Learn a repeatable workflow for shipping features with AI coding agents - from planning through autonomous execution.
This hands-on workshop walks you through the full lifecycle of AI-assisted development. You'll start with the fundamentals: understanding what LLMs can and can't do, and setting up your environment. Then you'll move into planning, using skills like /grill-me to stress-test vague requirements, /write-a-prd to produce structured PRDs, and /prd-to-issues to break work into thin, vertical "tracer bullet" slices that an agent can pick up independently.
From there, you'll shift into execution: running an AI agent (Ralph) human-in-the-loop with TDD, observing how it selects tasks, writes tests, implements code, and commits, then learning to refine your prompts and issue descriptions based on where it struggles. Finally, you'll explore running agents fully autonomously (AFK) and learn how to design codebases that AI agents love to work in.
What you'll learn:
- How to turn ambiguous requirements into agent-ready issues
- The tracer bullet approach to slicing work for AI agents
- Running AI agents human-in-the-loop and autonomously with TDD
- Designing codebase architectures that maximize agent effectiveness
Who it's for: Engineers who want to go beyond chat-based AI assistance and build a real workflow for shipping production features with autonomous coding agents.