The increasing complexity of engineering challenges requires methods and tools that enable researchers to efficiently access, generate, and integrate heterogeneous data. Task Area Ellen presents a FAIR-by-Design approach, embedding machine-actionable metadata directly into texts, software, and data from the outset to minimize documentation effort and maximize reusability. Key tools include SciKGTeX for semantic representation of scholarly contributions, DataDesc for technical metadata of software and data models, and the Open Research Knowledge Graph (ORKG) for connecting and analyzing scientific findings. A best-practice application, ETHOS.REFLOW, demonstrates the reproducible assessment of renewable energy potentials through open-source workflows. To further address information needs, AI-driven knowledge engineering methods—such as vector search, large language models, and automated knowledge extraction—are leveraged to contextualize research content. Tools like ORKG Ask enable semantic exploration across millions of research outputs, while Quinex automates the extraction of quantitative data with contextual detail. Together, these approaches empower researchers to both discover relevant information more effectively and integrate it into customized workflows when suitable data is unavailable. By combining FAIR principles with AI-driven knowledge technologies, this framework significantly enhances transparency, reproducibility, and efficiency in engineering research.

Acknowledgements

The authors would like to thank the German Federal Government, the German State Governments, and the Joint Science Conference (GWK) for their funding and support as part of the NFDI4Ing consortium. Funded by the German Research Foundation (DFG) - project number: 442146713. This work was also supported by the Helmholtz Association under the program "Energy System Design".