Heuristic evaluation
Flags usability risks using established interaction principles and severity levels.
UX-Ray, independent R&D
AI-assisted UX evaluation
AI-assisted UX evaluation for scalable design workflows
An independent R&D project exploring how AI can reduce audit friction and bring clearer feedback into Figma.
Quality control in three steps
From selected frame to an actionable audit
The three steps keep review in the design canvas, moving from a selected interface to structured findings the team can discuss.
Design reviews depend on time, reviewer availability, and a shared understanding of quality. As products and design systems grow, heuristic checks, accessibility review, visual hierarchy, and brand compliance become difficult to apply consistently.
UX-Ray explores an AI-assisted evaluation layer inside Figma. The concept combines design metadata, visual analysis, and structured recommendations so designers can review work earlier while keeping judgment and final decisions with the team.
"The goal was never to replace designers. The goal was to reduce operational friction, accelerate evaluation cycles, and bring clarity to design decisions through AI-assisted workflows."
Product demo
Watch the evaluation flow inside Figma
The video follows the working sequence from frame selection through analysis and categorized recommendations.
Executive summary
A UX audit layer inside the design tool
UX-Ray explores how AI can support design evaluation directly in the environment where designers work. The plugin analyzes Figma frames against usability heuristics, accessibility indicators, visual hierarchy principles, and custom brand guidelines.
The project responds to a practical operations problem: UX reviews often happen late, vary by reviewer, and consume time that product teams rarely have. UX-Ray was designed to provide faster, structured feedback while keeping strategic judgment in human hands.
The problem
Quality review does not scale naturally with product complexity
As products and design systems grow, evaluation work becomes harder to run consistently. Teams repeat accessibility checks, visual reviews, content critiques, and heuristic analysis across many screens and iterations.
The friction is not only time. It is uneven quality, late feedback, missed consistency issues, and cognitive load for designers who need to make decisions quickly. UX-Ray started with a question: how can AI help teams scale evaluation without reducing the role of human designers?
Strategic vision
AI should support UX workflows, not replace human design thinking. UX-Ray acts as an operational assistant that surfaces patterns, explains risks, and helps designers focus their attention.
Core capabilities
Multiple evaluation layers in one review pass
Accessibility validation
Reviews contrast, readability, and WCAG-style indicators to surface common barriers.
Visual hierarchy analysis
Identifies spacing, alignment, structure, and emphasis issues that affect scanning.
Brand consistency review
Compares interface choices against custom typography, color, spacing, and style rules.
Technical architecture
From Figma frame to categorized recommendations
The architecture turns recurring checks into a consistent five-step review flow, surfacing issues earlier while designers decide priorities.
- Extract design structure and semantic metadata from selected Figma frames.
- Generate visual and contextual analysis inputs for the evaluation prompt.
- Send structured prompts to GPT-4 Vision for review.
- Parse AI feedback into categories, severity levels, and explanations.
- Return actionable recommendations directly inside the design workspace.
How UX-Ray works
A review loop inside the design workspace
The product flow moves from a selected Figma frame to an AI-assisted audit report with visual annotations and recommendations.
-
01
Select your frame
Choose the Figma frame you want to evaluate.
-
02
Click Run UX-Ray
Activate the AI-powered analysis engine from inside the working context.
-
03
Get instant audit report
Review actionable findings with visual annotations and recommendations.
Evaluation foundation GPT + Figma API + Human UX Strategy
Enterprise potential
From plugin to design operations layer
The longer-term direction is team-wide evaluation, organization-specific guidelines, and AI-assisted governance for distributed or regulated teams. The focus is consistent review language and faster routing of issues that need human judgment.
Shared review workflows
Team workspaces, collaborative reviews, and version-aware feedback can make the audit process easier to coordinate across product teams.
Governed evaluation at scale
Custom guidelines, advanced analytics, API integration, and tailored reporting point toward a more adaptable design-operations layer.
Contribution
Role and methods in one view
My role
I defined the product concept, evaluation logic, UX flow, and AI-assisted feedback model.
- Product strategy and plugin UX
- AI workflow and prompt structures
- Technical integration concept for in-Figma feedback
Tools and methods
Figma Plugin API
TypeScript
GPT-4 Vision
WCAG contrast checks
Heuristic evaluation
Local feedback loop
Prompt design
Cursor
Outcome and reflection
Outcome
A working concept for faster feedback loops, more consistent UX reviews, and less repetitive operational work, with a path toward scalable design operations.
Reflection
Structured analysis can improve clarity, consistency, and operational flow in product organizations. The expertise still has to come from a person.
UX-Ray is an independent R&D concept and is not affiliated with Figma or OpenAI. Performance figures and projected improvements are based on internal experimentation, industry benchmarks, and exploratory testing rather than production-scale deployment.