My AI-Powered Design Process

Whether it’s 0-to-1, platform design, or feature-level work, the signal already exists. I use AI to synthesize it fast.

• Session recordings, NPS verbatims, support tickets, product analytics
• LLMs surface patterns across inputs in hours, not weeks
• Every design decision traces back to real customer behavior

No wireframes. Day one is a working prototype.

• Voiced prompts produce clickable, interactive simulations
• Stakeholders feel the product, not review a static mockup
• Better feedback. Faster decisions. The gap between review and understand closes.

Figma exploration takes days. AI takes hours. I run multiple models in parallel.

• Different form behaviors, state machines, user flows tested simultaneously
• Assumptions stress-tested before a single component is built
• The right idea reaches engineering with conviction, not compromise

No scheduled design crits. No screen shares. Prototypes go out async.

• Stakeholders review on their time, leave timestamped reactions
• Syncs happen with real context, not cold first impressions
• Review cycles shrink. Feedback gets broader. Momentum stays.

Enterprise products fail at the edges. I design for them on purpose.

• Empty states, permission boundaries, degraded network conditions: all prototyped
• AI generates realistic data sets and simulates load behaviors
• Problems get caught in prototype, not in production

Logic validated. Craft phase begins. Everything built to spec in Figma.

• Accurate tokens, correct states, proper spacing, motion-ready
• Every component maps back to the design system
• Engineers don’t interpret intent. They implement it.

Figma is the source of truth. Not “ready for handoff” in theory. Actually ready.

• Specs, tokens, states, and annotations structured for direct implementation
• I stay engaged during build: in-browser reviews, flagging drift early
• The difference between something that looks right and something that feels right