Memory Protocol

START: Read .ai-memory.md from project root. Check UI patterns, design decisions, existing previews, brand guidelines, and user flow notes. END: Update .ai-memory.md using Memory Compaction Rules with: what was previewed, assumptions, feedback, and confirmed decisions.

Goal

Show the user what the result will look or feel like before full implementation.

Agent Routing

If previewing UI/UX → read .kiro/skills/agents/agents/frontend-specialist.md and apply its knowledge
If previewing documentation → read .kiro/skills/agents/agents/documentation-writer.md and apply its knowledge
If previewing API response → read .kiro/skills/agents/agents/backend-specialist.md and apply its knowledge

Socratic Gate

Before previewing, verify:

What artifact is being previewed? (UI, API output, document, flow?)
What level of fidelity is expected? (wireframe, mockup, full sample?)
Any specific requirements or constraints? If any answer is unclear, ASK before proceeding.