DURA (Demystify-Use-Reflect-Assess): a lightweight framework for incorporating LLMs into courses

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

Description

DURA is the article's four-component framework for updating courses to incorporate AI/LLMs: Demystify how LLMs work and how they affect learning; Use LLMs with guidance and attribution; Reflect on LLM use and problem-solving; and Assess programming assignment skills through proctored assessments with retakes. The authors call it "our lightweight framework for incorporating LLMs into courses" and apply it in a large flipped CS2 course of 442 students. They state its components "deliberately support the learning process, as well as the need for reliable evidence of student learning," with demystification as the foundational component.

Design Implications

Context

Requirements

• The assess component is course specific and time-intensive, requiring question banks to support retakes, which the authors note was not reliable to generate without oversight
• Supporting test review and retakes requires support by the instructional team

Constraints

• The authors position the changes as manageable initial steps before overhauling labs and projects, and cannot attribute outcomes causally due to lack of a control group

Target Learners

• undergraduate CS2 (data structures) students
• instructors adapting CS courses for LLM use

Learning Goals

• meeting course learning outcomes without LLM assistance
• effective and ethical LLM use
• metacognition and self-regulation around LLM use

Claims

• Dura Updates Higher Music Caring Perception [+W]
• Help Seeking Decline Then Rise Dura Semester [~W]

Related Designs

Examples

-

Key Sources

• Margaret Ellis, Nikitha Donekal Chandrashekar, Sehrish Basir Nizamani, Mohammed Farghally, Jake O'Brien, and Naren Ramakrishnan. (2026). Demystify, Use, Reflect, Assess (DURA): An Experience Report on LLM Integration in CS2. arXiv. https://arxiv.org/abs/2606.30908

Page metadata

Field	Value
type	design
id	dura-framework-llm-course-integration
title	DURA (Demystify-Use-Reflect-Assess): a lightweight framework for incorporating LLMs into courses
description	DURA is the article's four-component framework for updating courses to incorporate AI/LLMs: Demystify how LLMs work and how they affect learning; Use LLMs with guidance and attribution; Reflect on LLM use and problem-...
status	review
generated	by process:settle-candidates on 2026-10-10
trust	unverified — no one has confirmed this page's content
sources	1 — margaret-ellis-2026

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