Barbero's 7-Step AI Workflow: Think Before You Code

Matteo Barbero's 7-step AI workflow front-loads all thinking before code generation. Steps run from free-form planning through PRD generation, issue and task breakdown, implementation with fresh AI sessions per task, code review, and final audit. Each step produces files feeding into the next. The core principle: AI's good at writing code but bad at deciding what to write, so humans handle the thinking upfront.

Matteo Barbero built a 7-step workflow for AI-assisted development that starts with a blunt observation: AI's good at writing code but terrible at figuring out what code to write. Fixing unmaintainable code is exactly why he designed this workflow. His solution is to front-load all the thinking before any code gets generated. The workflow moves through free-form planning, structured PRD generation, issue breakdown, task breakdown, implementation, code review, and final audit. Each step produces files that feed into the next.

One detail stands out. Barbero starts a fresh AI session for each task instead of keeping one long conversation going. "Long sessions with accumulated context tend to drift," he writes. Managing long AI sessions helps prevent exactly this problem.