Modeling, Prompting and Coding unified in one tool
The MoProCo approach (Modeling, Prompting, Coding) represents a novel paradigm in software development that flexibly combines the three development strategies of modeling, AI-supported prompting, and classic manual coding. The aim is to provide developers with a multi-paradigmatic development process that leverages both the strengths of established modeling techniques and the possibilities of modern generative AI, while maintaining the precision of manual implementation.
At the heart of MoProCo is the idea of thinking about software development in terms of models: technical structures and requirements are first captured in models, which serve as the starting point for the further development process. On this basis, targeted prompts to generative AI systems can automatically generate code artifacts that implement or extend the models. Where necessary, this process is supplemented by manual coding, for example for fine-tuning, optimization, or integration. Crucially, MoProCo leaves the choice open: depending on the context, expertise, and tools, the development focus can be more on modeling, prompting, or classic implementation.
Related publications
(Engling et al., 2026) — Models, Prompts, and Code! A Semi-Formal State Machine Language for Multi-Paradigmatic Software Development (ICSOFT 2026)
(Buchmann et al., 2025) — To Model, to Prompt, or to Code? The Choice Is Yours: A Multi-Paradigmatic Approach to Software Development
(Buchmann et al., 2024) — White-box LLM-supported Low-code Engineering: A Vision and First Insights
@inproceedings{EnglingSB26,author={Engling, Oliver and Schw{\"{a}}gerl, Felix and Buchmann, Thomas},editor={Mecella, Massimo and Nikiforova, Oksana and Maciaszek, Leszek A.},title={Models, Prompts, and Code! {A} Semi-Formal State Machine Language for Multi-Paradigmatic Software Development},booktitle={Proceedings of the 21st International Conference on Software Technologies, {ICSOFT} 2026, Porto, Portugal, July 16-18, 2026},pages={203--210},publisher={{SCITEPRESS}},year={2026},url={https://doi.org/10.5220/0015128800004088},doi={10.5220/0015128800004088}}
@inproceedings{BuchmannSP25,author={Buchmann, Thomas and Schw{\"{a}}gerl, Felix and Peinl, Ren{\'{e}}},editor={Mecella, Massimo and Rensink, Arend and Maciaszek, Leszek A.},title={To Model, to Prompt, or to Code? The Choice Is Yours: {A} Multi-Paradigmatic
Approach to Software Development},booktitle={Proceedings of the 20th International Conference on Software Technologies,
{ICSOFT} 2025, Bilbao, Spain, June 10-12, 2025},pages={296--303},publisher={{SCITEPRESS}},year={2025},url={https://doi.org/10.5220/0013557100003964},doi={10.5220/0013557100003964}}
@inproceedings{Buchmann2024a,author={Buchmann, Thomas and Peinl, Ren\'{e} and Schw\"{a}gerl, Felix},title={White-box LLM-supported Low-code Engineering: A Vision and First Insights},year={2024},isbn={9798400706226},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3652620.3687803},doi={10.1145/3652620.3687803},booktitle={Proceedings of the ACM/IEEE 27th International Conference on Model Driven Engineering Languages and Systems},pages={556560},numpages={5},keywords={model-driven engineering, large language models, low-code, semiformal, artificial intelligence},location={Linz, Austria},series={MODELS Companion '24}}