전통의 '결'을 생성하다
GYEOL
Designing AI that understands human values through reflective interaction.
OVERVIEW
Supported by the Mary Gates Research Scholarship, Gyeol investigates how AI can support meaningful self-reflection rather than simply generating answers—translating qualitative research into a guided system for discovering personal values.
ROLE
R&D Project Manager, AI Developer
TEAM
Art Team (3)
DURATION
8 Weeks
SOFTWARE
ComfyUI • JavaScript • REST API • OpenAI API • Figma
DISCIPLINE
Design Research · UX Research · HCI
RECOGNITION
Mary Gates Research Scholarship
01 / UNDERSTANDING THE CONTEXT
Reflection requires space for people to recognize their own patterns before AI names them.
As conversational AI becomes embedded in everyday life, most systems privilege speed, confidence, and immediate response. Gyeol began from a quieter question: what happens when the goal is not to automate thought, but to help people notice what they value? The project combines qualitative interviews, reflective prompt design, and AI-assisted interpretation to examine how personal meaning can emerge through guided interaction.
PRIMARY RESEARCH QUESTION
“How might AI help people discover their own values without replacing the reflective work of making meaning?”
Research materials, visual experiments, and interpretive systems arranged as an editorial archive.
02 / Research Question
The study focused on agency, trust, and the moment before interpretation becomes advice.
Rather than treating AI as an oracle, Gyeol studies how reflective systems can stay in a supportive role—organizing, summarizing, and revealing patterns while allowing users to remain the authors of meaning.
01 Identify how people describe core values when reflection is prompted through lived experience rather than abstract labels.
02 Understand when AI-generated summaries feel supportive, intrusive, accurate, or overly interpretive.
03 Translate qualitative findings into interaction principles for reflective, transparent, human-centered AI.
Scope Independent undergraduate research, qualitative interviews, prototype exploration, and design synthesis conducted with mentorship at the University of Washington.
Research Process
01 — Secondary Research / Mapping existing conversations around reflective AI, values clarification, and human agency.
02 — Participant Interviews / Semi-structured sessions explored moments when people struggled to articulate what mattered to them.
03 — Thematic Coding / Interview fragments were grouped into behavioral patterns, emotional tensions, and trust conditions.
04 — Design Translation / Findings became prompt structures, transparency cues, and moments where AI deliberately steps back.
05 — Prototype + Iteration / Early flows tested whether summaries felt reflective, transparent, and authored by the user.
A research board becomes evidence: prompts, interview synthesis, and prototype logic are treated as connected research artifacts rather than presentation decoration.
RESEARCH INPUTS
Literature review, interviews, reflective exercises, prototype probes.
OBSERVATIONS
Moments of hesitation, comparison, emotional specificity, and trust breakdowns.
RECURRING THEMES
Agency, accuracy, reflection depth, transparency, and user authorship.
DESIGN IMPLICATIONS
Prompt before summary, show reasoning, preserve ambiguity, invite reinterpretation.
What the Research Revealed
01 Values were easier to articulate through comparison. Participants struggled with direct labels, but deeper meaning emerged when they compared experiences, conflicts, and decisions.
02 Trust depended on traceability. AI summaries felt useful only when users could understand which moments, words, or patterns shaped the interpretation.
03 Reflection deepened when AI paused. The most meaningful moments came when the system asked users to interpret, revise, or reject a generated pattern.
04 A supportive AI must know when not to answer. Gyeol reframes intelligence as facilitation: organizing thought without claiming ownership of meaning.
From qualitative ambiguity to design direction
Participant experiences
Stories, decisions, tensions, and reflective fragments.
Recurring themes
Agency, accuracy, emotional nuance, trust, authorship.
Opportunity areas
Slow the interaction, reveal reasoning, invite reinterpretation.
Design decisions
Guided prompts, transparent summaries, reflection-first flow.
01. Reflection before recommendation
Allow users to explore their own thoughts before AI presents interpretive summaries.
02. Preserve user agency
The system may suggest patterns, but users remain the authors of their own stories.
03. Transparency builds trust
Make visible how an insight was generated and where AI is uncertain.
04. Meaning emerges through conversation
Design reflection as a process of noticing, revising, and returning—not a single answer.
Translating Research into Design
The final direction is a guided reflection experience: users respond to structured prompts, AI identifies recurring themes, and the interface asks users to interpret those patterns before accepting them. The design differs from conventional AI tools by treating summary as a continuation of reflection rather than a conclusion.
Prototype and research artifacts shown as an annotated design archive, connecting final interaction choices back to the evidence that shaped them.
Research Insight → Users needed time to form their own interpretation.
Design Response → AI summaries appear after reflection prompts, not before.
Why It Matters → The system supports agency instead of steering users toward premature conclusions.
Research Insight → Accuracy mattered less than feeling faithfully represented.
Design Response → Each generated theme is paired with the user’s own words and a prompt to revise or reject it.
Why It Matters → Trust is built through traceability and control.
Research Insight → Values emerged through patterns across experiences.
Design Response → The prototype visualizes recurring themes as relationships instead of isolated labels.
Why It Matters → Users can see meaning as evolving, connected, and open to interpretation.
Testing and Iteration
Prototype testing focused on what did not work: moments where AI felt too definitive, summaries that over-interpreted, and prompts that made reflection feel evaluative. Iterations softened the system’s voice, added explanation before interpretation, and introduced explicit moments for users to correct the AI.
Supported by the Mary Gates Research Scholarship
The project received competitive undergraduate research funding from the University of Washington, validating its rigor as an independently led research initiative. Deliverables included interview synthesis, interaction principles, prototype flows, and a research-backed design framework for reflective AI.
NEXT STEPS
What Gyeol Changed in My Practice
REFLECTION
“The future of AI isn’t defined by how many questions it can answer. It’s defined by how thoughtfully it helps people answer their own.”
Gyeol changed how I understand the ethical role of design in human–AI interaction. I entered the project thinking about AI as a tool for efficiency; I left more interested in systems that ask better questions, slow down interpretation, and protect the user’s right to define meaning for themselves.
NEXT PROJECT