ROLE

Product Designer

TIMELINE

2 Days

TEAM

Individual

RESPONSIBILITY

Ideation, Product Design, User Testing

ROLE

Product Designer

TEAM

Individual

TIMELINE

2 Days

RESPONSIBILITY

Ideation, Product Design, User Testing

✶ OVERVIEW

✶ OVERVIEW

Decision Trace is a lightweight Chrome extension that surfaces decision signals directly on top of AI responses. Instead of explaining what the model says, it reveals how much trust a response might deserve.

Decision Trace is a lightweight Chrome extension that surfaces decision signals directly on top of AI responses. Instead of explaining what the model says, it reveals how much trust a response might deserve.

✶ WHY

✶ WHY

I spend a lot of time using AI tools in my everyday life. Over time, I realized that AI answers often sound confident, even when there is uncertainty or real-world risk hidden in the response. Without any clear structure, it is easy to accept these answers as reasonable and move on.

Decision Trace makes those hidden decision signals visible, without getting in the way of how people normally read and think.

I spend a lot of time using AI tools in my everyday life. Over time, I realized that AI answers often sound confident, even when there is uncertainty or real-world risk hidden in the response. Without any clear structure, it is easy to accept these answers as reasonable and move on.

Decision Trace makes those hidden decision signals visible, without getting in the way of how people normally read and think.

✶ IDEA

✶ IDEA

What if AI outputs felt inspectable rather than authoritative?

What if AI outputs felt inspectable rather than authoritative?

Decision Trace introduces a quiet layer that visualizes risk, uncertainty, and evidence gaps at the moment of reading.

Decision Trace introduces a quiet layer that visualizes risk, uncertainty, and evidence gaps at the moment of reading.

✶ WHAT IT DOES

✶ WHAT IT DOES

Decision Trace automatically detects new AI responses and displays

Decision Trace automatically detects new AI responses and displays

  • Task type

  • Risk presence

  • Missing evidence signals

  • Uncertainty markers

  • Task type

  • Risk presence

  • Missing evidence signals

  • Uncertainty markers

Details stay hidden unless the user chooses to inspect further.

Details stay hidden unless the user chooses to inspect further.

✶ AI METHODOLOGY

AI METHODOLOGY

01. Conceptual Logic

01. Conceptual Logic

with ChatGPT

  • Used to structure complex decision scenarios and define the system’s underlying logic.

  • Abstract intuition was translated into explicit reasoning models, forming the conceptual backbone of the project.

  • Used to structure complex decision scenarios and define the system’s underlying logic.

  • Abstract intuition was translated into explicit reasoning models, forming the conceptual backbone of the project.

02. Technical Translation

02. Technical Translation

with Claude

  • Used to translate the defined logic into a working Chrome extension.

  • Enabled rapid prototyping of real interactions, shortening the design-to-code cycle.

  • Used to translate the defined logic into a working Chrome extension.

  • Enabled rapid prototyping of real interactions, shortening the design-to-code cycle.

03. Conceptual Logic

03. Conceptual Logic

with Human-in-the-loop

  • While AI handled syntax and structure, creative decisions stayed human-led.

  • Based on quick user feedback, I adjusted tone, visual balance, and usability to better support real reading.

  • While AI handled syntax and structure, creative decisions stayed human-led.

  • Based on quick user feedback, I adjusted tone, visual balance, and usability to better support real reading.

✶ VISUAL APPROACH

✶ VISUAL APPROACH

Ask a question → AI responds → signals update automatically

Ask a question → AI responds → signals update automatically

Signals are passive indicators, not instructions.

Users can open a Details view to explore a minimal decision tree without breaking reading flow.

Signals are passive indicators, not instructions.

Users can open a Details view to explore a minimal decision tree without breaking reading flow.

KEY FEATURES

KEY FEATURES

Ask and read naturally

Ask and read naturally

The interface is signal-first and text-light. Inspired by system indicators and familiar UI patterns,
the UI stays calm, translucent, and non-intrusive.

The interface is signal-first and text-light. Inspired by system indicators and familiar UI patterns,
the UI stays calm, translucent, and non-intrusive.

Signals update automatically

Signals update automatically

As the response appears, key decision signals are detected in real time, advice, risk, evidence, and uncertainty.

As the response appears, key decision signals are detected in real time, advice, risk, evidence, and uncertainty.

Inspect only if needed

Inspect only if needed

Why Details helps?

Why Details helps?

Details doesn’t explain more. It shows what kind of reasoning is happening.

Details doesn’t explain more. It shows what kind of reasoning is happening.

  • Where advice begins

  • Which real-world risks are involved

  • Whether claims imply evidence

  • Where uncertainty is introduced

This allows users to slow down only when it matters.

This allows users to slow down only when it matters.

Click Details to reveal a minimal decision tree.

See how the response is structured without leaving the reading flow.

Click Details to reveal a minimal decision tree.

See how the response is structured without leaving the reading flow.

✶ ITERATION

ITERATION

Each iteration was tested with 3 users for quick feedback on clarity and reading flow.

Each iteration was tested with 3 users for quick feedback on clarity and reading flow.

Iteration 1

Iteration 1

Buttons invited explicit actions but drew attention away from reading.

Buttons invited explicit actions but drew attention away from reading.

Feedback

Feedback

  • Too verbose

  • Required multiple actions to access deeper tracing

  • Pulled attention away from reading the AI response

  • Felt intrusive rather than supportive

  • Too verbose

  • Required multiple actions to access deeper tracing

  • Pulled attention away from reading the AI response

  • Felt intrusive rather than supportive

Iteration 2

Iteration 2

Simplified to signals only, but lacked a path for deeper inspection.

Simplified to signals only, but lacked a path for deeper inspection.

Feedback

Feedback

  • Lighter and less distracting

  • However, it felt too minimal

  • Without a way to explore further, the signals felt incomplete

  • Overall, the interface felt unfinished

  • Lighter and less distracting

  • However, it felt too minimal

  • Without a way to explore further, the signals felt incomplete

  • Overall, the interface felt unfinished

Final Iteration

Final Iteration

A signal-first, progressive design with scoped detail view that enhances reading without interruption.

A signal-first, progressive design with scoped detail view that enhances reading without interruption.

Key changes

Key changes

  • Removed all action buttons

  • Reduced language to core decision signals

  • Introduced a structured decision tree behind a single “Details” control

  • Enabled scrollable inspection without expanding the panel itself

  • Removed all action buttons

  • Reduced language to core decision signals

  • Introduced a structured decision tree behind a single “Details” control

  • Enabled scrollable inspection without expanding the panel itself

Each iteration removed friction until the interface learned to stay quiet and speak only when the user asked for more.

Each iteration removed friction until the interface learned to stay quiet and speak only when the user asked for more.

✶ USER FLOW

USER FLOW

Ask → AI responds → Signals update → Optional Details inspection

Ask → AI responds → Signals update → Optional Details inspection

The user asks a question in ChatGPT

The user asks a question in ChatGPT

The AI generates a response

The AI generates a response

Decision Trace automatically detects the new response

Decision Trace automatically detects
the new response

A signal map appears, summarizing risk,
uncertainty, and evidence at a glance

A signal map appears, summarizing risk,
uncertainty, and evidence at a glance

If needed, the user opens Details
to inspect the underlying decision structure

If needed, the user opens Details
to inspect the underlying decision structure

The flow is optional, non-blocking, and designed to preserve reading momentum.

The flow is optional, non-blocking, and designed to preserve reading momentum.

TAKEAWAYS

TAKEAWAYS

Keep decision support unobtrusive

Support was most effective when it stayed subtle and did not interrupt reading flow. Visual cues outperformed text-heavy explanations.

Use progressive disclosure to manage complexity

Revealing information in layers helped preserve momentum. It allowed users to access detail without overwhelming them upfront.

Protect user trust through neutrality

Signals must inform rather than persuade. When interfaces feel directive, credibility declines.

✶ NEXT STEPS

NEXT STEPS

Develop a deployable Chrome extension

Move the prototype into a functional extension to test real-world usage.

Expand and refine signal detection

Adapt the system for additional LLM platforms and explore context-aware risk indicators.

© 2026 Euijin Lee

© 2026 Euijin Lee

© 2026 Euijin Lee