Teacher-Authored Prompts for Configuring Student-AI Dialogue: K-12 Classroom Implementation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Alex, Sun, Min, Esbenshade, Lief, Tian, Victor, Zhang, Zachary, He, Kevin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913042082562048
author Liu, Alex
Sun, Min
Esbenshade, Lief
Tian, Victor
Zhang, Zachary
He, Kevin
author_facet Liu, Alex
Sun, Min
Esbenshade, Lief
Tian, Victor
Zhang, Zachary
He, Kevin
contents GenAI has rapidly entered instructional and learning settings as a teaching assistant or AI tutor. However, less is known about how pedagogical intent connects to the learning generated within these systems, especially when student-facing AI dialogues are fine-tuned through teacher orchestration in live classrooms. This study examines a classroom deployment of a "Classroom Teaching Aide" (TASD) system, which enables teachers to author both a teacher-to-AI setup prompt (instructional scaffold) and a student-facing conversation starter to launch AI-mediated classroom discussions. We analyze a multi-subject pilot conducted in Spring 2025, involving 20 participating teachers (16 of whom implemented the system), across 39 classrooms and 77 TASD settings, yielding 1,479 student-AI conversations with 878 unique students. Using platform logs, LLM coding with human validation, and post-study teacher interviews (N=10), we characterize teacher authoring choices and link them to enacted student-AI interaction outcomes. In deployment, student-AI conversations were largely aligned with instructional intent: 71% were fully on-track, and fewer than 1% were substantially off-track. However, a persistent design-enactment gap emerged for cognitive demand: 38% of conversations under-reached the teacher-targeted DOK level, approaching 50% when targeting DOK 3. The study also shows that explicit finish lines in the prompt reduced the DOK gap by 0.22 levels (p < .001), and "no direct answers" guardrails reduced AI final-answer rates by 8.5 percentage points. These findings position teacher-authored prompt layers as critical orchestration levers that translate pedagogical intent into structured student-AI dialogue, underscoring both their promise for scalable classroom integration and the need for additional supports to reliably sustain higher-order reasoning during enactment.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16738
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Teacher-Authored Prompts for Configuring Student-AI Dialogue: K-12 Classroom Implementation
Liu, Alex
Sun, Min
Esbenshade, Lief
Tian, Victor
Zhang, Zachary
He, Kevin
Human-Computer Interaction
GenAI has rapidly entered instructional and learning settings as a teaching assistant or AI tutor. However, less is known about how pedagogical intent connects to the learning generated within these systems, especially when student-facing AI dialogues are fine-tuned through teacher orchestration in live classrooms. This study examines a classroom deployment of a "Classroom Teaching Aide" (TASD) system, which enables teachers to author both a teacher-to-AI setup prompt (instructional scaffold) and a student-facing conversation starter to launch AI-mediated classroom discussions. We analyze a multi-subject pilot conducted in Spring 2025, involving 20 participating teachers (16 of whom implemented the system), across 39 classrooms and 77 TASD settings, yielding 1,479 student-AI conversations with 878 unique students. Using platform logs, LLM coding with human validation, and post-study teacher interviews (N=10), we characterize teacher authoring choices and link them to enacted student-AI interaction outcomes. In deployment, student-AI conversations were largely aligned with instructional intent: 71% were fully on-track, and fewer than 1% were substantially off-track. However, a persistent design-enactment gap emerged for cognitive demand: 38% of conversations under-reached the teacher-targeted DOK level, approaching 50% when targeting DOK 3. The study also shows that explicit finish lines in the prompt reduced the DOK gap by 0.22 levels (p < .001), and "no direct answers" guardrails reduced AI final-answer rates by 8.5 percentage points. These findings position teacher-authored prompt layers as critical orchestration levers that translate pedagogical intent into structured student-AI dialogue, underscoring both their promise for scalable classroom integration and the need for additional supports to reliably sustain higher-order reasoning during enactment.
title Teacher-Authored Prompts for Configuring Student-AI Dialogue: K-12 Classroom Implementation
topic Human-Computer Interaction
url https://arxiv.org/abs/2604.16738