Skip to content

Non-generative AI academic chatbot with TA-supported knowledge base and #quizme practice function

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 causal), q3 · 0 of 1 report an effect size · 2 claims rest on one study

Description

A text-based chatbot with non-generative AI capability that sent 2-3 scheduled, customized messages per week (about 40 per semester) to students in large online courses. Messages provided "timely reminders about course requirements", customized feedback on individual progress, connections to academic supports, and an additional communication channel. When students texted in, the bot responded from a pre-programmed knowledge base; low-probability matches were flagged to the course TA, whose manual responses updated the knowledge base. A #quizme function in Government let students request multiple-choice practice quizzes before exams.

Design Implications

Context

Requirements

  • Faculty buy-in and a course TA embedded in both the course and chatbot administration to maintain the knowledge base and review bot responses daily for quality control
  • Students opted in to receiving text-based communication from the university

Constraints

  • The #quizme function was deployed only in Government, since Microeconomics did not have exams
  • Messages required timely gradebook information from the TA to customize outreach to students' performance each week

Target Learners

  • Undergraduate students in large-enrollment, asynchronous online courses at a minority-serving public university

Learning Goals

  • Course engagement and assignment completion
  • Course performance and completion
  • Connection to academic supports such as tutoring

Claims

Examples

-

Key Sources

  • Meyer, Katharine, Lindsay C. Page, Catherine Mata, Eric N. Smith, B. Tyler Walsh, C. Lindsey Fifield, Michelle Tyson, Amy Eremionkhale, Michael Evans, Shelby Frost, and Eye Eoun Jung. (2026). Let's Chat: Leveraging Chatbot Outreach for Improved Course Performance (NBER Working Paper No. 35397). National Bureau of Economic Research. doi:10.3386/w35397. Also released as EdWorkingPaper 22-564, Annenberg Institute at Brown University: https://edworkingpapers.com/ai22-564
Page metadata
Field Value
type design
id gsu-academic-chatbot-mainstay
title Non-generative AI academic chatbot with TA-supported knowledge base and #quizme practice function
description A text-based chatbot with non-generative AI capability that sent 2-3 scheduled, customized messages per week (about 40 per semester) to students in large online courses.
status review
generated by process:settle-candidates on 2026-10-10
trust unverified — no one has confirmed this page's content
sources 1 — meyer-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.