AI as Consumer and Participant: A Co-Design Agenda for MBSE Substrates and Methodology

2026-04-28

AI Summary

Current Model-Based Systems Engineering (MBSE) models are primarily designed for human comprehension and lack support for AI consumption, resulting in AI-generated outputs that, while useful, suffer from untraceable and unverifiable reasoning. This work introduces, for the first time, three core principles for the co-design of MBSE models and modeling methodologies to address this gap. By integrating SysML modeling, large language model prompt engineering, and a machine-queryable knowledge architecture, the approach transforms MBSE models into AI-accessible knowledge bases. The study delineates essential characteristics that models must possess in an AI-native systems engineering paradigm, advocating a shift from human-centered representations toward AI-participatory knowledge infrastructure. It lays foundational groundwork for future methodological development and calls upon the community to pursue co-design research before architectural conventions become entrenched.

Abstract

AI tools are being deployed over MBSE models today, and those models were not designed for this kind of consumption. The problem is not simply that tools hallucinate: well-prompted frontier models produce competent, useful output over a conformant SysML model, but the reasoning they produce is drawn from training rather than retrieved from the model itself, and different tools over the same model produce different results with nothing in the record to adjudicate between them. The model, in other words, is functioning as a prompt rather than as a knowledge base. Attaching better tools to the same model does not resolve this. The model and the methodology that governs its construction need to be designed together for AI participation, treating the model as a machine-queryable knowledge substrate rather than a structured artefact for human navigation, and that co-design has not yet happened in any systematic way. This paper works through a concrete workflow scenario to show what that gap looks like in practice, proposes three principles that jointly characterise what model and methodology must achieve together, and closes with a call to the community to begin this work before the architectural decisions about AI integration settle without the methodological foundation they require.

Problem

• MBSE
• AI integration
• knowledge substrate
• SysML
• model co-design

Innovation

• AI co-design
• MBSE
• knowledge substrate
• SysML
• machine-queryable model