The Problem

Many learners want to acquire new skills but struggle to:

• convert inspiration into searchable keywords

• identify what skill they should learn

• navigate overwhelming learning platforms

Traditional search-based discovery assumes users already know what to look for, which often isn’t the case for beginners.

UX Goal

• Make skill discovery intuitive and accessible

• Reduce cognitive load during content exploration

• Support self-directed and personalized learning

• Use AI as a supporting tool, not the focus of the experience

  
  

Key UX Decisions

1. Image-first interaction instead of search

To lower the entry barrier, SkillSnap allows users to upload or capture an image related to something they want to learn (e.g., an object, artwork, or activity).

This approach:

• removes the need for precise keywords

• supports exploratory learning

• aligns with how curiosity often starts visually

2. Guided learning recommendations

Instead of showing long content lists, the app guides users through:

• suggested skill areas related to the image

• curated learning paths and course categories

This helped users move from inspiration = direction without feeling overwhelmed.

3. Conversational and visual UI

To keep the experience lightweight and human:

• the interface was designed to be visual-first

• interactions were broken into small, progressive steps

• optional conversational prompts supported discovery and refinement

This supported different learning styles while keeping cognitive load low.

Impact

• Demonstrated how AI concepts (image recognition, recommendations) can improve UX without dominating it

• Reduced friction in early-stage skill discovery

• Created a beginner-friendly experience for users unsure where to start

  
  

What I Learned

• Users often need help identifying what to learn before how to learn

• Visual cues can be more effective than text-heavy search in early discovery stages

• AI adds value when it simplifies decisions rather than adding complexity