An AI-powered tool to help
data analysts detect

critical anomalies
critical anomalies

Filter false-positive alarms and receive real-time alerts for key trends

Read the study to learn how anomalies are filtered and displayed

Read the full study (Password required)

Read the full study (Password required)

Continuous Intelligence

SAP’s self-learning analytics tool, monitoring anomalies in real-time. Currently under development for the beta launch in 2025.

SAP

SAP

SAP

B2B

B2B

B2B

UXR

UXR

UXR

UXD

UXD

UXD

Challenge

Help data analysts quickly identify and evaluate vital anomalies while filtering out false positives

Opportunity

Redesign an AI-powered analytics tool to filter false anomalies and deliver real-time alerts for critical events

Team

UX Designer - Me

UX Designers

UX Researcher

Project Manager/Lead

Development Team (SAP Labs)

Timeline

5 months

Tool

Figma

Microsoft Teams

MIcrosoft Words

JavaScript, HTML, CSS

Task

User interview

Usability test

Wireframe

Prototyping

UI design

Component design

I omitted confidential information on this page to comply with my non-disclosure agreement. All information in this case study is my own and does not necessarily reflect the views of SAP.

I omitted confidential information on this page to comply with my non-disclosure agreement. All information in this case study is my own and does not necessarily reflect the views of SAP.

My personal thoughts and anecdotes will be quoted on the right panel.

My personal thoughts and anecdotes will be quoted on the right panel.

Working with people from different timezones taught me about time-management a lot.

Working with people from different timezones taught me about time-management a lot.

Background

AI-powered tool for data analysts to quickly uncover critical anomalies in large, time-sensitive investigations

AI-powered tool for data analysts to quickly uncover critical anomalies in large, time-sensitive investigations

AI-powered tool for data analysts to quickly uncover critical anomalies in large, time-sensitive investigations

  1. Data analysyst's job is to discover vital anomalies in a short time

  1. But data continuously grows in size, complexity, and velocity.

  1. They face too many notifications, sometimes involving false-positive information.

  1. Tracking all potentially relevant metrics is humanly impossible. Manual exploration is insufficient and may come too late.

  1. Data analysyst's job is to discover vital anomalies in a short time

  1. But data continuously grows in size, complexity, and velocity.

  1. They face too many notifications, sometimes involving false-positive information.

  1. Tracking all potentially relevant metrics is humanly impossible. Manual exploration is insufficient and may come too late.

  1. Data analysyst's job is to discover vital anomalies in a short time

  1. But data continuously grows in size, complexity, and velocity.

  1. They face too many notifications, sometimes involving false-positive information.

  1. Tracking all potentially relevant metrics is humanly impossible. Manual exploration is insufficient and may come too late.

The biggest challenge for us was misleading information; how do we guide users to filter false-positives?

The biggest challenge for us was misleading information; how do we guide users to filter false-positives?

Result

Improved anomaly display

Improved anomaly display

Improved anomaly display

Increased navigation usability

Increased navigation usability

Increased navigation usability

Solution

Simplifying anomaly detection and management

Self-learning cloud service

Use AI to continuously monitor data, filter key anomalies, and quickly display insights on the Overview page

Find anomalies by customizing metrics

Define custom metrics to focus on specific anomalies for precise analysis

See new patterns in a card layout

Identify anomalies and trends in new data that deviate from expectations, displayed as card components

Check high-level info through attribute keywords

Check high-level info through attribute keywords

Display anomaly attributes within labels and highlight deviations in blue for quick identification

Analyze critical patterns with essential details

Easily compare and review pattern deviations in an expanded window

Communicate quicker

Enhance decision-making with the comment feature

Share metrics with colleagues

Easily share your metrics with others and add their metrics to your board

Track and manage key anomalies using flags

Flag anomalies for follow-up on your My Insights page

Users needed a way to filter and navigate easily to differentiate crucial anomalies from false positives.


→ Focused on designing a system to display anomaly alerts clearly and enable users to sort and prioritize them efficiently.

Users needed a way to filter and navigate easily to differentiate crucial anomalies from false positives.


→ Focused on designing a system to display anomaly alerts clearly and enable users to sort and prioritize them efficiently.

Process

Interview & usability testing for an effective design process

Interview & usability testing for an effective design process

Interview & usability testing for an effective design process

Making ‘how might we’ question

Making ‘how might we’ question

Making ‘how might we’ question

“How might we let users become aware of new anomalies, correlations, and micro-trends in online data at the point of detection?”

How finding anomalies matters in business

How finding anomalies matters in business

How finding anomalies matters in business

Quickly discovering anomalies means business profits

Collaborating with developers, PMs, and UX designers/researchers

Collaborating with developers, PMs, and UX designers/researchers

Collaborating with developers, PMs, and UX designers/researchers

With UXDs

Designed low to high-fidelity screens, working on the same file or distributing tasks depending on the scope.

stakeholders

Collaborated to weave their needs.

UXRs

Prepared the research, took notes, and analyzed the interviews.

Devs & PM

With developers & PM: Weekly sync to discuss each week's design process.

Rebuilding navigation and redesigning the platform

Rebuilding navigation and redesigning the platform

Rebuilding navigation and redesigning the platform

Prototyping responsibilities

My key responsibilities were to restructure and prototype the website’s navigation

Customer demo in high-visibility events

My work was used for various customer demos and presentations, including a big event like SAP NOW.

Users needed a way to filter and navigate easily to differentiate crucial anomalies from false positives.

→ Focused on designing a system to display anomaly alerts clearly and enable users to sort and prioritize them efficiently.

Reflection

Iteration is meaningful, but iteration without purpose does not have any meaning

I realized that ‘WHY’ enormously matters in shipping the real project, especially a B2B project requiring specific knowledge. Thinking about the reason for working on each screen has enabled me to be curious and get a profound insight into each screen.

Read the full study (Password required)

Read the full study (Password required)

Experience

UX Visual Designer

SAP

2024.05 — Current

UX Design Co-Op

Motorola Solutions

2024.02 — 2024.05

Design Technologist Intern

SAP

2023.05 — 2024.02

...and more

Get in Touch

I’m happy to collaborate!

Please reach out via LinkedIn.

Education

New York University, Tisch School of the Arts

BFA Interactive Media Arts, Game Design

2018 — 2024

...and Have a great day!
So Yeon Kim @2025
Experience

UX Visual Designer

SAP

2024.05 — Current

UX Design Co-Op

Motorola Solutions

2024.02 — 2024.05

Design Technologist Intern

SAP

2023.05 — 2024.02

...and more

Get in Touch

I’m happy to collaborate!

Please reach out via LinkedIn.

Education

New York University, Tisch School of the Arts

BFA Interactive Media Arts, Game Design

2018 — 2024

...and Have a great day!
So Yeon Kim @2025
So Yeon Kim @2025