From Overload to Insights: How AI Agents Can Support Scientists in Analyzing Complex Data
Artificial Intelligence
Summary
The authors studied how scientists at European XFEL handle very large and complex data from experiments, which is hard because information they need is scattered in many places. They created and tested an AI helper that fits the scientists' specific needs and works with their powerful computers. By reviewing tools, talking to experts, and running user studies, the authors figured out the main challenges and how an AI system can help with finding knowledge and writing code. They also offered advice on designing AI tools that can adapt as technology changes in scientific settings.
Authors
Tim Fuchs, Luca Gelisio, Steffen Hauf, Walid Maalej
Abstract
Scientists at European XFEL conduct experiments that generate very large and complex datasets. The subsequent data analysis is challenging as scientists must 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 and 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.