Qloo Agentic Hackathon

🌉 BridgeScout

Tell it what your customers already love — BridgeScout uses Qloo's cultural taste graph to pick the first overseas city, neighbourhood, stockists, and co-brand partners.

Live demo

Primary demo (Render free tier). First load may take ~30–60s while the free instance wakes.

Open live demo → GitHub repo

What it does

Resolves brand references via Qloo search
Scores candidate cities with destination + location affinity
Maps neighbourhood heatmaps and local partners (places, brands, artists, podcasts)
Demographics + cited launch brief — every claim links to evidence E1…En

Run locally (one-liner)

git clone https://github.com/dongwei-polyred/bridgescout.git
cd bridgescout
python3 -m venv .venv && . .venv/bin/activate
pip install -r requirements-dev.txt
cp .env.example .env   # add QLOO_API_KEY for live mode
set -a; . ./.env; set +a
uvicorn bridgescout.app:app --reload --port 8000
# open http://localhost:8000?autorun=1

Without QLOO_API_KEY the app runs in labelled DEMO mode with synthetic data.

Deploy your own (Render)

New → Blueprint → select dongwei-polyred/bridgescout (uses render.yaml + Dockerfile)
Set secret QLOO_API_KEY (optional: LLM_API_KEY / LLM_BASE_URL / LLM_MODEL)
Deploy — health check at /api/health

MIT License · Built for Qloo Agentic Hackathon · Aggregate taste only, no personal data.