This study examines how AI agents can support scientists analyzing the large and complex datasets produced at European XFEL. The authors used a design science research process involving a rapid literature review, systematic evaluation of 16 AI tools, interviews, a focus group, and an expert user study. They developed and evaluated two prototypes integrated with the facility’s high-performance computing environment. The work identifies knowledge challenges in specialized scientific analysis and derives requirements for agents that assist with knowledge retrieval and source-code generation. It also proposes design recommendations for maintainable systems that can adapt as the AI tool landscape changes.
No heat snapshots are available in the last 24 hours.