Small Courses as Capture Vessels for Live AI Work

articleideaaicourseswizardshitcontent-strategydiscovery-backfillneeds-source

turns a live X thread into a course seed for wizardshit.ai and the joelclaw discovery pipeline, but needs parent context before publishing as a real lesson

Joel asked @joelclaw and James Longster whether he could make “a small course out of this” for wizardshit.ai. That’s the whole extracted artifact, which is both annoying and useful.

The useful bit is the shape: a live public thread becomes a course seed. Not a giant curriculum. Not a 90-module bullshit monument. A small course, captured while the idea still has heat.

The annoying bit is that X did not expose the parent context, so “this” is currently a hole in the record. The note is still worth keeping because it marks a pattern for joelclaw: discovery backfills should preserve thin signals, but they should also label missing source context instead of pretending the artifact is complete.

Key Ideas

  • wizardshit.ai can use small courses as fast containers for live AI work instead of waiting for polished curriculum shapes.
  • A short X post can be enough to preserve intent, but not enough to preserve source truth.
  • Joelclaw discovery notes need a clear needs-source path when extraction misses the parent thread or referenced material.
  • Backfilled links from Slack are valuable as signals, but the pipeline should separate “captured link” from “understood artifact.”