All Case Studies

Guardian

Guardian is Protect AI's security tool that scans machine learning environments for risks, misconfigurations, and potential vulnerabilities. Think of it as an always-on security system for AI pipelines.

Protect AI September 2023 — Present Lead Designer + Design Systems
Data Visualization AI Security Machine Learning
Guardian dashboard — Protect AI

Objective

Design an experience that makes AI/ML model security understandable, trustworthy, and actionable for engineers and analysts.

Target Personas

ML Engineer

"Before I download or deploy a model, tell me if it's risky and how to fix it."

Platform Engineer

"Automate checks in pipelines without slowing delivery."

Security Analyst

"Get reliable signal, reduce false positives, and prove compliance."

Compliance Officer

"Show evidence that models meet internal and regulatory standards."

UX Approach

Protect AI Personas diagram

Key Flows

Scan a model pre-download

Results detail → Fix guidance → Approve or Quarantine

CI enforcement setup

Pick template → Configure policy → Test run → Gate on severity

Policy authoring

Create rule → Scope to environments → Review impact → Publish

Triage & remediation

Prioritized queue → Evidence panel → Assign → Track to resolution

Audit & reports

Time-series of findings, SBOM export, policy drift report

Challenges & Solutions

Security + ML Complexity

Users span ML, Platform, and SecOps — jargon differs. Solved with role-based defaults, glossary tooltips, and progressive disclosure.

Signal vs. Noise

Users distrust unreliable results. Calibrated severity and confidence badges, grouped duplicates, clear provenance, and one-click risk acceptance with expiry.

Shift-Left Without Slowing Delivery

Local scanner path for pre-commit checks, CI templates with runtime estimates, dry-run mode, and policy preview.

Policy Authoring

Policy Builder with rule cards, natural language assist, scoping, simulation, versioning, and diff on publish.

Data Density

Table virtualization, column presets per persona, smart grouping, and finding detail drawer with tabs.

Enterprise Trust

Attestations/SBOM export, immutable audit log, report templates, and clear lineage from policy to scan to action.

Radius Design System

Built alongside Guardian to unify the product surface and accelerate delivery.

Foundations

Design tokens, light/dark themes, density scales, motion

Components

Primitives (Button, Input, Tabs, Table) and complex patterns (Scan Result Card, Finding Detail Drawer, Diff Viewer, Policy Builder, Severity Badge)

Patterns

Progressive disclosure, inline explainers, review & publish workflows, wizard setup, zero-state guidance

Accessibility

WCAG 2.2 AA contrast, keyboard focus order, live regions for scan status, reduced motion support

Outcomes

Clarity

Users reported faster understanding of what's wrong and what to do

Speed

Local scanning + CI templates reduced setup time; policy preview decreased gate failures

Adoption

Role-tailored defaults and better evidence improved trust across teams

Scalability

Radius DS accelerated new features and ensured consistency across the platform