Dataharvest 2026 - the European Investigative Journalism Conference

Every investigative journalist has faced the same bottleneck. What would I find if I could check all of them: all the company registrations, all the addresses, all the permits? Until recently, answering that question required weeks of scripting. In this session, we introduce a faster way: directing an AI coding agent to build investigative data pipelines on demand. Participants will direct an agent to pull data from a public source, clean it, and turn it into an interactive visualization, all without writing code manually. The approach is applicable to a range of investigative beats, from financial crime and corruption to environmental accountability and lobbying networks.

To follow along, participants should have a basic understanding of web technologies, but no programming experience is needed. After attending this session, participants will be able to direct an AI coding agent to build a data pipeline, from raw data to interactive visualization, and apply this methodology to their own investigative questions. Participants should have a laptop with a modern web browser. We will provide API keys and access credentials during the session. Detailed setup instructions will be shared via a GitHub repository before the workshop.

Coding has long been a skill journalists wanted to learn to make their investigations more efficient and rigorous. The main barrier was the significant time investment required to develop that skill. But since large language models emerged, we no longer need to write code ourselves. We do, however, still need to make informed choices when instructing an LLM to write code for us. Otherwise, those choices get made for us by the model.

How do we instruct the LLM best? How can we understand a code? And how do we catch potential mistakes? No prior coding knowledge is required to attend this session. You'll learn a simple, systematic approach to conversations, context management, and effective prompting that will help you to code anything.

The participants should either have an account with a subscription to large language model provider such as ChatGPT or Claude and be able to use them locally with Claude Code or Codex. Alternativelly, they should install Open Code (https://opencode.ai) and we will provide them with API keys.

Slides: https://datafrosch.fun/slides/code-anything/

Predictive Markets are on the rise, and with them, easy money for insider knowledge and those who can influence their outcomes. While regulation is slow to catch up, investigations don't have to be. Polymarket is the most well-known of these predictive markets, and one thing that defines it is open data on all exchanges going on in a market.

This session will cover key concepts of Polymarket and the possibilities and limitations of investigating it. It will include basic Python code to extract and analyse its open data, and a new open source user interface tool you can use to quickly understand the market and accounts. In the end, we will learn techniques to identify suspicious actors from a few example markets.

Although some code will be shared during the session, you don't need to have a working knowledge of Python to participate.

Comic-book hero Tintin is, without a doubt, the most famous Belgian journalist who never lived. In the course of his 24 albums, which brought him from the early Soviet Union to the surface of the Moon, Tintin did preciously little *actual writing*, but there are still one or two lessons journalists can learn reading the adventures. ‘

Your hosts for this session have set a "trail" through the Tintin stories, and the legacy of Belgium's most famous boy adventurer. Come and compete in a light-hearted quiz which we hope will help you to fall in love with Herge's creation all over again - this time as a datajournalist!

Unlike some quizzes contestants are encouraged to use their phones or laptops to help them navigate through the questions. No previous knowledge of Tintin is required!