At the European XFEL, scientists conduct experiments that generate very large and complex datasets, making subsequent data analysis a significant challenge. Scientists need to combine their domain expertise with facility- and software-specific knowledge scattered across documentation, tools, and support channels.
To address this problem, we designed and evaluated an agentic AI system tailored to the scientists' needs, integrated with the high-performance computing environment of European XFEL. Using a design science research approach, we conducted a rapid literature review, a systematic evaluation of 16 AI tools, multiple interviews, a focus group, and a user study with experts at European XFEL to develop and evaluate two prototypes.
Our study identifies key knowledge challenges in scientific data analysis, derives requirements for an AI agent that supports knowledge retrieval and source code generation, and proposes design recommendations for a specialized system adaptable to the evolving AI tool landscape. These findings provide guidance for developing maintainable AI support in highly specialized scientific environments.
Blogger's Review: This study highlights the significance of AI in scientific data analysis, particularly in handling complex datasets. With effective AI agents, scientists can integrate and analyze data more efficiently, boosting research productivity. As AI technologies continue to evolve, such systems will fundamentally alter the workflow of scientific research.