dynamic itineraries. You tell it your vibe, interests, pace, and budget—Waypoint finds flights, stays, and experiences, then organizes your days into a personalized trip plan that updates as your plans change.

### How we built it

We used generative AI (specifically Claude Haiku 3.5 and Groq) for itinerary reasoning and natural conversation. We integrated Serp APIs for flights, hotels, and events, stored trip context in structured memory, and created an adaptive planning pipeline that refines the itinerary based on new user input. The frontend offers a clean chat-style interface to guide planning in real time.

### Challenges we ran into

Handling edge cases that gives malformed data that causes the AI to complain Getting the AI to respect budget + time constraints consistently Avoiding hallucinated attractions and ensuring real recommendations Designing conversations that feel natural and not like forms

### Accomplishments we're proud of

Built a fully working end-to-end travel planning agent in a weekend Created a fluid feedback loop where the trip updates instantly based on changes

### What we learned

Generative AI is strongest when given structure, memory, constraints, and context. Otherwise it's straight up annoying. Conversations are a powerful UI when paired with real planning logic

### What's next

Live booking + one-click confirmation Group trip planning and shared itinerary negotiation Local event recommendations and real-time weather-based re-routing Mobile app with offline itinerary mode

## 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
- JavaScript (language) — 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

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.