Recap and video recording of the first KIMed webinar

How to (Not) Build a RAG System – Lessons Learned from Developing an Intelligent Search System for Patient Records

News | 27 May 2026

As part of the new webinar series “KIMed Network Insights – After-Work Seminar on AI and Medicine,” KIMed brings together interdisciplinary experts who are engaged in the use of artificial intelligence (AI) in medicine.

The series kicked off with the webinar “How to (Not) Build a RAG System – Lessons Learned in Developing an Intelligent Search for Patient Records” on May 20, 2026. Sarah Rockstroh and Dr. Robert Haase, research associates at the National AI Competence Center SCADS.AI Dresden/Leipzig, spoke to 35 participants about their experiences, challenges, and insights from the development and use of Retrieval-Augmented Generation (RAG) systems.

In the subsequent discussion with the speakers and the audience, the acceptance of RAG systems was discussed. It was also emphasized that medical applications require constant dialogue with medical professionals and flexibility on the part of AI engineers. During development, one should not focus on a single AI system but rather remain flexible and adapt the AI system to the needs of medical professionals.

We would like to thank everyone for the stimulating discussion and are pleased to provide you with the webinar slides and the recording:

 

Co-funded by the European Union
This project is co-financed from tax revenues on the basis of the budget adopted by the Saxon State Parliament
You are using an outdated browser. The website may not be displayed correctly.