"Bespoke Bots": Diverse Instructor Needs for Customizing Generative AI Classroom Chatbots

TL;DR

This study explores how university instructors customize AI chatbots for education, revealing diverse needs and preferences that suggest modular design for adaptable classroom AI tools.

Contribution

It identifies key customization categories and shows how instructor priorities vary by context, informing design of flexible educational AI chatbots.

Findings

Instructors prioritize course alignment and pedagogy over persona customization.

Customization needs vary significantly by course size, discipline, and teaching style.

Modular chatbot designs could better accommodate diverse instructor requirements.

Abstract

Instructors are increasingly experimenting with AI chatbots for classroom support. To investigate how instructors adapt chatbots to their own contexts, we first analyzed existing resources that provide prompts for educational purposes. We identified ten common categories of customization, such as persona, guardrails, and personalization. We then conducted interviews with ten university STEM instructors and asked them to card-sort the categories into priorities. We found that instructors consistently prioritized the ability to customize chatbot behavior to align with course materials and pedagogical strategies and de-prioritized customizing persona/tone. However, their prioritization of other categories varied significantly by course size, discipline, and teaching style, even across courses taught by the same individual, highlighting that no single design can meet all contexts. These findings suggest that modular AI chatbots may provide a promising path forward. We offer design implications for educational developers building the next generation of customizable classroom AI systems.