Qloo LLM Hackathon

Join the Qloo Global Hackathon —

This is your opportunity to shape the future of intelligence using Qloo’s unique insights, which combine cultural knowledge with consumer behavior to understand how people interact with the world around them.

Developers, creatives, and builders around the world are invited to a month-long event to experiment at the intersection of large language models (LLMs) like ChatGPT, Claude, and Gemini, and Qloo’s Taste AI™ API — the world’s most advanced graph of cultural and consumer preferences.

Qloo’s API unlocks deep, semantic insight into how people interact with the world around them — from music, TV, dining, fashion, and travel to brands, books, podcasts, and more. With no personal identifying data foundation, it’s a privacy-first way to power intelligent systems with real insight into what people enjoy and how their interests connect.

Whether you’re building a next-gen personal assistant, a smarter recommendation engine with cultural depth, or a completely new kind of app that understands people through their passions, this hackathon is your chance to push the boundaries of what’s possible with LLMs and cultural intelligence.

Why Join?

• Access the world’s richest cultural intelligence platform

• Power your project with Qloo’s API and your favorite LLM

• Compete for cash prizes and global recognition

• Build more personalized experiences, from smarter chatbots to enriched user profiles and recommendations — no personal data required

This isn’t just another hackathon — it’s your chance to build something real: a prototype that could become a product, grounded in deeper human understanding.

Team size: Up to 4 members. Solo submissions welcome.

• Intelligent & Thoughtful Use of LLMs
  Does the project demonstrate thoughtful, effective use of a large language model? Are the model’s capabilities meaningfully extended or enhanced by the integration with Qloo’s API?
• Integration with Qloo’s API
  How well does the project incorporate Qloo’s Taste AI API? Does it showcase the unique value of Qloo’s cross-domain affinities or privacy-first data approach?
• Technical Implementation & Execution
  Is the project well-built and smoothly operating? Does it reflect solid, industry-quality code? Are frontend and backend components thoughtfully implemented, with effective integration of tools like Qloo’s API and any LLMs?
• Originality & Creativity
  Is the concept novel, unexpected, or particularly insightful? Does it explore a new use case for cultural intelligence in AI or push the boundaries of what recommendation systems can do?
• Potential for Real-World Application
  Does the project address a real need or open up new possibilities for AI tools? Could it evolve into a useful product or be expanded into a broader use case?