Skip to content

TASD: teacher-authored prompt layers as orchestration levers for configuring student-AI dialogue

Design · All designs
Evidence · 3 claims (2 for, 1 mixed) · 1 study (1 design), q2 · 0 of 1 report an effect size · 3 claims rest on one study

Description

TASD (Colleague AI Classroom Teaching Aide) frames student-AI interaction as a configurable classroom routine rather than an autonomous tutor. It uses a three-layer structure: a foundational LLM, a researcher-designed system-level prompt, and a top layer of teacher-authored prompts encoding local goals, plus a student-facing opening instruction. The article treats teacher prompts as "interaction design artifacts" that specify what students work on, how the AI structures participation, and what boundaries preserve responsible use, positioning teacher-authored prompt layers as levers translating pedagogical intent into structured dialogue.

Design Implications

Context

Requirements

  • Teachers must author both an AI-facing shared prompting layer and a student-facing opening instruction to launch the activity

Constraints

  • The article notes the need for additional supports to reliably sustain higher-order reasoning during enactment, given the persistent DOK under-targeting gap

Target Learners

  • K-12 middle school (grades 6–8) and high school (grades 9–12) students across mathematics, science, ELA, social studies, world languages, and CTE

Learning Goals

  • Task-aligned classroom discussion
  • higher-order thinking and cognitive demand realization
  • responsible AI use

Claims

Examples

-

Key Sources

  • Alex Liu, Min Sun, Lief Esbenshade, Victor Tian, Zachary Zhang, and Kevin He. (2026). Teacher-Authored Prompts for Configuring StudentAI Dialogue: K12 Classroom Implementation. https://arxiv.org/abs/2604.16738
Page metadata
Field Value
type design
id tasd-teacher-authored-prompt-orchestration
title TASD: teacher-authored prompt layers as orchestration levers for configuring student-AI dialogue
description TASD (Colleague AI Classroom Teaching Aide) frames student-AI interaction as a configurable classroom routine rather than an autonomous tutor.
status review
generated by process:settle-candidates on 2026-10-12
trust unverified — no one has confirmed this page's content
sources 1 — alex-liu-2026

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