Defining AI Roles in Requirements Elicitation and Analysis

Sammanfattning

Artificial intelligence is increasingly used to support Requirements Engineering (RE),especially in text-intensive activities such as summarizing stakeholder input, extracting candidate requirements, and organizing requirements-related information. Yetin early RE, where requirements elicitation and requirements analysis depend oncontextual interpretation, incomplete information, and stakeholder negotiation, itremains unclear how responsibilities should be allocated between human practitioners and AI systems.This thesis investigates how human–AI roles are configured in requirements elicitation and requirements analysis, and how practitioners evaluate the benefits, risks,and trust conditions associated with these configurations. A sequential exploratorymixed-methods design was used, combining six semi-structured interviews with software engineering practitioners and a follow-up survey with 67 valid responses. Interview data were analyzed thematically and used to inform the survey design, whilesurvey data were analyzed descriptively.The findings show that AI involvement in early RE is task-contingent rather thangeneral. Practitioners were most willing to use AI as an assistant or preliminaryprocessor in bounded, information-heavy, and verifiable tasks, including summarizing, extracting, organizing, and structuring requirements-related material. Bycontrast, tasks involving stakeholder interaction, interpretation of implicit needs,prioritization, trade-off decisions, and accountability remained strongly human-led.AI-assisted configurations were perceived as the most useful, whereas AI-only configurations were rare and associated with the highest perceived risk. Trust in AI wastherefore conditional rather than general: it increased when outputs were easy toverify and tasks were low in decision criticality, and decreased when work dependedon contextual judgment, sensitive information, or consequential decisions.Based on exploratory mixed-methods evidence, this thesis proposes a practitionerinformed role-boundary framework at the task level for AI involvement in early RE.The framework clarifies where AI can productively support elicitation and analysiswork and where human judgment should remain dominant. Overall, the study arguesthat AI should be integrated into early RE as a calibrated collaborative support toolrather than as a substitute for human practitioners.