-
-
Architecture Diagram
-
Base UI
-
Recommendation Example
Inspiration
Traveling abroad often means juggling weather apps, etiquette blogs, and shopping lists. Existing platforms rarely consider cultural norms or climate. We set out to create an AI chatbot that makes travel shopping smarter, respectful, and stress-free.
What it does
- Understands trip details (destination, season, purpose).
- Suggests culturally appropriate, weather-aware products.
- Explains why item was recommended.
How we built it
- AI/NLP: Google Vertex AI for intent recognition.
- Cultural Data: Internal database + Wikipedia API.
- Climate Layer: Weather + seasonal intelligence.
- Architecture: Python/Flask microservices, Docker, deployed on GKE with CI/CD.
- UI: Responsive chat with product cards.
Challenges
- Handling AI latency.
- Ensuring cultural sensitivity without stereotypes.
- Parsing nuanced queries like “early spring in Seoul”.
Accomplishments
- Deployed a scalable chatbot on GKE.
- Delivered culturally aware recommendations.
What we learned
- Empathy is as important as technical precision.
- Microservices improved agility and scaling.
- Transparency builds trust with users.
Log in or sign up for Devpost to join the conversation.