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 that 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 for Waypoint
- 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
Built With
- claude
- fastapi
- groq
- javascript
- python
- react
- uagents

Log in or sign up for Devpost to join the conversation.