Back to search

Virginia Tech

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

Abstract

dc:description.abstractgeneral

Imagine having a personal tutor available anytime who asks thoughtful questions to help you gauge how well you understand ideas you are studying in class, without telling you the answers. This research developed and tested an artificial intelligence system called "Gadfly" that does exactly that. The tool uses the Socratic method, an ancient teaching approach where learning happens through questioning rather than lecturing, to have a conversation with the student in a casual text-based exchange. The study was based in a longstanding educational challenge: how to give students the benefits of one-on-one tutoring when there aren't enough human tutors available. The tutor was designed to work in online courses where students and teachers aren't online at the same time, creating meaningful learning conversations that ideally could promote critical thinking. When seven education and technology experts tested the system, they found it particularly good at asking open-ended questions, maintaining logical conversations, and being easy to use. They suggested improvements around helping students connect ideas to real-world situations and presenting different viewpoints on complex topics. This research shows that modern AI technology can effectively implement time-tested teaching methods in online environments. While not meant to replace human teachers, systems like Gadfly could provide valuable opportunities for students to check their understanding and practice critical thinking at their own pace, potentially making quality educational experiences accessible to many more learners.

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
OAI identifier oai:identifier
oai:vtechworks.lib.vt.edu:10919/135529

Chain of custody

source
Harvested from
Virginia Tech
Base URL
vtechworks.lib.vt.edu/oai/request
Last updated
2026-07-22
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