CampusCulture AI

An audience-aware campus event planner that uses Qloo's cultural intelligence API to generate personalized recommendations and build budget-conscious event plans.

Comment

Inspiration

College events are often planned around assumptions about what students enjoy. We wanted to build something that makes campus event planning more audience-aware, helping organizers create experiences that better reflect students' cultural interests while staying within budget.

What it does

CampusCulture AI is an audience-aware campus event planning application. Organizers can provide an audience profile, interests, event type, location, attendee count, budget and constraints.

The application generates a structured event plan containing:

  • A suggested event theme
  • Cultural and music recommendations
  • Suggested activities and food options
  • A budget breakdown
  • Alternative recommendations
  • Warnings and planning assumptions

How we built it

We built the frontend using React and Vite, with a Python FastAPI backend.

The backend integrates with Qloo's API:

  1. Audience interests are resolved into Qloo entities through its Search API.
  2. The resulting entity identifiers are used as signals for Qloo's Insights API.
  3. Retrieved cultural recommendations are incorporated into the event-planning workflow.
  4. A recommendation and budget-allocation engine generates the structured event plan.

Qloo currently powers the music recommendation component. Other planning categories use curated fallback recommendations, which are clearly identified in the interface.

Challenges we ran into

One of our biggest challenges was integrating Qloo's Search and Insights endpoints into the backend while handling API errors, missing results and fallback recommendations.

We also worked on connecting the React frontend to FastAPI, handling asynchronous requests and ensuring that the generated results were displayed dynamically rather than relying on hardcoded examples.

What's next

We plan to expand Qloo integration across more recommendation categories, improve personalization, and introduce more advanced agentic planning and evaluation capabilities.

Built With

Share this project:

Updates