Apprentice Tutor Builder: A Platform For Users to Create and Personalize Intelligent Tutors
Project Overview
The document explores the use of generative AI in education through the Apprentice Tutor Builder (ATB), a platform that facilitates the development of intelligent tutoring systems (ITS) tailored to individual educators' needs. It highlights the significant impact of ITS on enhancing student learning outcomes while addressing the challenges associated with their creation, such as the requirement for specialized programming skills and the time involved in development. The ATB simplifies this process by providing a user-friendly drag-and-drop interface, enabling instructors to build tutor interfaces and train AI agents interactively through demonstrations and feedback. User studies indicate that the ATB is both usable and flexible, with participants recognizing its potential for personalized tutoring experiences. Overall, the document underscores the promise of generative AI in transforming educational practices by making advanced tutoring systems more accessible to educators, ultimately aiming to improve student engagement and learning success.
Key Applications
Apprentice Tutor Builder (ATB)
Context: Used by instructors in educational settings to create personalized intelligent tutors for subjects like mathematics.
Implementation: Instructors utilize a drag-and-drop interface to build tutor designs and interactively train the AI agent through demonstrations and feedback.
Outcomes: Participants found the interface intuitive and praised its time-saving capabilities, with successful authoring of tutors and high model correctness in user studies.
Challenges: Some users desired more flexibility in interface design and guidance on agent training. There were also concerns about the time required for effective training.
Implementation Barriers
Technical Barrier
Challenges in creating custom tutors due to the need for specialized programming skills and the time-consuming nature of tutor development.
Proposed Solutions: The ATB platform aims to reduce complexity by providing a user-friendly interface and interactive training methods, allowing non-technical users to create tutors.
Usability Barrier
Some participants expressed a need for more control and flexibility in designing tutor interfaces and training processes.
Proposed Solutions: Feedback from user studies suggests improving the interface builder for better alignment and element management, as well as enhancing guidance for agent training.
Project Team
Glen Smith
Researcher
Adit Gupta
Researcher
Christopher MacLellan
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Glen Smith, Adit Gupta, Christopher MacLellan
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai