See Museum (SeeM)
Online Museum Platform (Internship Project)
SeeM is a web-based museum platform that explores how AI can support art learning and discovery through clearer navigation and reduced cognitive load.
My Role Snapshot
UIUX Designer Intern @ SeeM
Timeline
05/2024 – 09/2024
Team
3 UIUX Designers · 1 Product Manager · 5 Engineers
Scope & Responsibilities
Improved navigation clarity and content understanding by owning interaction design for key exploration flows and leading iterative usability testing.
-
Designed the AI-guided exhibition and exploration flow in Figma
-
Led 2 rounds of usability testing with 58 participants, synthesizing findings into prioritized changes
-
Collaborated with the PM and engineers to refine IA, page structure, and interaction details within technical constraints
Design Context & Early Signals
Access to museum education is often limited by location, cost, and institutional constraints, reducing opportunities for consistent art exploration.
Early research combined stakeholder input, secondary research, and designer-led exploratory research.
As a designer, I participated in synthesizing these signals to frame initial design priorities.
Key Signals That Shaped Design Decisions:
-
84% of museum visitors reported dissatisfaction with current museum experiences, indicating gaps in engagement and discovery.
-
Attendance at local and university museums declined by 66%, highlighting a need for remote and flexible access.
-
Educational institutions reported over 3× demand for museum-based learning experiences.
-
Museums face an average of $400K in annual operational losses, reinforcing the need for scalable digital experiences.
These signals pointed to one core challenge: how to support meaningful exploration without overwhelming users with information.
Problem Framing & Design Constraints
Context:
Access to museum education is often limited by physical location, cost, and institutional constraints, reducing opportunities for consistent art exploration.
Design Goal:
Design a web-based exhibition experience that supports art exploration through clearer navigation and reduced cognitive load.
Key Constraints:
-
Managing complex AI-generated content and recommendations
-
Supporting users with varied art knowledge and learning needs
-
Designing within a limited development timeline
Insights from early research synthesis were used to inform navigation structure and feature prioritization.
Design Strategy: Progressive Exploration Across Key Features
Instead of treating AI features as isolated tools, I applied a single interaction strategy across the platform: progressively revealing content based on user intent and depth of exploration.
This strategy shaped how each feature behaves:
Personalized Discovery
Personalized Discovery
Surfaces a limited set of relevant artworks based on user interests, reducing early choice overload.
AI-assisted Curation
AI-assisted Curation
Generates exhibitions step by step based on user-selected parameters, allowing gradual refinement rather than instant output.
Structured Browsing
 |  |  |
|---|---|---|
 |
Structured Browsing
Offers multiple entry points while controlling information density to support exploration without overwhelming users.
Contextual AI Guidance
Progressive Exploration Model (Core Interaction Pattern)
This model operationalizes the design strategy by revealing information gradually based on how users interact with the artwork.
Core Design Decision: Progressive disclosure to balance immersion and understanding.
Stage 1: Distant Shot
Provides an overview of the exhibition to help users orient themselves before engaging with individual artworks.
Stage 2: Mid Shot
Introduces essential context while preserving the overall composition, preventing early cognitive overload.
Stage 3: Close Shot
Allows closer inspection of artworks while maintaining spatial context across the exhibition.
Stage 4: Super Close Shot
Supports focused exploration of specific details. Contextual AI prompts appear only when a deeper understanding is needed.
AI as Supporting Layer
-
AI Guidance appears only when users pause or zoom
-
Questions are suggested based on the viewed region
-
AI does not interrupt the primary exploration flow
This approach keeps visual immersion intact while still supporting learning and curiosity.
Supporting Collection Behaviors
Different saving behaviors reflect different user intentions
Separate flows were designed for saving exhibitions and saving individual artworks, allowing users to revisit content based on learning goals rather than treating all saved items the same.
SeeMuseums
See Your Own AI Generated Online Museum
SeeM is not a concept about AI features, but an exploration of how interaction design can guide attention, pacing, and understanding in complex content environments.
This project reflects my approach to designing AI-assisted experiences with clarity, restraint, and user intent in mind.
