AI Course Experiments

Example Output

Published Output

The project ultimately resulted in a published introductory course on moxibustion through Flow Temple.

Overview

I developed an introductory moxibustion course for Flow Temple while testing where AI tools helped with research, structure, slides, and video. I began with books, articles, and practitioner resources, then used generated drafts as material to review and edit rather than finished teaching content.

Why I Started

I learn best by building. Making a course gave me a reason to organize what I was studying and test whether these tools could support a coherent learning experience.

Core Question

Can modern AI tools help transform large amounts of source material into structured educational content without losing the quality of the underlying knowledge?

Workflow Diagram

Key Experiments

Knowledge Synthesis

I used NotebookLM to compare source material and explore a course structure. Checking generated claims against the underlying sources remained an essential editorial step when deciding what belonged in an introductory lesson.

AI Slide Generation

I used Gamma to turn edited outlines into visual lesson drafts, then reviewed their wording and sequence.

AI Avatar Production

I tested HeyGen avatars and narration, including pronunciation and delivery. The example above shows one video produced during the experiment.

Automated Production Workflows

I tried a repeatable path from source collection to outline, slides, and video. Editorial checks remained necessary at each stage; I did not measure time saved.

Technology Stack

• Knowledge Synthesis: NotebookLM
• Content Generation: LLMs (Gemini, Claude, GPT-4)
• Slide Generation: Gamma
• Video Avatars: HeyGen
• Automation: Custom pipelines

Lessons Learned

The tools made it easier to draft different formats. The harder work was choosing what to teach, checking it against sources, and making the sequence understandable to a beginner.