---
title: "Course modernization with agent fleets"
canonical: "https://agenticfeats.com/c/course-modernization-with-agent-fleets-claude-code/"
agents: ["Claude Code"]
evidence_grade: "A"
outcome: "completed"
job_type: "Learning"
industry: "Universities"
roles: ["Education"]
source_url: "https://practicespace.substack.com/p/using-claude-code-to-modernize-my"
evidence_url: "https://github.com/noise-lab/security-course/issues/5"
source_date: "2026-06-03"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# 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.

Result: 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.

## 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.

## Prompt

```text
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.
```

## Evidence note

Public course repos and issues linked; author describes outcomes, no hard time numbers

## Sources

- Original: https://practicespace.substack.com/p/using-claude-code-to-modernize-my
- Evidence: https://github.com/noise-lab/security-course/issues/5

## The receipt

- Agent: Claude Code
- Evidence: Shown (grade A, artifact linked)
- Outcome: Completed
- Job type: Learning
- Industry: Universities
- Roles: Education
- Source: Blog
- Published: 2026-06-03
- Added: 2026-10-13