Daniel Nilsson
Test Scouts (Sweden)
From Meeting Conversations to Verification Assets: An Industrial Exploration of AI Driven Requirement and Test Case Generation
Organizations generate vast amounts of valuable information in meetings. However, much of this information remains unstructured, unused, or inconsistently translated into system requirements and test assets. In this presentation, I share insights from a project that explored how AI agents can bridge this gap by converting meeting recordings into actionable system requirements and structured test cases.
The talk outlines our approach to orchestrating multiple specialized AI agents. These agents are responsible for tasks such as speech-to-text processing, semantic analysis, requirement extraction, and the generation of test cases. Together, they form a cohesive pipeline. We discuss key challenges such as ambiguity in natural language, aligning AI-generated output with organizational standards, and ensuring traceability across different artifacts. Real project examples illustrate where the agents performed well, where human oversight remained critical, and how iterative prompt engineering and workflow design improved reliability.
Comprar Tickets
Daniel is a dedicated tester from Gothenburg, Sweden with more than 20 years’ experience within software testing of complex system. He has mainly worked with testing embedded software in the automotive industry, including personal vehicles, trucks, and busses. Test automation has followed him throughout his entire career, from automating manual scripts to strategical processes and development of complete test environments and frameworks.
Daniel has assisted several large global automotive companies in their work with increasing the quality mindset within their organizations, this includes introducing, teaching and coaching test teams in Japan, China, Germany and the US in agile test methodology and leading and coaching outsourced test teams in India. During the last 8 years focus has been on testing AI (machine learning) based systems as well as exploring using AI agents to improve the efficiency and quality not only in the products but also in the testing itself.
He is a seasoned speaker at local and international test conferences and recently started teaching Embedded System Testing and AI at Higher Vocational Education.
