SmartStandards: Efficient Extraction and Operationalization of Requirements from Industry Safety Standards Using Generative AI

Developing safety-critical systems require compliance with multiple standards which impose numerous requirements on development and assurance processes. However, understanding, filtering, and operationalizing relevant requirements demands substantial effort and expertise. The shortage of experienced engineers and the growing number of applicable standards and regulations call for new methods to manage this complexity and improve efficiency. This study investigates how generative AI can support engineers in efficiently extracting concrete requirements from a set of standards. We developed a generative AI-based tool that automatically analyzes standards and proposes a list of requirements based on predefined relevance criteria. The tool is embedded into a human-in-the-loop workflow in which domain experts verify and validate the extracted requirements to ensure high quality and maintain traceability to the original standards. We evaluated our approach to three safety standard documents for automated driving systems in the context of verification and validation. AI-generated requirements were first reviewed by a novice safety engineer, and we measured both the tool’s processing time and the engineer’s verification time. We compared this AI-supported workflow to fully manual analysis in an industry project by engineers with three to eight years of experience where 130 out of 314 clauses are declared as relevant. We observed an 84% increase in efficiency, while 7% of the entries were incorrectly specified after novice verification. Subsequent expert review resolved the remaining errors and resulted in a net efficiency improvement of 60%. The evaluation shows that a collaborative human–AI approach can improve the efficiency of standards analysis significantly and reduce the effort required from expert engineers, while maintaining a high level of quality suitable for safety-critical development.