About the challenge

Agents are getting smarter, but they're culturally blind. They can reason, plan, and execute — but ask them what to recommend, what to build, or what people actually want, and they're guessing. This hackathon is about fixing that. Build an agentic tool, an agent-powered app, or wire Qloo into an agent that already exists. Use our API and taste graph — 250M+ entities across music, film, dining, fashion, and more — to give your agent something most never get: real cultural grounding.

We're not looking for demos of what LLMs can already do. We're looking for the thing that only works because it knows what people love. Show us the use case where cultural intelligence is the difference between "technically functional" and "actually good." Build it, ship it, blow our minds.

Get your API key here to get started: https://docs.qloo.com/reference/qloo-llm-hackathon-developer-guide#getting-your-api-key

Requirements

What to Build

Build a working software application that integrates the Qloo API and either functions as an agentic tool, is built using an agent framework, or wires Qloo into an agent you already have. Use Qloo to ground recommendations in real cultural taste so your agent can do more than "answer well"; it can reliably know what people like across music, film/TV, dining, fashion, travel, and more.

Your project should make cultural intelligence the differentiator: the agent should outperform generic LLM-only approaches because it has access to Qloo's API and taste graph (250M+ entities). If your submission would work the same without Qloo, you're building the wrong thing.

Don't be afraid to think laterally: 

- Can an agent help electricians’ customers choose lighting styles for specific rooms -- mood, comfort, function, and personal taste -- instead of generic “bright or dim” advice?

- Can an agent recommend meals and dining options for seniors that match not just taste, but age-specific needs like easy-to-chew menus, low-heat delivery, medication-aware ingredients, or other health constraints?

- Can an agent support people in rare-disease journeys by finding the right mix of information + community + next steps that matches what they actually need both emotionally and practically?

What to Submit

To be eligible, your submission must include all of the following:

1. A link to a functional demo application

A live, working app participants can try end-to-end. This should demonstrate the core features of your project.

2. A URL to a public code repository (GitHub, GitLab, or Bitbucket)

The repo must be public and it should contain all source code, assets, and instructions needed for the project to run.

3. A text description of what your project does

Explain the key features and functionality: what the agent or workflow can do, and what makes it "Qloo-powered."

4. External hosting / fully published requirement

Your demo must be hosted and fully published externally, such as a live website or web app, or a hosted APK / TestFlight build. Submissions that only run locally or rely on private access will not qualify.

5. An open-source license, with the file visible in About section of your repo. 

NOTE: Demo videos are not required. Instead of asking for a recording, we're requiring something judges can actually use.

 

Hackathon Sponsors

Prizes

$25,000 in prizes
First Place
$15,000 in cash
1 winner

Second Place
$6,000 in cash
1 winner

Third Place
$4,000 in cash
1 winner

Devpost Achievements

Submitting to this hackathon could earn you:

Judges

Jason Calacanis

Jason Calacanis
American Entrepreneur & Angel Investor / Bestie

Mike Diolosa

Mike Diolosa
CTO, Qloo

Nicole Seligman

Nicole Seligman
Member / OpenAI Board of Directors

Todd Boehly

Todd Boehly
Co-founder, Chairman, & Chief Executive Officer / Eldridge Industries

Cedric the Entertainer

Cedric the Entertainer
American Actor, Comedian, Producer, and TV Host

Michael Abrams

Michael Abrams
EVP Strategic Initiatives / Live Nation Entertainment

Judging Criteria

  • Technological Implementation
    How thoroughly and skillfully does the project use Qloo? Does the code reflect genuine effort and a working, non-trivial implementation?
  • Design
    Does the project deliver a complete, coherent product experience, not just a technical proof of concept?
  • Potential Impact
    Does the project make a credible, specific case for solving a real problem for a real audience and does the solution actually address that problem based on what's demonstrated?
  • Quality of the Idea
    Is this a creative, non-obvious use of Qloo and does the team demonstrate genuine understanding of the problem space they're working in?

Questions? Email the hackathon manager

Invite others to compete

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.