prd-workflow

# PRD Workflow - Feature Planning

**Current branch:** !`git branch --show-current 2>/dev/null || echo "not in git repo"`
**Existing plans:** !`ls plans/ 2>/dev/null | head -5 || echo "none"`

The PRD (Product Requirements Document) workflow transforms ideas into atomic,
implementable stories through structured interview, research, and specification.

## When to Use PRD Workflow

- Starting a new feature from scratch
- Turning a vague idea into concrete tasks
- Need thorough requirements gathering
- Want AI-assisted research and review

## The 4-Phase Approach

| Phase | Name | Purpose |
|-------|------|---------|
| 1 | Input Classification | Identify feature name and type |
| 2 | Interview + Exploration | Gather requirements, then run research/expert agents |
| 3 | Spec Write | Create specification with Implementation Stories section |
| 4 | Dex Handoff | Parse stories into Dex tasks |

**Key Change:** Research and expert agents run after interview completes (blocking). Findings are reviewed before spec writing.

## Starting the Workflow

```bash
/prd "Add user authentication"           # From idea
/prd path/to/existing/code               # From codebase
/prd                                     # Interactive discovery
```

## Phase 2: Interview + Exploration

**Commitment:** "I will ask 8-10+ questions covering: core problem, success criteria, MVP scope, technical constraints, UX flows, edge cases, error states, and tradeoffs."

### Interview (8-10+ questions)

Cover these areas:
- Core problem, success criteria, MVP scope
- Technical systems, data models, existing patterns
- UX/UI flows, error states, edge cases
- Tradeoffs, compromises, priorities

Focus on **non-obvious** details that will bite during implementation.

### After Interview, Run Agents (blocking)

Spawn ALL agents in parallel (user waits ~2-3 min):

**Research Agents:**
- `prd-codebase-researcher` - Existing patterns, files to modify
- `git-history-analyzer` - Prior attempts, why patterns evolved
-