Designing AI-Assisted Writing Interfaces for Requirements Engineering - Exploring Factors Influencing Usability and Design Guidelines

Sammanfattning

The integration of Large Language Models (LLMs) into professional workflows hascreated new opportunities for supporting information-intensive tasks such as Requirements Engineering (RE). However, despite the growing interest in AI-assistedwriting tools, limited research has explored how such tools should be designed tosupport usability in industrial RE contexts. This thesis investigates how interactiondesign can support the integration of AI-assisted writing tools into requirementsmanagement systems to assist engineers in formulating clear and consistent requirements.The study was conducted in collaboration with Geely Technology Europe and focused on a custom-built extension for the requirements management platform SystemWeaver. Using a Research through Design approach combined with the DoubleDiamond framework, the project included a literature review, semi-structured interviews, thematic analysis, ideation, prototyping, and usability testing.The results identified four key factors important for usability when integrating AIassisted writing tools in requirement management systems: control, trust, flexibility,and efficiency. Based on these findings, fourteen design guidelines across interaction,functionality, and design were developedThe study highlights the importance of balancing trust and over-reliance, efficiencyand control, as well as flexibility and consistency when integrating AI into professional requirements engineering environments. The findings contribute to the fieldsof Human-Computer Interaction, Human-AI Interaction, and Requirements Engineering by providing practical design guidance for future AI-assisted writing toolsin industrial contexts.