Shown·Claude Code·Universities
Course modernization with agent fleets
Claude Code turned course evaluations into tracked GitHub issues, then ran agents to rebuild assignments, exams and about two dozen slide decks.
Roughly two dozen decks were rebuilt into Quarto reveal.js with speaker notes and refresh checklists, and the approach was reused for two more courses.
Overview
How it was set up
Claude Code with GitHub issues as specs, a shared template spec, one agent per deck about six at a time, Quarto reveal.js, and web search for current examples.
Worth knowing
The author hand-built and approved one reference deck before scaling the fan-out.
A prompt to start from
Read the attached course evaluations and summarize the constructive themes. Then file a GitHub tracking issue for [course] with one checklist box per theme, so each fix can be checked off with the commit that shipped it.Written by Agentic Feats from the source. Not the author's exact prompt.
Sources 1
History
- Source published
- 2026-06-03
- Added to Agentic Feats
- 2026-10-13
- Pick
- No
- Markdown copy
- /c/course-modernization-with-agent-fleets-claude-code.md
More in universities
5 featsResultThe draft was usable but weaker than accepted NSF summaries; thinking mode helped, though it began hallucinating and misreading the sources.
ResultFrom one short prompt, Manus produced a publishable-style report with charts from 1,000 synthetic responses. The data is made up.
ResultA roughly 3,000-line open-source Canvas tool built in four months. It cut a 45-minute weekly student check to a 2-minute conversation with Claude.