Context: This document outlines a possible workflow for using large language models such as ChatGPT or Claude to review and improve LMS course materials exported in IMS Common Cartridge format. The proposal is exploratory and intended for discussion with Distance & Online Learning leadership and AI Fellows across SUNY.
Overview Concept

Large language models are increasingly capable of reviewing and revising structured documents. One potential application in higher education is using AI to analyze course packages exported from learning management systems.

D2L and many other LMS platforms support the IMS Common Cartridge (CC) standard, which packages course content into a portable format containing HTML pages, XML manifests, assessments, and supporting files.

The proposed idea is to build a workflow that allows course cartridges to be exported, interpreted as structured content, reviewed or revised with AI tools, and then rebuilt for re-import into the LMS.

The intention is not to automate course design, but to create a human-in-the-loop review pipeline that could support instructional design teams and faculty.

Conceptual Workflow Pipeline

The proposed workflow follows a structured pipeline from export through re-import:

StageDescription
1. Course Export Course exported from D2L as a Common Cartridge (.imscc) file.
2. Cartridge Extraction The cartridge is unpacked into its underlying files: manifest XML, HTML pages, assessment XML, and linked resources.
3. Structured Interpretation Content is parsed into a structured representation of modules, pages, assignments, and resources.
4. AI Review AI systems analyze course content and suggest revisions or improvements.
5. Reconstruction Revised content is written back into the course structure.
6. Cartridge Rebuild The package is rebuilt into a valid .imscc file.
7. LMS Re-Import The updated course package is imported back into D2L for faculty review.
Principle
The AI system operates primarily on course content — pages, text, explanations — while structural metadata and packaging remain controlled by software tools.
Potential Use Cases Applications

If implemented carefully, this workflow could support several instructional design tasks:

Course Refresh

Identify outdated references, broken links, or unclear explanations in older courses.

Accessibility Review

Flag missing alt text, unclear headings, or readability issues.

Instructional Design Support

Generate draft discussion questions, summaries, or formative prompts for existing content.

Consistency Checks

Review for formatting consistency across modules and pages.

Content Summaries

Generate module summaries or study guides from existing materials.

Course Documentation

Convert course exports into human-readable documentation for program review or accreditation.

Limitations and Risks Constraints

Important technical and policy limitations must be acknowledged before attempting a system like this.

Packaging Complexity

Common Cartridge files depend on precise XML relationships between resources. Incorrect edits can easily break cartridge imports.

Assessment Formats

Quizzes and tests rely on QTI XML formats that vary between LMS platforms. Automated editing of assessments could introduce errors.

Vendor Extensions

Although Common Cartridge is a recognized standard, LMS platforms frequently add proprietary extensions that complicate automated manipulation.

AI Reliability

LLMs generate plausible language but may introduce inaccuracies. All AI-generated revisions require human review before adoption.

Compliance Considerations

Course materials may contain licensed or copyrighted content. Any AI workflow must align with institutional policies regarding FERPA, copyright, and AI governance.

Reality Check
This approach should be considered an instructional design support tool, not an automated course generation system.
Possible Next Steps Pilot

If there is interest in exploring this concept, a small prototype could test the workflow before any broader commitment:

Stage 1

Build a parser that safely extracts content from a D2L cartridge.

Stage 2

Run AI analysis on HTML course pages only.

Stage 3

Rebuild a valid cartridge without modifying structural metadata.

Stage 4

Test import into D2L and review results with instructional designers.

This staged approach allows feasibility testing before considering broader adoption.

Questions for the SUNY Community Inquiry

Before pursuing development, it would help to know whether similar work is already underway across SUNY:

  • Are any campuses experimenting with AI tools to review or revise LMS course exports?
  • Are there existing scripts or tools that parse D2L Common Cartridge packages?
  • Has anyone explored AI-assisted course refresh workflows within instructional design teams?

If work is already happening in this space, coordination could help avoid duplication and accelerate development.

Contact Discussion
Contact
Steven M. Schneider
Professor of Information Design & Technology
Co-Director, AIX Center
SUNY AI Fellow for the Public Good
SUNY Polytechnic Institute