-
Notifications
You must be signed in to change notification settings - Fork 0
Home
A living course for IT professionals who are comfortable in an AI chat window and starting to build real software with it, but who are still copy-pasting between the chat and their files. The goal is to replace that loop with durable engineering workflows: version control, collaboration, CI/CD, runners, and the tools that extend AI into real systems.
Thesis: the model is the cheap, swappable part. The workflow around it is the skill that lasts. This course is deliberately model- and vendor-agnostic: whichever LLM you use, the scaffolding is the same.
This repo is the course, and it also dogfoods the course: it's version-controlled, it commits its
own AI instructions file (AGENTS.md, the subject of Module 5), and each module is
built on a branch and merged through review, the same motion the modules teach.
- Module 1: The Copy-Paste Problem
- Module 2: Version Control as a Safety Net
- Module 3: Version Control for Words, Not Just Code
- Module 4: Getting the AI Out of the Browser
- Module 5: Commit the AI's Config, Not Just the Code
- Module 6: Branches as Sandboxes for Experiments
- Module 7: Worktrees for Running Agents in Parallel
- Module 8: Remotes and Hosting (GitHub, the Alternatives, and Owning Your Repo)
- Module 9: Issues and the Task Layer
- Module 10: Reviewing Code You Didn't Write
- Module 11: Collaboration: Humans and Agents on One Repo
- Module 12: When It Goes Wrong: Revert, Reset, and Recovery
- Module 13: Testing in the AI Era
- Module 14: Continuous Integration
- Module 15: Security Scanning for AI-Generated Code
- Module 16: Containers and Reproducible Environments
- Module 17: Secrets, Config, and Environments
- Module 18: Continuous Delivery and Deployment
- Module 19: Runners, the Compute Behind the Automation
- Module 20: MCP Servers, Giving the AI Hands
- Module 21: Skills: Teaching the AI Your Playbook
- Module 22: Securing Third-Party MCP Servers and Skills
- Module 23: Working with Existing Codebases
- Module 24: Assistive Agents (AI Review and Issue Triage)
- Module 25. Autonomous Agents: Issue-to-PR and Self-Healing CI
- Module 26: Orchestrating Multiple Agents
- Module 27. Evals: Trusting an Agent That Acts Without You
📖 This wiki is generated from the course repo; edit
modules/there, not these pages.
Generated from the ai-workflow-course repo • the model is the cheap, swappable part; the workflow is the durable skill.
Unit 1: Get out of the chat window
- 1 · The Copy-Paste Problem
- 2 · Version Control as a Safety Net
- 3 · Version Control for Words, Not Just Code
- 4 · Getting the AI Out of the Browser
- 5 · Commit the AI's Config, Not Just the Code
- 6 · Branches as Sandboxes for Experiments
- 7 · Worktrees for Running Agents in Parallel
Unit 2: Make it shareable, reviewable, recoverable
- 8 · Remotes and Hosting (GitHub, the Alternatives, and Owning Your Repo)
- 9 · Issues and the Task Layer
- 10 · Reviewing Code You Didn't Write
- 11 · Collaboration: Humans and Agents on One Repo
- 12 · When It Goes Wrong: Revert, Reset, and Recovery
Unit 3: Automate the checking and shipping
- 13 · Testing in the AI Era
- 14 · Continuous Integration
- 15 · Security Scanning for AI-Generated Code
- 16 · Containers and Reproducible Environments
- 17 · Secrets, Config, and Environments
- 18 · Continuous Delivery and Deployment
- 19 · Runners, the Compute Behind the Automation
Unit 4: Extend the AI into your systems
- 20 · MCP Servers, Giving the AI Hands
- 21 · Skills: Teaching the AI Your Playbook
- 22 · Securing Third-Party MCP Servers and Skills
- 23 · Working with Existing Codebases
Unit 5: AI in the Loop
- 24 · Assistive Agents (AI Review and Issue Triage)
- 25 · Module 25. Autonomous Agents: Issue-to-PR and Self-Healing CI
- 26 · Orchestrating Multiple Agents
- 27 · Module 27. Evals: Trusting an Agent That Acts Without You
Finale