Ellie Na l UX Portfolio

The closed-beta test results showed that greater detail in the responses correlated with higher case law relevance and applicability.

I evaluated satisfaction based on 472 responses from 268 users during the closed beta. Specificity was measured by scoring three criteria: time and place, cause and effect, and details. Each criterion was rated out of 5 points, providing a clear assessment of the overall level of specificity.

Optimizing Outcomes

How might we boost the case law

outcome module's effectiveness?

How might we elicit the most detailed

factual statements from the users?

Improving Motivation

Focus Areas in UX

Why does 'Specificity of Details' matter?

Legal situations are often more sensitive than they appear, where small details can affect the outcome

Key Factor

In assault cases, the verdict can change depending on where the person was struck, the force used, and the context. This is why I focus on these critical details, as they play a decisive role in aligning with the most relevant case findings.

Simple assault

(Criminal Law Article 260)

Justified self-defense

(Criminal Law Article 21)

Assault causing bodily injury

(Criminal Law Article 257)

Aggravated assault

(Criminal Law Article 261)

A drunk person bumped into another person’s shoulder on the street, leading to a brief altercation and a small bruise on the arm.

A man walking down the street was approached by someone who made threatening remarks, and the man struck the individual

A person was punched in the face during a street altercation,

causing a broken nose and requiring medical treatment.

A person initiated an unprovoked attack on another individual at an intersection, injuring them in the process.

Assault Severity and Area

Assault Context

The key details vary by case type. Given the differences across the 10 categories, I divided them into 10 subcategories systematically gathering essential factual elements for a total of 100 distinct legal issues.

How I designed the query for an AI-guided recommendation system

1/2

Collected two key statement elements for each subcategory,

focusing on building a query database that’s both tailored and impactful for diverse legal contexts.

Detailed Search Powered by

Sample-Based Learning & AI

Advanced Focus-Search Algorithm

Optimizing Outcomes: Boosting Module Effectiveness

Focused Search Recommendations for Gaining Specialized Insights

Efficient Case Comparison Based on Similarities and Differences

Within a comprehensive collection of highly relevant case precedents, users can utilize specialized keyword search options to gain deeper insights into the specific aspects they seek to explore.

Access key information without reading lengthy case documents by comparing my situation with similar cases. The system highlights relevant details worth exploring, naturally guiding focused searches.

Point 1

Point 2

UX Solution

Improving Motivation: Elicit the most detailed factual statements

Gaining an Objective Sense of Abstract Qualities Through the Sample

Controlling actual writing through

AI-guided recommendations

The sample serves as an objective reference point for abstract qualities like 'detailed explanations' and 'a casual tone,' helping users learn effectively and empowering them to take practical action.

It provides real-time feedback on missing key details, offering writing direction. While sample-based learning lacked control, AI ensures practical specificity by identifying gaps and guiding the writing process.

Point 1

Point 2

A set of five description recommendation items will be constructed by first identifying five basic common items. Among these, two items will be replaced with specific key factors that align with subtypes, ensuring a total of five tailored items in the final set.

Principles of Item Generation by Type
in AI-Guided Recommendation Systems

[ Example of Assault and Battery]

Parties Involved

Witnesses or Evidence

Date, Time, and

Location of

the Incident

Incident Details

Physical Actions

and Injuries

Injuries or Damages

Evidence

Common & Default Items

Detailed & Alternative Items

Battery resulting from intervention in a domestic dispute

General Legal Expression

I was just trying to stop a fight between a couple and the guy suddenly punched me in the stomach

Expression with Natural Language Processing

Confronting the complexities of a personal legal case through natural language processing (NLP)

Approach

The value of case law for individuals is in comparing it to their own situations to find solutions. Since even small details can change the outcome, it’s important to fully capture the complexity of each personal case. To do this,

I encouraged people to express their situation in a way that felt most natural to them, bringing out the key details

Design Iteration

4 Factors Evaluated for Effectiveness

Through Usability Testing

There were two main considerations for each of the 1 and 2 solutions during the decision-making process. Using Figma prototyping tests, I compared the effectiveness of each option with feedback from four users.

In Solution 1

In Solution 2

Dual Mode with Guided Autonomy

Efficient Information Layout

Sample Display Methods

Case Law Structure and Display Order

Dual Mode with Guided Autonomy

Free Writing Mode

Guided Writing Mode

- An issue arose where the options meant for viewing samples were mistakenly perceived as mandatory fields for describing one's situation

- Testing revealed no significant differences in statements between the two modes. Instead of prior legal knowledge or past consultation experience,

the key variable was the understanding and learning of the narrative direction. Based on this, I decided to unify the modes.

I initially created two modes with varying levels of guide intervention based on users' familiarity with the situation and legal knowledge. Experienced users can freely describe their situation, while new users receive step-by-step guidance with key details to help them complete each section.

Sample Display Methods

A - no sample

B - random sample

C - random sample by topic

Word count varies significantly among individuals, with some writing as little as one sentence

While the word count range has narrowed, many still write concisely, and there's a notable difference in specificity

Responses are generally over 80 characters, with higher specificity, as users tend to provide more details when selecting topic their situation

I gathered four testers and asked them to provide responses in sequence (A, B, and C). I observed a noticeable difference in both the quantity and specificity of their answers. As I progressed from A to C, the responses became progressively more detailed and insightful.

Basic Layout Structure for the Results Module

A - CTA on top

B - fragmented placement of elements

C - A clear flow of title-content-CTA

The CTA button showed the lowest engagement because the visual flow led users’ attention downward after encountering the button, causing it to be overlooked.

The fragmented placement of elements such

as the ‘See Original’ button, relevance score creates a disjointed visual hierarchy, disrupting the user’s natural flow of attention.

Placing the title alongside the relevance score ensures clear communication, while the title-content-CTA flow creates the most stable visual hierarchy.

I focused on designing a foundational layout structure for the results module that

guides the most stable visual flow and effectively boosts CTA button click-through rates.

The information lacks a clear hierarchy, presenting all elements at the same level, which makes it challenging for users to quickly scan and grasp the key points.

A - No hierarchy

By reducing the information to two key categories and differentiating visual levels based on importance, users can more quickly grasp the core points.

B - Clear hierarchy

Efficient scanning of key information

Since users will be viewing multiple similar case precedents, it was important to enable them to quickly grasp the key points before reading the full details of each case. Therefore, I focused on the visual hierarchy of the information.

Takeaway

In my efforts to lessen the typing burden while capturing more detailed information with the help of AI guidance and sample inputs, I’ve seen significant improvements in specificity. However, the challenge of typing large volumes of content still persists. Therefore, in the next phase, I would like to explore voice recognition or conversational technology to alleviate this effort

As the only designer, I managed branding to screen layouts, considering both design and tech. Working with developers, I saw how design impacts development and adjusted for technical issues. Balancing team communication and quick fixes, I learned to balance creativity with practicality and realized the importance of teamwork for smooth execution.

A complicated case law search system

for individuals with limited legal knowledge

Where It All Began

Case law is not just a reference but an essential tool for navigating legal challenges. Although access has improved, finding relevant cases remains a challenge for most people due to the vast amount of data and a lack of understanding of legal terms and case types.

Keyword Uncertainty

Result Overload

Criteria Confusion