Background
Smukfest is Denmark’s most beautiful festival — 55,000 guests across multiple stages over a week. Behind the scenes, it’s all about security, and security requires preparation. Every year, hundreds of artists play across stages, and the security team needs to know what to expect. A hip-hop show with crowd surfing requires different staffing than a jazz evening.
I lead data and analytics at Smukfest, and I built a tool that makes that preparation systematic instead of gut-feel-based.
What I built
A web platform in FastAPI where AI agents automatically research each artist: genre, energy level, audience profile, crowd dynamics, historical incidents and risk profile. The security team gets an overview they can act on — not a stack of PDFs to read through.
Tech stack
- FastAPI for backend and API
- AI agents for automated research and risk assessment
- Jinja2 + Tailwind CSS + Alpine.js for frontend
- JSON-based data — no database, version controlled in Git
- Docker + Traefik for production with Let’s Encrypt SSL
The system syncs automatically with Smukfest’s API, fetches artists and showtimes, and the AI agents populate risk assessments. Each assessment contains energy level, expected density, substance culture and an overall risk profile.
Results
The platform runs in production at risiko.smukfest.dk. The security team uses it for morning briefings and planning. Instead of googling artists and guessing at crowd dynamics, they have structured data for every single show.
It’s an example of what AI can do in an industry that doesn’t usually think in terms of technology. Festival security is serious work — now it has a serious tool.
