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

2026-04-17

AI Summary

This study addresses the challenge of effectively translating teachers’ instructional intentions into meaningful student–AI dialogue outcomes in K–12 classrooms. To this end, we propose the Teacher-Assisted Scaffolding Dialogue (TASD) system, which incorporates a dual-layer prompting mechanism: teacher-defined guiding prompts for the AI and starter utterances for students, structuring interactions to align with pedagogical goals. Leveraging platform logs, human-validated LLM-based coding, and teacher interviews, we evaluated cognitive depth using the Depth of Knowledge (DOK) framework and examined prompting constraints such as “explicit endpoints” and “prohibition of direct answers.” Results show that 71% of student–AI dialogues accurately reflected instructional intent; “explicit endpoints” significantly reduced the DOK gap by 0.22 levels (p<.001), while “prohibition of direct answers” decreased AI’s provision of direct answers by 8.5 percentage points. This work is the first to empirically demonstrate the link between teacher prompt design and cognitive quality of student–AI dialogue in authentic classroom settings, revealing a critical gap between design aspirations and implementation realities.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Humans and AI: Interaction Techniques and Devices
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

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.

Problem

• teacher-authored prompts
• student-AI dialogue
• instructional intent
• cognitive demand
• classroom implementation

Innovation

• teacher-authored prompts
• student-AI dialogue
• instructional orchestration
• cognitive demand
• generative AI in education