Yaw AI

PRODUCT MANAGEMENT

CROSS-TEAM LEADERSHIP

UI/UX DESIGN

Yaw AI app mockup with avatar standing next to phone

What is Yaw AI?

It was an AI chatting app that brought group conversations to life through 3D avatars and distinct AI characters.

Over two years, I grew from design intern to Design Lead — hiring and managing a team of 8 artists and animators, owning all UI/UX work, and serving as the primary bridge between teams across two full product pivots.

As Design Lead, I was handed one of those pivots directly: take an existing social avatar app and redesign the entire product experience around a new AI chatting vision — fast and with limited resources.

01

App screenshots of previous version

A New Direction?

Previously, our app was meant to be a social space where friends could keep up with each other, play games together, and build relationships through their avatars. However, with the emerging AI market, the founders and their investors wanted to change directions and capitalize on this new trend.

They tasked me with leading the product and design transition — aligning the design team, coordinating with engineering, and ensuring every change was buildable within our timeline.

02

My Constraints

This new version was going to require a lot of work, so I had a few constraints to follow to make sure it all came together well:

  1. Keep the 3D avatars: The founders wanted to keep them to continue exploring a new medium for AI chats.
  2. Be as efficient as possible: I had to take developmental time into account for every single change I considered.
  3. Minimize design workload: The design team needed enough space to fully flesh out the 3D chat experience.

03

The 3D Chatrooms

I proposed recycling and retexturing existing props from the previous status animations to hit our timeline without sacrificing quality.

A fully 3D chat meant a new environment was necessary. We aimed for two, but we were successful in creating three distinct rooms. We expedited the process, which meant more time for the development team to test their chat's functionality.

Animated winter scene Animated underwater scene Animated school hallway scene

04

Meet the New AI Characters

I led the marketing test strategy that determined our character direction.

We found the most appeal was with characters that were colorful, distinct, and somewhat futuristic. This presented more opportunities for advertising and managing consistent themes in the app. We built characters based on unique personas to best show this off, and we began to build the app around this concept. We had seven characters designed, with five being deployed in the app. These are some of the ones available:

Animated futuristic boy Animated girl in hoodie Animated boy in front of fire

05

App screenshots of AI chat

Improving Onboarding

I identified the drop-off pattern and designed the solution end-to-end.

Many users were falling short of completing every milestone event during onboarding. Most users did not grasp the concept of adding both AI and real friends into the chat. I came up with the concept of a mixed tutorial and early chatting experience. AI characters would chat with the user, add others automatically, and suggest inviting friends in a way that clearly showed the user how the rooms worked.

We saw improvements in milestone-count, and user retention and acquisition also benefitted from the changes.

06

Mockup graphic of chat

Improving the Chat

I proposed the use-case specialization strategy after analyzing retention patterns across characters.

Many users were not exploring the other AI characters; different personalities were not interesting enough to switch. I suggested the idea of tying characters to use-cases that matched their personalities. Not only would users chat with more variety, but it would also help us further stand out from other AI chatting apps.

We saw really great success with our language-tutor and pop-culture characters. User retention improved and two other characters were finally getting involved.

07

Avatar in outfit and two avatar heads showing emotions

Improving App Performance

I identified the performance bottleneck and proposed a solution that served all teams simultaneously.

With a bulk of our users on Android, we faced many issues with lower-level devices, particularly frame rate and power consumption in the chatrooms. I recommended we move away from full avatar customization towards outfits. We could create higher quality clothing, minimize load, and save space all at once.

With more efficient and better designs, our marketing was more cohesive, our app expanded to an even wider audience, and the quality of the chat was improved. We created 50+ outfits to change customization.

08

Marketing image of Yaw characters

The New Yaw

Changing Yaw from a casual social app to a fully realized AI chatting experience required tight coordination across design, engineering, and marketing, all under significant time pressure. By managing the design team's workload carefully and making deliberate tradeoffs at every stage, we shipped a complete product overhaul across multiple update cycles.

The results spoke for themselves: 200K+ downloads and a +26% improvement in two-week retention within three months of the relaunch.

09

Tools & Skills Used

For Design: Figma, Blender, Adobe Photoshop, Adobe Illustrator

For Product Management: Notion, Firebase, Jira, Loom

Skills Involved: Product Management, UI/UX Design, Project Planning, Cross-Team Collaboration, Problem Solving, Data Analysis, Wireframing