Introduction

The "L" in SDLC stands for lifecycle — each phase's output is the next phase's input. This workshop takes that literally. Requirements become stories. Stories become a backlog. The backlog becomes a spec. The spec drives tests. Tests drive implementation. Implementation gets automated by a pipeline.

Every phase produces a durable file that feeds the next:

Raw sources → Structured notes → Requirements → User stories → Backlog → Spec → Architecture → Tests → Implementation → Autonomous pipeline

Nothing lives only in chat. Everything is committed to files. When a session ends, the work survives — and when the workshop ends, your taskflow/ repo contains every artifact above, plus a reusable Ralph pipeline that can build the next feature from your backlog on its own.

By the end of this workshop, you will be able to:

• Understand how Claude Code works — the agentic loop, context window, tools, sub-agents, and Plan Mode
• Configure Claude Code for your team — CLAUDE.md, settings, path-scoped rules, and auto memory
• Extend Claude Code — build custom agents, skills, hooks, and MCP integrations
• Apply Claude Code across the full SDLC — requirements engineering, system design, TDD implementation, and self-review
• Build an autonomous coding pipeline — the Ralph Loop, a bash-driven pipeline that builds features from your backlog without interactive prompting

Head to Getting Started when you are ready to set up your environment.