AI Design Navigator - Figma Plugin
From two semesters of AI research to a working Figma plugin.
AI Design Navigator — plugin panel inside Figma. Recommendations are grounded in primary research and updated via live web search.
Project Details
Tools
Figma API, Claude AI + Web Search
Role
UX Researcher and Product Designer
Team
Me
Timeline
08 Weeks
Overview
AI tools have proliferated across every stage of the design process.
What hasn't kept pace is guidance - a clear answer to which tool serves which moment, and what switching costs are involved.
This project addresses that gap directly.
Above : browser with 10+ AI tool tabs open. Simple, relatable.
The Problem
The AI tool landscape has grown faster than the guidance around it.
The result : Designers know the tools exist but lack a clear framework for when to use them, what each costs in terms of workflow disruption, and whether switching environments is worth it for a given task.
The Research
Two semesters of primary research
across the full design pipeline.
As a Graduate Assistant at RIT, I conducted structured research into AI tools across the UI/UX design workflow over two semesters. Semester 1 focused on tool evaluation - six tools tested against a standardised prompt, rated across four criteria : workflow fit, information design, interaction logic, and editability.
Above : Research table - 6 tools (and more were researched) × 4 criteria
The Plugin
A contextual recommendation engine
embedded in the designer's workflow.
The plugin reads the selected frame, infers the design stage, and prompts the designer with a single open question. Recommendations are generated from the primary research database and supplemented by live web search - ensuring the tool stays current as the landscape evolves, without manual updates.
Above : Each recommendation surfaces three fields: what to prepare before switching, what to expect on return, and known limitations from the research.
The System
A design system built for a professional audience.
What's Next
A living tool built to stay current.
The recommendation database is seeded from primary research, but the plugin runs a live web search on every query. New tools are surfaced automatically. Known tools that have changed significantly are flagged. The research provides the framework;
the search layer ensures the data doesn't age.
Next iteration : Community-sourced ratings alongside the research baseline - allowing practising designers to validate or challenge the original findings with their own firsthand experience.
Primary research,
shipped as a product.