In response to the growing importance of large language models (LLMs) and big data workflows, we have developed a secure, locally hosted AI platform at the Leibniz Institute for Astrophysics Potsdam (AIP). The service, available under https://ai.aip.de, enables all AIP researchers and staff to access advanced LLM capabilities directly—without relying on external providers.
Built entirely on open-source technologies and hosted on AIP’s infrastructure, the platform prioritizes data security, low-latency interaction, and customizability. Users can leverage the system for a wide range of tasks including text generation, code assistance (“vibe coding”), and scientific data workflow generation.
A standout feature is our integration with the REANA reproducible research platform. An in-house agentic LLM assistant can autonomously analyze a scientific query, retrieve datasets, write code, and build a complete REANA workflow pipeline. This pipeline—comprising source code, configuration, plots, and metadata—is executable directly on AIP servers.
This innovation opens new possibilities for AI-assisted science. By automating data analysis tasks and integrating tightly with AIP’s computing ecosystem, ai.aip.de helps researchers focus on scientific discovery while AI handles routine and technical complexity.

The amount of information available to treating physicians as well as to life science researchers has grown massively within the last years. The increased level of detail and precision as well the multi-modal nature of data poses a challenge to the e.g. medical doctors focusing on important findings while integrating as much relevant information as possible. Approaches including e.g. artificial intelligence agents might help to improve informed decision making in daily clinical routine even in the light of workload consolidation. Besides medical care, machine learning offers great chances in medical research, especially in epidemiological research founded on large datasets. Real world medical data provides insights into authentic medical challenges, nevertheless this comes with specific issues like dealing with missing values or imbalance of cases. Further, ensuring bias-free model development can be challenging. Machine learning algorithms allow efficient evaluation of large (real-world) datasets in the context of existing knowledge and expectations but also might help to identify new aspects leading to ideas outside of the box of established medical research.

The recently established Leibniz Science Campus “Digital Transformation of Research” (DiTraRe) investigates effects of the broadly understood process of digitalisation of research on a multilevel scale. In a brief introduction, we present the main ideology behind DiTraRe, which is to establish a new research branch. We present different measures via which we are aiming at our main goal as well as discuss different outcomes which will be achieved alongway. We discuss the impact which our consortium may have on researchers and society together with its connections to NFDI initiatives.

Expert talk: Data Infrastructures as a Foundation for AI Projects
This presentation will examine the critical components that drive AI progress, with a focus on the need for large-scale, machine-interpretable data that adapts to the unique demands of different sectors. Key topics will include transparency and reproducibility in AI, as well as the importance of making essential resources—publications, data, models, and code—accessible, interconnected, and scalable.
A robust data infrastructure is essential for the AI community, supporting every stage of the data lifecycle—from collection and creation to processing, analysis, publishing, archiving, and reuse of resources. This talk will highlight the foundational role of these infrastructures in AI-driven initiatives, showcasing several ongoing infrastructure initiatives and illustrating how they contribute to a modern data ecosystem.