Systems Engineering
ASU Canvas Builder
AI Course Authoring System
Draft and transform learning materials into Canvas-ready courses with WCAG 2.1 AA and ASU Design standards embedded.
EdPlus at ASU
- Python
- Claude
- Canvas
Self-reported
35+ onboarded
Instructional designers onboarded; 18 report active use in a team poll.
Self-reported
7 of 8
Pilot survey respondents report less time on assessments and planning.
Self-reported
8 of 8
Pilot cohort users rated it 4 or 5 out of 5 for satisfaction and for speed and quality of work.
The Friction
Designers applied standards by hand at the end of a course build, when fixes cost the most, and accessibility and alignment, the checks that mattered most, were the easiest to defer. Designers were also still editing in the live course because there was nowhere safer to work.
What I Did First
This is the successor to the Canvas Course Authoring Workbench. I had already answered the interface questions by interviewing four designers about how they build; the open questions sat around the editor. Standards had to be enforced while someone was authoring, when a fix is cheap, and nothing could reach a live course without a review step.
What I Built
A Claude Code and Codex plugin: 28 skills, 112 Python scripts, 17 standards documents, and 8 page templates. The WCAG 2.1 A and AA static subset runs on every content surface (pages, quizzes, assignments, and discussions) as findings that warn on pages; interactive activities must pass before they go live. A three-tier course level system detects Introductory and Advanced from the course code and calibrates Bloom's ranges, scaffolding, and rubric descriptors to match. Course content stages before push with a preview; page, assignment, and discussion text and Classic Quizzes can be rolled back. Separate skills validate CLO, MLO, assessment, and material alignment, and score whether an assessment strategy can still certify learning when students have AI.
What Came of It
I onboarded 35+ instructional designers, and 18 report active use in a team poll. In a pilot cohort survey, 7 of 8 respondents report spending less time on assessments and planning, and all 8 rated it 4 or 5 out of 5 for overall satisfaction and for improving the speed and quality of their work. It is distributed as a versioned plugin with a contribution process scoped to ASU colleagues, and contributions have started arriving.
Scope and Limits
Still in beta. The pilot cohort is small and its survey figures are self-reported. Confidence in the correctness of generated output scored lower than every other dimension, which is where the next work goes. Assessment assurance scoring produces a judgment. It certifies nothing.
More systems, and the learning experiences behind them.
or write directly to brent.michael670@gmail.com