<!-- Generated from the same rendered source as /en/cases/smukfest-risiko. Do not edit dist directly. -->
Title: AI-Powered Risk Assessment for Smukfest | Brokk & Sindre
Description: Hundreds of artists, thousands of guests, and a security team that needs to prepare for everything from mosh pits to quiet jazz sessions.
Canonical: https://brokk-sindre.dk/en/cases/smukfest-risiko

- [Home](/en)

- [Cases](/en/cases)

- Smukfest risiko

# AI-Powered Risk Assessment for Smukfest

Hundreds of artists, thousands of guests, and a security team that needs to prepare for everything from mosh pits to quiet jazz sessions.

By Mikkel Krogsholm · July 1, 2024

AI can prepare a decision, while responsibility for safety remains human. Sources, uncertainty and judgment must therefore remain inspectable.

- AI automatically researches each artist as they're announced

- Risk assessment per artist: crowd profile, intensity, density

- In production at risiko.smukfest.dk and used by the security team

## 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](https://fastapi.tiangolo.com) 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.

## Related cases

### Agent-First API for Real Estate Data

Realview wanted to test how AI agents could work directly with its real estate data through a modern, structured interface.

### Crowd Flow Analysis for Smukfest

When thousands of festival-goers switch stages at the same time, bottlenecks form. Without data, it's guesswork where the problems occur.

## Do you face a consequential AI decision?

Write about the decision, or ask about a leadership briefing or talk.
