AI note-taking tools are everywhere, but people rarely double-check the summaries or action items they generate. The problem space was ambiguous with no clear patterns to follow. Our team set out to understand how people build trust with AI meeting tools, and when they decide to verify the outputs.

What I did:
- Ran expert interviews and user interviews to narrow the problem space down.
- Led co-design workshops that reshaped our assumptions and broadened our design scope.
- Built prototypes with Figma Make and Claude Code to test concepts quickly.
- Defined the design system and brand guidelines, and created wireframes and prototypes for the core workflows.

Outcome & Impact:
Delivering prototypes, design recommendations, and AI adoption guidelines to Microsoft, giving them a research-backed framework for building trust and verification into AI meeting tools.