Skip to content

Phased Agent Workflow (PAW)

PAW Logo

PAW is a VS Code extension that coordinates multi-stage AI agent workflows for feature implementation and code review. It transforms complex development tasks into structured, verifiable phases with clear handoffs between specialized agents.

Why PAW?

Building features with AI coding agents is powerful, but without structure, it's easy to lose track of decisions, introduce inconsistencies, or struggle to iterate when things go wrong.

PAW provides:

  • Structured phases — Move from spec to implementation to docs with clear checkpoints
  • Durable artifacts — Every decision is captured in version-controlled Markdown
  • Rewindability — Fix upstream problems and regenerate downstream work
  • Human oversight — You approve specs, plans, and PRs at critical decision points
  • Two workflows — Build new features OR review existing pull requests

Quick Start

  1. Install the extension from GitHub Releases
  2. Open a Git repository in VS Code
  3. Run PAW: New PAW Workflow from the Command Palette
  4. Follow the guided workflow through each stage

Get Started →

Two Workflows

Implementation Workflow

Build features from scratch through structured phases:

Specification → Planning → Implementation → Finalization

Use for: New features, enhancements, refactors, and bug fixes.

Learn more →

Review Workflow

Thoroughly review pull requests with evidence-based feedback:

PR → Understanding → Evaluation → Feedback Generation

Use for: Reviewing any PR—especially large or poorly-documented ones.

Learn more →

Key Concepts

Concept Description
Stages Workflow milestones (Specification, Planning, Implementation, Finalization)
Phases Discrete implementation chunks within the Implementation stage
Agents Specialized AI chat modes that handle specific stages
Artifacts Durable Markdown documents produced at each stage

Documentation

Requirements

  • VS Code with GitHub Copilot
  • Git repository
  • GitHub MCP Tools or Azure DevOps MCP Tools (recommended)