GraphRAG in Real-Life Use Cases
How structured retrieval helps high-stakes decision making - Daan Di Scala
Moving beyond basic RAG isn't just a technical upgrade, it's the key to building truly trustworthy AI. In this session, discover how GraphRAG transforms raw data into reliable insights across three applied real-world use cases.
In this talk, he will:
Introduce his work at TNO as an AI scientist
Cover the topic of Trustworthy AI decision support, and in particular:
Discuss: how can knowledge-driven RAG and GraphRAG approaches make retrieval more trustworthy?
Take you through 3 applied use cases and showcase the effect of different approaches
About the Speaker:
Daan Di Scala studied Artificial Intelligence at Utrecht University, The Netherlands. After his Master thesis focused on privacy preserving AI agents, he started working at TNO Data Science in 2023 as AI researcher. TNO is the Dutch research institute for applied science, where Daan's research revolves around the trustworthiness of AI in high-stakes domains (agrifood, healthcare, legal). In 2025 he started his PhD at Utrecht University on the topic of Knowledge-Grounded AI for Trustworthy Advice. In his work, he investigates how structured knowledge can enhance state-of-the-art LLM systems to improve the trustworthiness of AI advice, enabling users to better understand, evaluate, and appropriately rely on AI-generated recommendations for high-stakes decisions.
DataTalks.Club is the place to talk about data. Join our Slack community!