Back to search

Virginia Tech

Design and Development of a Socratic Intelligent Tutoring System: Leveraging Agentic AI for Asynchronous Online Learning

Abstract

dc:description.abstract

This design and development study explores the initial development and validation of an intelligent tutoring system designed to operationalize the Socratic method in asynchronous online learning environments. Building on Bloom's (1984) "2 Sigma Problem," which highlights the challenge of scaling personalized tutoring approaches, this research investigates whether the Socratic method can be effectively implemented using generative AI in a Retrieval Augmented Generation (RAG) based agentic system. The system, named "Gadfly," was developed using enterprise web services and designed around five core principles of Socratic methodology: defining terms, refutation (elenchus), Socratic questioning, puzzlement (aporia), and recollection (anamnesis). These principles were implemented through prompt engineering and aligned with dimensions of learner engagement and constructivist learning theory. Seven expert reviewers evaluated the system across multiple dimensions, including Socratic method implementation, pedagogical effectiveness, usability, and ethical considerations. Results indicated that the system successfully implemented key aspects of Socratic dialogue, particularly in using open-ended questions, providing an intuitive interface, and employing structured questioning. Areas for improvement included the system's ability to present diverse viewpoints, introduce intellectual uncertainty, and encourage real-world application of concepts. This research contributes to our understanding of how AI technologies can support personalized, dialogue-based learning experiences in online environments. The findings suggest that while further refinement is needed, AI-powered Socratic tutoring represents a promising approach to scaling this ancient pedagogical method to meet contemporary educational needs.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Curriculum and Instruction
Department dc:contributor.department
Education, Vocational-Technical
Grantor dc:publisher
Virginia Tech
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kayanuma, Bryce Platt
Chairs dc:contributor.committeechair
  • Lockee, Barbara B.
  • Holmes, Glen A.
Committee members dc:contributor.committeemember
  • Johnson, Alicia Leinaala
  • Scales, Glenda R.

Subjects

dc:subject × 5

Rights

dc:rights
Statement dc:rights
  • Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Other
vt_gsexam:43039

Chain of custody

source
Harvested from
Virginia Tech
Base URL
vtechworks.lib.vt.edu/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Kayanuma, Bryce Platt. Design and Development of a Socratic Intelligent Tutoring System: Leveraging Agentic AI for Asynchronous Online Learning. doctoral thesis, Virginia Tech, 2025. https://hdl.handle.net/10919/135529