Date
Publisher
arXiv
Effective feedback, including critique and evaluation, helps designers develop design concepts and refine their ideas, supporting informed decision-making throughout the iterative design process. However, in studio-based design courses, students often struggle to provide feedback due to a lack of confidence and fear of being judged, which limits their ability to develop essential feedback-giving skills. Recent advances in large language models (LLMs) suggest that role-playing with AI agents can let learners engage in multi-turn feedback without the anxiety of external judgment or the time constraints of real-world settings. Yet prior studies have raised concerns that LLMs struggle to behave like real people in role-play scenarios, diminishing the educational benefits of these interactions. Therefore, designing AI-based agents that effectively support learners in practicing and developing intellectual reasoning skills requires more than merely assigning the target persona's personality and role to the agent. By addressing these issues, we present Feed-O-Meter, a novel system that employs carefully designed LLM-based agents to create an environment in which students can practice giving design feedback. The system enables users to role-play as mentors, providing feedback to an AI mentee and allowing them to reflect on how that feedback impacts the AI mentee's idea development process. A user study (N=24) indicated that Feed-O-Meter increased participants' engagement and motivation through role-switching and helped them adjust feedback to be more comprehensible for an AI mentee. Based on these findings, we discuss future directions for designing systems to foster feedback skills in design education.
Study at a glance
- Question: Can AI mentee personas help students practice and improve their design feedback skills through role-playing?
- Setting and data: User study with 24 participants.
- Method: User study testing a newly developed system.
Why it matters
Design students often struggle to give feedback because of low confidence and fear of judgment. While AI role-playing could help, language models often fail to act like real people, limiting their educational benefits.
Key findings
- Feed-O-Meter increased participant engagement and motivation through role-switching as mentors giving feedback to an AI mentee.
- The system helped participants adjust their feedback to make it more comprehensible for the AI mentee.
- The platform allowed users to reflect on how their feedback impacted the AI mentee's idea development process.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
