MAL
MAL
Company
Company
LG Electronics
LG Electronics
Duration
Duration
AUGUST 2023 - JULY 2024
AUGUST 2023 - JULY 2024
Cutting revision cycles by 50% with an AI SaaS verification tool, enabling faster and accurate global workflow.
Cutting revision cycles by 50% with an AI SaaS verification tool, enabling faster and accurate global workflow.
Overview
Overview
LG’s global teams create thousands of contents each year across appliances, apps, and digital products. Before it goes live, it must be verified for accuracy, grammar error, consistency, and brand tone — a process that inconsistent, and heavily manual. I designed MAL (Machine-Assisted Language), an internal AI-driven verification platform, to make that process scalable. But this wasn’t just a design problem — it was an organizational challenge. I had to navigate legacy workflows, pushback from global teams resistant to change, and massive data audit. My role was to create the systems — tone, rules, and workflows — that AI could thrive in, while winning trust from stakeholders across the company.
LG’s global teams create thousands of contents each year across appliances, apps, and digital products. Before it goes live, it must be verified for accuracy, grammar error, consistency, and brand tone — a process that inconsistent, and heavily manual. I designed MAL (Machine-Assisted Language), an internal AI-driven verification platform, to make that process scalable. But this wasn’t just a design problem — it was an organizational challenge. I had to navigate legacy workflows, pushback from global teams resistant to change, and massive data audit. My role was to create the systems — tone, rules, and workflows — that AI could thrive in, while winning trust from stakeholders across the company.
Role
Role
Product Designer
Product Designer
Platform
Platform
Internal SaaS tool
Internal SaaS tool
Scope
Scope
Product Design, AI Platform Design, Stakeholder Alignment, Content, UX Writing
Product Design, AI Platform Design, Stakeholder Alignment, Content, UX Writing
Team
Team
Product Manager, UX Writer, 3 Engineers, Technical Writers
Product Manager, UX Writer, 3 Engineers, Technical Writers
Starting in the Unknown
Starting in the Unknown
Significant inefficiency due to tangled workflow and inconsistencies across legacy contents.
Significant inefficiency due to tangled workflow and inconsistencies across legacy contents.
LG’s global product, both physical and digital teams were dealing with an enormous challenge: - Thousands of UX writing assets produced annually, across different product lines. - No consistent verification process — each division had its own way of checking content. - Legacy files full of inconsistencies, making automation nearly impossible. The result: verification took weeks, slowed down product launches, and created friction across teams.
LG’s global product, both physical and digital teams were dealing with an enormous challenge: - Thousands of UX writing assets produced annually, across different product lines. - No consistent verification process — each division had its own way of checking content. - Legacy files full of inconsistencies, making automation nearly impossible. The result: verification took weeks, slowed down product launches, and created friction across teams.
Why This Project Mattered
Why This Project Mattered
We needed a way to verify massive amounts of content efficiently.
We needed a way to verify massive amounts of content efficiently.
My first assumption was that the problem was primarily a tooling gap.
My First Hypothesis
My First Hypothesis
My first assumption was that the problem was primarily a tooling gap.
My first assumption was that the problem was primarily a tooling gap.
I though, if we could automate verification using AI, teams would naturally adopt the new system. I mean, on paper, it sounded pretty straightforward: Step 1. Train AI on existing content. Step 2. Automate verification checks. Step 3. Save teams time and reduce errors. So simple. No?
I though, if we could automate verification using AI, teams would naturally adopt the new system. I mean, on paper, it sounded pretty straightforward: Step 1. Train AI on existing content. Step 2. Automate verification checks. Step 3. Save teams time and reduce errors. So simple. No?
But...we got stuck.
But...we got stuck.
As I dug deeper, it became clear that the problem wasn't just technical. It was cultural and organizational.
As I dug deeper, it became clear that the problem wasn't just technical. It was cultural and organizational.
This wasn’t just a design problem — it was a product–market fit problem inside the organization. Before we could train AI, we had to fix the system it lived in one by one.
This wasn’t just a design problem — it was a product–market fit problem inside the organization. Before we could train AI, we had to fix the system it lived in one by one.
Rethinking the Approach
Rethinking the Approach
Through audits, and stakeholder interviews, I realized before we even get to the AI part, we need to start with language and building consistency.
Through audits, and stakeholder interviews, I realized before we even get to the AI part, we need to start with language and building consistency.
We had to first: Establish a unified brand tone and style guide across teams. Design scalable verification rules for AI to check against. Create a user flow that respected how teams actually worked, while nudging them toward the new system.
We had to first: Establish a unified brand tone and style guide across teams. Design scalable verification rules for AI to check against. Create a user flow that respected how teams actually worked, while nudging them toward the new system.
Designing MAL
Designing MAL
The team made a decision to design MAL as a web app rather than a standalone tool. This was driven by two constraints:
The team made a decision to design MAL as a web app rather than a standalone tool. This was driven by two constraints:
1. Security Constraints: All data needed to remain within the LG cloud ecosystem. 2. Adoption Concerns: Requiring a separate login & app download would create friction and resistance. By embedding MAL within existing systems, we minimized the sense of “one more thing to manage” and kept workflows seamless.
1. Security Constraints: All data needed to remain within the LG cloud ecosystem. 2. Adoption Concerns: Requiring a separate login & app download would create friction and resistance. By embedding MAL within existing systems, we minimized the sense of “one more thing to manage” and kept workflows seamless.
With the contraints in mind, I started to ideate and build MAL around these three design pillars:
With the contraints in mind, I started to ideate and build MAL around these three design pillars:
1. Systems Thinking 2. Seamless AI Integration 3. Non-Disruptive Design
1. Systems Thinking 2. Seamless AI Integration 3. Non-Disruptive Design
Solutions
Solutions
Systems Thinking: Building from Ground Up
Systems Thinking: Building from Ground Up
I collaborated with UX writers and global stakeholders to create a universal brand guideline that respected each division’s restrictions while unifying core standards. I focused on capturing brand rules, grammar hierarchies, and division-specific requirements.
I collaborated with UX writers and global stakeholders to create a universal brand guideline that respected each division’s restrictions while unifying core standards. I focused on capturing brand rules, grammar hierarchies, and division-specific requirements.
Seamless AI Integration: Training for Trust
Seamless AI Integration: Training for Trust
Once we had a consistent dataset, I partnered with engineers to separate the database into two parts: 1. Label Data (the content being verified) 2. Rule Data (the standards it must meet) This structure allowed us to train AI models that could search, verify, and cross-check brand guidelines across divisions. (image above) Then I moved on to actual platform design. I designed the outputs to be explainable: each revision was flagged with a clear before/after indication, so users understood why something was flagged and why it needed correction. This transparency was critical in building trust with skeptical teams.
Once we had a consistent dataset, I partnered with engineers to separate the database into two parts: 1. Label Data (the content being verified) 2. Rule Data (the standards it must meet) This structure allowed us to train AI models that could search, verify, and cross-check brand guidelines across divisions. (image above) Then I moved on to actual platform design. I designed the outputs to be explainable: each revision was flagged with a clear before/after indication, so users understood why something was flagged and why it needed correction. This transparency was critical in building trust with skeptical teams.
Non-Disruptive Design: Meeting Users Where They Are
Non-Disruptive Design: Meeting Users Where They Are
From my earliest interviews, one theme was loud and clear: “We don’t have time to learn another tool.” This resistance shaped my design philosophy. Instead of introducing a complex interface, I deliberately designed MAL to feel familiar and frictionless. The UI mimics a simple search engine — one box, one primary action. Users could toggle between three options (verify sentence, Excel, or HTML). By keeping the experience minimal, adoption felt almost effortless.
From my earliest interviews, one theme was loud and clear: “We don’t have time to learn another tool.” This resistance shaped my design philosophy. Instead of introducing a complex interface, I deliberately designed MAL to feel familiar and frictionless. The UI mimics a simple search engine — one box, one primary action. Users could toggle between three options (verify sentence, Excel, or HTML). By keeping the experience minimal, adoption felt almost effortless.
Result: What Changed
Result: What Changed
The first version of MAL rolled out across select LG teams — and the results spoke for themselves:
The first version of MAL rolled out across select LG teams — and the results spoke for themselves:
But the biggest effect wasn’t just efficiency. It was laying the foundation for AI to scale responsibly across LG. MAL created the structure — tone, rules, workflows — that made future automation possible.
Reflection
Reflection
Enterprise design isn’t just about interfaces — it’s about building systems that align people, process, and technology at scale.
Enterprise design isn’t just about interfaces — it’s about building systems that align people, process, and technology at scale.
This project taught me that designing at enterprise scale is as much about people as it is about tools. I learned how to navigate global workflows, balancing complexity with simplicity so the system was powerful enough to scale yet easy for teams to adopt. I saw firsthand how alignment requires patience and clear communication, especially when priorities conflict across functions and time zones. And I came to appreciate the trade-offs of AI in practice — it could accelerate reviews, but cultural nuance still demanded human judgment. In the end, the real design challenge wasn’t just building a tool, but building trust in the system around it.
This project taught me that designing at enterprise scale is as much about people as it is about tools. I learned how to navigate global workflows, balancing complexity with simplicity so the system was powerful enough to scale yet easy for teams to adopt. I saw firsthand how alignment requires patience and clear communication, especially when priorities conflict across functions and time zones. And I came to appreciate the trade-offs of AI in practice — it could accelerate reviews, but cultural nuance still demanded human judgment. In the end, the real design challenge wasn’t just building a tool, but building trust in the system around it.
PORTFOLIO
CHECK OUT SOME MORE
CHECK OUT SOME MORE
CHECK OUT SOME MORE
CHECK OUT SOME MORE
NEARVILLE
NEARVILLE
NEARVILLE
description
NEARVILLE
NEARVILLE
NEARVILLE
description
NEARVILLE
NEARVILLE
NEARVILLE
description
NEARVILLE
NEARVILLE
NEARVILLE
description
CHRONICLE
CHRONICLE
CHRONICLE
description
CHRONICLE
CHRONICLE
CHRONICLE
description
CHRONICLE
CHRONICLE
CHRONICLE
description
CHRONICLE
CHRONICLE
CHRONICLE
description