
Context: Teaching requirements elicitation remains challenging in Software Engineering education, as it requires the development of communication, analytical, and critical thinking skills in realistic settings. Goal: This paper presents and evaluates Reqcraft, an AI-based interview simulator designed to support students’ learning of requirements elicitation through interactive and realistic client simulations. Method: We conducted a mixed-methods study with 100 undergraduate students enrolled in Requirements Engineering courses. Data were collected through a survey combining Likert-scale questions and open-ended responses, and complemented with interviews with two experienced instructors. Results: The results indicate that Reqcraft improves students’ understanding of the elicitation process, enhances their ability to formulate questions, and supports the identification of functional and non-functional requirements. Students reported high levels of engagement and perceived realism, while instructors highlighted improvements in communication and collaborative learning. Some limitations were observed, particularly related to system performance and interaction constraints. Conclusion: AI-based simulators such as Reqcraft represent a promising approach to complement traditional teaching methods in Requirements Engineering by providing scalable, interactive, and practice-oriented learning experiences.
Requirements Engineering, AI-based Simulation, Generative AI, Software Engineering Education, Requirements Elicitation
Requirements Engineering, AI-based Simulation, Generative AI, Software Engineering Education, Requirements Elicitation
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
