Participants will gain a basic understanding of how generative AI and large language models work and what implications this has for their use for research data management. The session will use a sample research project to explore the areas in which AI can support research data management.

Contents:

• Fundamentals of generative AI and large language models

• Capabilities and limitations of current AI systems

• Research versus generation: Which tool is best suited for which purpose?

• AI-assisted research based on standards, requirements, and best practices

• Critical evaluation of sources and assessment of AI-generated research results

• Initial application to a specific RDM case

Learning Objectives:

Participants will be able to…

• explain the basic principles and limitations of generative AI and large language models,

• distinguish between different AI tools in terms of their use for research and generation,

• identify appropriate applications of AI in research data management,

• critically evaluate AI-assisted research results and the sources used.

Registration form (deadline: 01.11.2026)

This workshop focuses on the practical application of generative AI. Participants will learn how the quality of the results is influenced by context, the task at hand, data and the desired output format, and how unstructured information can be processed systematically.

Contents:

• Context Engineering Instead of “Magic Prompts”

• Structured Tasks: Role, Context, Task, Format, and Constraints

• Structuring Unstructured Information

• Key-Value Extraction and Structured Output Formats

• Hallucinations and Other Common Sources of Error

• Quality Assurance Through Source-Bound AI Systems

• Human Oversight and Verification

Learning Objectives:

Participants will be able to…

• Formulate tasks and contexts for AI systems in a structured and goal-oriented manner,

• Convert unstructured information into comprehensible structures using generative AI,

• Identify typical sources of error, such as hallucinations, and assess their impact on FDM processes,

• Systematically review and improve AI-generated results using appropriate sources.

Registration form (deadline: 10.11.2026)

This workshop focuses on entire work processes with AI in research data management. Participants distinguish between AI assistants, automated workflows, and more autonomous systems, and develop criteria for determining which tasks in research data management can be automated and in which areas human oversight remains essential.

Contents:

• AI assistants, workflows, agents, and agent-based systems

• Appropriate and inappropriate automation scenarios in FDM

• Human-in-the-loop and boundaries of responsibility

• Bias and responsibility

• Data protection and handling of sensitive research data

• Copyright, scientific integrity, and the EU AI Act

• Documentation of AI usage and traceability

• Development of custom use cases

Learning Objectives:

Participants will be able to…

• distinguish between AI assistants, automated workflows, and more autonomous AI systems,

• evaluate FDM tasks in terms of their suitability for AI support and automation,

• identify risks related to data protection, bias, scientific integrity, and accountability,

• develop appropriate forms of AI support for their own FDM use cases, including necessary human checkpoints.

Registration form (deadline: 20.11.2026)