AI-Powered Media
Intelligence Platform
Transformed a technically advanced AI tagging platform into a transparent, efficient, and enterprise-ready product.
.png)
Role
Lead Product Designer (UX/UI)
Company
GRAIPH
Duration
2021 - 2025 (4 years)
Team
Devices
Web · Desktop App · Tablet
Tools & methodology
Figma · Adobe XD · FigJam · Slack · Miro
Impact at a Glance
-
40% reduction in task completion time (8 → 4.8 min)
-
60% improvement in usability score
-
80+ UI components developed and documented
4-person product team (CEO, CIO 2 engineers)
PROJECT IMPACT
40%
Faster Task Completion
60%
Usability Improvement (SUS 68 → 85)
80+
Reusable Components Delivered
+60%
Increase in AI Trust
CONTEXT & CHALLENGE
GRAIPH’s AI tagging engine was powerful but difficult to understand for non-technical users.
Workflows were fragmented across 4 screens.
AI decisions felt like a black box.
Users lacked confidence reviewing automated results.
The challenge: Make AI transparent, controllable, and efficient without reducing automation power.
MY ROLE
Led end-to-end UX/UI strategy focused on AI transparency and workflow efficiency.
• Conducted user research with media analysts
• Designed AI confidence visualization framework
• Unified fragmented workflows into single interface
• Built 80+ reusable component library
• Partnered closely with AI/ML engineers
• Validated solutions through usability and A/B testing
Legacy UI (before)
Dark UI, olive green palette, dense screens, confusing Tagger, inconsistent interactions.
New UI (after)
Clean, bright and modern UI; unified design system; clearer workflows; improved tagging experience; new brand identity.
.png)
THE PROBLEM
User challenges
❌ 85% didn’t understand AI confidence scores
❌ Tagging required switching between 4 screens
❌ High cognitive load reviewing large media libraries
❌ Frequent manual corrections
Business challenges
❌ Low AI trust
❌ Slower adoption
❌ Reduced enterprise confidence
RESEARCH & DISCOVERY
Methods
-
User interviews (media analysts & content managers)
-
200+ support ticket analysis
-
Shadowed tagging sessions
Key Insights
AI Transparency Gap
Users couldn’t predict or verify AI decisions.
Confidence scores lacked meaning.
Workflow Fragmentation
Tagging process split across 4 screens.
Context switching increased errors.
Data Overload
Large libraries overwhelmed users.
No prioritization by confidence level.
Core Insight:
-
Users didn’t want less AI.
-
They wanted AI they could understand and control.
PROCESS & APPROACH
Phase 1 — AI Transparency Framework
Mapped user mental models of trust.
Tested multiple confidence visualization concepts.
Outcome:
3-tier confidence system simplifying review focus.
.png)
Phase 2 — Unified Tagging Interface
Collapsed 4-screen workflow into single interface:
-
Left: Media preview
-
Center: AI suggestions + manual tagging
-
Right: Applied tags + bulk actions
Outcome:
Reduced context switching and improved task flow.
Phase 3 — Data Visualization Optimization
Redesigned dashboards to:
• Prioritize high-risk content
• Surface low-confidence AI tags
• Enable batch review
Outcome:
Faster decision-making at scale.
.png)
KEY DESIGN
DECISIONS
Decision 1 — AI Confidence Visualization
Problem:
Users didn’t trust AI because decisions lacked transparency.
Decision:
3-tier confidence model:
High (85–100%) Auto-applied
Medium (60–84%) Requires review
Low (<60%) Manual tagging
Added “Show reasoning” explanation.
Impact:
• +60% increase in AI trust
• -40% review time
• -55% manual corrections
Decision 2 — Unified Tagging Interface
Problem:
Workflow split across 4 screens created friction.
Decision:
Single interface with contextual panels and batch actions.
Impact:
• Task time: 8 → 4.8 minutes
• -55% tagging errors
• +45% satisfaction
• Lower cognitive load (NASA-TLX)
DESIGN SYSTEM
To support scale and consistency, I built an 80+ component system tailored for AI and data-heavy interfaces.
Includes:
• Data visualization components
• Tagging controls & confidence indicators
• Batch action modules
• Structured design tokens
• Documentation for design & engineering
Impact:
• 50% faster design-to-development
• 80% component reuse across modules
• +40% engineering velocity
.png)
TESTING & VALIDATION
Concept Testing
• 10 sessions validating confidence visualization
• Added reasoning tooltip after feedback
Usability Testing
• 10 beta sessions
• Unified interface reduced errors by 55%
A/B Testing
• 25 users (old vs new workflow)
• 40% faster task completion
• SUS improved from 68 → 85
Continuous validation through analytics and enterprise client feedback.
_edited.jpg)
OUTCOMES & IMPACT
User Metrics
• 40% faster task completion
• 60% usability improvement (SUS 68 → 85)
• 55% fewer tagging errors
• 70% of users rated AI as trustworthy (vs 30% before)
Business Impact
• 10 enterprise clients onboarded in 6 months
• Contributed to $2.5M funding round
• Platform positioned for Series A
• Increased enterprise adoption confidence
Product Impact
• 80+ reusable components
• 50% faster feature delivery
• 40% engineering velocity increase
LEARNINGS & REFLECTION
AI products require trust frameworks, not just automation.
• Transparency increases efficiency.
• Reducing cognitive load drives adoption.
• Workflow unification improves both UX and business metrics.
• Data-heavy interfaces demand strong visual hierarchy.
This project deepened my expertise in AI transparency, complex workflow simplification, and enterprise SaaS design.