Background
Smukfest has 55,000 guests and hundreds of concerts. The security team must prepare for very different audience situations. 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 research each artist: genre, energy level, audience profile, crowd dynamics, historical incidents and risk profile. The security team receives a structured overview for its own assessment.
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 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, with structured data available for every show.
The tool prepares the work. The security team still makes the final assessment and remains responsible for staffing and response.