Skip to content

Sequence of nine structured instructor-led AI demonstrations for modeling strategic LLM delegation and evaluation

Design · All designs
Evidence · 1 claim (1 for) · 1 study (1 causal), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

A deployable classroom intervention: nine short, instructor-led AI demonstrations delivered at roughly weekly cadence, progressing from baseline tool literacy through pedagogical framing (metacognition, Socratic tutor system prompts), strategic delegation of low-risk programming tasks for a truss design project, and LLM benchmarking. As the article states, "Each demonstration occupied approximately 10–15 minutes at the end of a regularly scheduled class meeting and recurred at roughly weekly cadence." Demonstration workflows and the Socratic tutor system prompt are publicly documented in appendices.

Design Implications

Context

Requirements

  • Delivered by the regular course instructor within existing lecture time without displacing core content
  • Complete workflows and system prompt are documented and reproducible from the published appendices

Constraints

  • Demonstrations evolved dynamically by instructor judgment rather than a rigid script, so components driving outcomes cannot be isolated
  • Some timing was misaligned with student readiness and end-of-semester fatigue affected later sessions

Target Learners

  • undergraduate engineering students in a core problem-solving course

Learning Goals

  • strategic LLM delegation
  • model evaluation and benchmarking
  • metacognitive awareness of AI's role in learning

Claims

Examples

-

Key Sources

  • Shuang Geng, Helen Lallos-Harrell, Jiya Ashar, Thomas J. McKenna, Annwesa Dasgupta, Caleb Farny, and Emma Lejeune. (2026). Structured AI Demonstrations and Student LLM Use in Engineering Mechanics: Study Design and Preliminary Results. https://arxiv.org/abs/2607.28710
Page metadata
Field Value
type design
id nine-structured-ai-demonstrations-sequence
title Sequence of nine structured instructor-led AI demonstrations for modeling strategic LLM delegation and evaluation
description A deployable classroom intervention: nine short, instructor-led AI demonstrations delivered at roughly weekly cadence, progressing from baseline tool literacy through pedagogical framing (metacognition, Socratic tutor...
status review
generated by process:settle-candidates on 2026-10-11
trust unverified — no one has confirmed this page's content
sources 1 — shuang-geng-2026

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