Enterprise Modelling for Context Engineering Workshop (EMCE)

Organizers

Stijn Hoppenbrouwers^1,3, Hend (Erik) Proper², Vincent Wiegel¹

¹ HAN University of Applied Sciences, Arnhem, the Netherlands
² TU Wien, Vienna, Austria
³ Radboud University, Nijmegen, the Netherlands

Overview

Over the past decades, enterprise modelling has established itself as a central practice in information systems research and organizational engineering. Enterprise models have served as pragmatic, semantic, and structural resources to support communication, requirements engineering, business–IT alignment, and organizational change. The discipline has evolved from a rigid “blue printing” perspective to a more architectural and socio-technical view, reflecting the dynamic nature of modern enterprises (Sandkuhl et al., 2018; van Gils & Proper, 2018).

In parallel, the emerging field of context engineering (L. Mei et al., 2025) underscores the need to systematically represent, structure, and govern contextual knowledge as a foundation for advanced AI and digital transformation. While current AI excels at identifying common patterns in large-scale generic data, it struggles with domain-specific, local, and transient knowledge requirements—calling for precise, sometimes normative and actionable conceptualizations (Dey, 2001; Bazire & Brézillon, 2005).

Using enterprise modelling for context engineering is not only useful for providing context-specific data to AI, but also for helping enterprises articulate their stance towards AI—capturing terms and concepts, principles, values, norms and rules. In settings where AI systems may lack transparency, enterprise models can serve as a “fortress of human-defined meaning”, informing AI while protecting organizational meaningfulness (Jarrahi, 2018; European Commission, 2021).

As a concrete starting point, context engineering can be viewed as the next step beyond utilitarian prompt engineering—using model-based, deliberate and situation-specific representations of organizations and their environments. This aligns with long-standing ambitions of enterprise modelling and opens new avenues for integrating semantics, pragmatics and normative frames into socio-technical systems, including AI-enabled decision support and digital twins (Mihai et al., 2022).

EMCE invites participants to explore the strategic link between enterprise modelling and context engineering. Using a semi-structured group facilitation setup, we will examine how established modelling practices may create a bridge to AI-enabled organizational intelligence and how context engineering can help enterprises to enable and govern AI in alignment with their principles, values, and aspirations. Depending on the workshop outcome, one or more papers may result, possibly to be presented at PoEM 2026.

Participation

If you are interested in participation, please register for PoEM 2025 and send an email to stijn.hoppenbrouwers@han.nl. You can also post questions to this address.

References

van Gils, B., Proper, H.A. (2018). Enterprise Modelling in the Age of Digital Transformation. In: PoEM 2018, LNBIP 335. Springer. https://doi.org/10.1007/978-3-030-02302-7_16
Sandkuhl, K., Fill, H.-G., Hoppenbrouwers, S., Krogstie, J., Matthes, F., Opdahl, A. L., Schwabe, G., Uludag, Ö., & Winter, R. (2018). From expert discipline to common practice. Business & Information Systems Engineering, 60(1), 69–80. https://doi.org/10.1007/s12599-017-0516-y
Mei, L., Yao, J., Ge, Y., et al. (2025). A survey of context engineering for large language models. arXiv. https://doi.org/10.48550/arXiv.2507.13334
Bazire, M., & Brézillon, P. (2005). Understanding context before using it. In Modeling and Using Context (CONTEXT 2005). Springer. https://doi.org/10.1007/11508373_3
Dey, A. K. (2001). Understanding and using context. Personal and Ubiquitous Computing, 5(1), 4–7. https://doi.org/10.1007/s007790170019
European Commission (2021). Proposal for a Regulation on Artificial Intelligence (AI Act). EUR-Lex
Jarrahi, M. H. (2018). Human-AI symbiosis in organizational decision making. Business Horizons, 61(4), 577–586. https://doi.org/10.1016/j.bushor.2018.03.007
Mihai, S., Bălăceanu, A., Bălăceanu, C., Apostol, A. C., Dobre, C., & Mavromoustakis, C. X. (2022). Digital twins: Enabling technologies, challenges, trends, prospects. IEEE Communications Surveys & Tutorials, 24(4), 2255–2291. https://doi.org/10.1109/COMST.2022.3208773