Back to work

MEL · CONVERSATIONAL AI

mel

Designing the path from a first chat to deeper use.

We first suspected short sessions were an AI-quality problem. User journeys showed something else: the capability already existed, but people could not see what to try next. I brought relevant modes into the conversation and reduced complex choices into clearer starting points.

Role
Product Designer
Scope
UX/UI · Interaction · Design System
Duration
2024–2025
Platforms
iOS · Android · Web

LISTENINGTHINKINGSPEAKING

02PRODUCT OVERVIEW

A LIVE AI CHAT EXPERIENCE

Conversation, character, and space respond as one experience.

MEL is a real-time AI character experience. People can talk by text or voice, create their own character, and enter visually generated contexts that make the relationship feel more present.

  • REAL-TIME CHAT
  • VOICE
  • CHARACTER CREATION
  • GENERATED CONTEXTS
MEDIA 01MEL product overview videoReplace with product overview MP4 · 16:9

03PRODUCT INSIGHT

WHAT THE JOURNEY REVEALED

Users did not need more features. They needed a path to the next one.

The issue was not AI quality alone. Advanced modes stayed invisible until the interface introduced the next useful possibility at the moment it became relevant.

CAPABILITYDISCOVERYCONTINUITY

04CHALLENGE 01 · VOICE CONVERSATION UX

TURN-TAKING CLARITY

Voice made the AI feel alive. State clarity made it usable.

A live exchange can become ambiguous quickly. The interface had to make speaking, listening, waiting, and response timing legible without interrupting the conversation.

  1. 01
    Problem

    Voice, text, and visual response competed for attention.

  2. 02
    Principle

    One dominant state at a time; transition before decoration.

  3. 03
    Outcome

    Speaking, listening, waiting, and responding became distinct states.

05CHALLENGE 02 · CREATE YOUR OWN MEL

RELATIONSHIP ONBOARDING

Creation needed freedom, but also a place to begin.

Character creation was not merely avatar setup. It was the first emotional commitment to a relationship. I grouped the choices into clearer starting routes, preserving expression without presenting an infinite wall of options.

  1. 01
    Problem

    Too much freedom created hesitation before creation began.

  2. 02
    Principle

    Simplify the first choice; reveal expression progressively.

  3. 03
    Outcome

    A clearer route from intention to character to conversation.

MEDIA 03Custom Mel creation journey3–5 key screens on transparent canvas · 3:2

06CHALLENGE 03 · GENERATIVE DATE SCENE WORKFLOW

DESIGN × ML COLLABORATION

Generated visuals had to feel usable, not merely possible.

In late 2023 and early 2024, consistent people and backgrounds were difficult to generate. I worked with the ML team through a ComfyUI-based workflow, iterating on mood, composition, continuity, and scenario clarity until date scenes could support the product experience.

  1. 01
    Brief

    Mood, relationship context, place, and product constraints.

  2. 02
    Generate

    ComfyUI workflow with repeatable inputs and controls.

  3. 03
    Refine

    Character consistency, composition, artifacts, and legibility.

  4. 04
    Ship

    Date and place imagery selected for real product scenarios.

MEDIA 04AComfyUI workflowSimplified node pipeline · 16:9
MEDIA 04BDate / place output gallery4–6 generated scene references · 16:9

07SYSTEM & COLLABORATION

ONE INTERACTION LANGUAGE

Give multiple modes one shared interaction language.

Voice, text, creation, and visual states needed to feel like one product across iOS, Android, and Web. Shared state patterns and naming reduced reinterpretation during design and engineering handoff.

  1. 01
    Before

    Modes and platforms expressed the same states differently.

  2. 02
    System

    Shared states, component structure, naming, and behavior rules.

  3. 03
    Effect

    Clearer handoff and a more extensible multi-platform product.

MEDIA 05Cross-platform design systemComponents · states · iOS / Android / Web · 4:3

08IMPACT & REFLECTION

REPORTED BETA SIGNALS

Capability became meaningful when people could enter, understand, and continue.

7 → ≈30min

Reported average chat duration

−6%

Reported onboarding-exit change

≈1,000

Beta participants

Values are retained from the original beta materials. Where the exact definition or experimental method is incomplete, they are presented as reported directional signals—not causal proof.

Emerging AI products do not become meaningful through capability alone. They become meaningful when users can enter, understand, and continue the experience.
What this experience opened next

From guidance to sensory feedback

After reducing hesitation in an AI creation flow, I explored a different question: can immediate sound, motion, and haptics make interaction itself worth repeating?

Next project · 03 / 04KKuukTactile interaction · Haptics · 2026