AI-assisted Script Management for Requirements Elicitation Interviews
2026-08-03 • Software Engineering
Software EngineeringArtificial Intelligence
AI summaryⓘ
The authors studied how AI tools can help people conduct interviews to gather project requirements. They created a system that generates interview scripts based on business goals, tracks topics in real time, and suggests follow-up questions. Compared to just training people, their AI-assisted method led to fewer topics covered but deeper questioning and more detailed goal models. Interviewers found the topic tracking especially helpful. Overall, the AI changed how interviews progressed and the kind of information collected.
Requirements elicitationInterview script generationFollow-up questionsTopic coverage trackingGoal modelingAI-assisted interviewingElicitation workflowQuasi-experimental study
Authors
Anmol Singhal, Paulo Carvalho, Travis Breaux
Abstract
Requirements elicitation interviews require interviewers to balance topic coverage, active listening, and adaptive probing while responding to stakeholders in real time. Although prior work has explored AI support for isolated interviewing tasks, such as script generation and follow-up question generation, little is known about how integrated support affects the interview and what requirements artifacts emerge. Furthermore, script management---which helps the interviewer track topic coverage in real time and decide when to probe further---remains underexplored. This paper presents an AI-assisted elicitation workflow that combines theory-guided script generation grounded in business goals with live support for topic coverage tracking and on-demand follow-up question generation. We evaluate the workflow in a between-subjects quasi-experimental study comparing a no-training, AI-assisted condition with a training, AI-unassisted condition. Based on a rubric derived from elicitation best practices, the AI-generated scripts score higher than training-only scripts (92.8 vs. 74.8 out of 100). AI-assisted interviews cover fewer topics (9.6 vs. 14.5), cover more scripted questions (86% vs. 69%), ask more follow-ups per topic (3.43 vs. 1.15), and produce more refined goal models (lowest-level goal fraction 0.653 vs. 0.598). Participants find script management useful, rating topic tracking as the most useful workflow feature (86% agreement). Collectively, these results show that the AI-assisted condition is associated with a different interview trajectory and different elicited requirements than a training-only condition, positioning AI-assisted workflows as elicitation scaffolds for future studies.