Towards Educator-Driven Tutor Authoring: Generative AI Approaches for Creating Intelligent Tutor Interfaces
Tommaso Calo, Christopher J. MacLellan
TL;DR
The paper addresses the barrier of building intelligent tutor interfaces by enabling educators to author interfaces with generative AI, using a compact DSL and prompt engineering to support both whole-interface and component-level generation. Implemented on the Apprentice Tutor Builder with GPT-4, the approach aims to keep educators in control while leveraging AI to accelerate design. A preliminary evaluation indicates substantial time savings, especially for complex tutors, suggesting potential for broader adoption of ITS design. The work lays out future directions for educator-centric studies and generalization to other tutor-authoring tools and end-user design tasks.
Abstract
Intelligent Tutoring Systems (ITSs) have shown great potential in delivering personalized and adaptive education, but their widespread adoption has been hindered by the need for specialized programming and design skills. Existing approaches overcome the programming limitations with no-code authoring through drag and drop, however they assume that educators possess the necessary skills to design effective and engaging tutor interfaces. To address this assumption we introduce generative AI capabilities to assist educators in creating tutor interfaces that meet their needs while adhering to design principles. Our approach leverages Large Language Models (LLMs) and prompt engineering to generate tutor layout and contents based on high-level requirements provided by educators as inputs. However, to allow them to actively participate in the design process, rather than relying entirely on AI-generated solutions, we allow generation both at the entire interface level and at the individual component level. The former provides educators with a complete interface that can be refined using direct manipulation, while the latter offers the ability to create specific elements to be added to the tutor interface. A small-scale comparison shows the potential of our approach to enhance the efficiency of tutor interface design. Moving forward, we raise critical questions for assisting educators with generative AI capabilities to create personalized, effective, and engaging tutors, ultimately enhancing their adoption.