Requirements governance in complex system migrations remains fragmented, manual, and dependent on implicit knowledge spread across heterogeneous documents and stakeholders. This thesis investigates how a document-grounded, AI-assisted workflow can support requirements governance while keeping humans in control of consequential decisions, using the railway sector's GSM-R to FRMCS transition as its case. Following Design Science Research, seven design requirements were derived and operationalised in a staged three-agent prototype with role-differentiated human checkpoints. Evaluation on official FRMCS specifications showed five requirements fully met and two partially met, while exposing how a normalisation error propagated into a spurious conflict flag. The contribution is a set of explicit workflow design requirements with documented rationale, redistributing human effort from repetitive comparison toward targeted verification and authorisation.

Repository in GitHub to perform the work in n8n: https://github.com/kristikapllani/frmcs-requirements-governance-workflow ... Read more