Yuriko Zheng's Portfolio

<-HOME

OVERVIEW

HIGHLIGHTS

AI GENERATION PROCESS

KPI

TAKEAWAYS

Artificial Intelligence (AI)

Generative AI, Advertising, Motion

Gemini: Because learning isn't One Size Fits All

OVERVIEW

This project explores a new creative concept for Google NotebookLM, showing how Gemini can help students turn teacher-provided materials into personalized study tools. By solving one student’s learning challenge, the concept illustrates how adaptable learning can create broader impact across education.

TIMELINE

3 MONTHS

ROLE

UI motion & Strategy/

Research

MY TEAM

Yuriko Zheng

Joyce Ahn

TOOLS

Figma

Gemini

After Effects

Midjourney

TIMELINE

3 MONTHS

MY TEAM

Yuriko Zheng

Joyce Ahn

ROLE

UI motion & Strategy/

Research

TOOLS

Figma

Gemini

After Effects

Midjourney

TIMELINE

3 MONTHS

MY TEAM

Yuriko Zheng

Joyce Ahn

ROLE

UI motion & Strategy/

Research

TOOLS

Figma

Gemini

After Effects

Midjourney

TIMELINE

3 MONTHS

MY TEAM

Yuriko Zheng

Joyce Ahn

ROLE

UI motion & Strategy/

Research

TOOLS

Figma

Gemini

After Effects

Midjourney

HIGHLIGHTS

AI GENERATION PROCESS

Creating Our Characters

Gemini was used to generate the initial static characters. We refined these visuals in Photoshop to create stronger references, which were then used as prompts in Midjourney and Reve to generate motion. Finally, Adobe After Effects was used to bring all elements together and assemble the final animated sequences.

AI GENERATION PROCESS

Conversion, retention, and satisfaction.

Feature Adoption Rate – % of students using NotebookLM’s personalized study tools.
Engagement Time – average time students spend studying with generated materials.
Teacher Adoption – number of teachers uploading and using class materials.

Feature Adoption Rate – % of students using NotebookLM’s personalized study tools.
Engagement Time – average time students spend studying with generated materials.
Teacher Adoption – number of teachers uploading and using class materials.

TAKEAWAYS

Design is not a one way street.

Prompting requires as much intention as design itself.
Clear, detailed prompts produced stronger and more usable results, proving that AI output depends heavily on the thoughtfulness of the input.

A multi-tool workflow sharpened both execution and adaptability.
Working across AI image generation, refinement, and motion design strengthened my ability to connect different tools into one cohesive final outcome.

Storytelling gives technology its emotional impact.
This project reinforced that features alone do not hold attention—narrative, pacing, and visuals are what make an idea resonate.

KPIs

What's Next?

Reimagining NotebookLM’s art direction helped me explore how storytelling and simple visuals can make AI tools feel more approachable for students.

Next, I’d expand the concept to different subjects and learning situations to see how personalized learning could scale across classrooms.

AI should support learning, not replace it—helping students engage with material in ways that work best for them.

Reimagining VRBO’s art direction allowed me to explore a potential visual identity to make VRBO more approachable, and what VRBO can be.

Next, I would test how a more collaborative booking flow affects real results. The goal is to see if this direction improves engagement and overall customer satisfaction.

Reimagining VRBO’s art direction allowed me to explore how visual identity can shift perception — positioning VRBO as not just a booking platform, but a space for shared experiences.

The focus moving forward is iteration: translating visual exploration into functional systems that enhance clarity, reduce friction, and strengthen trust throughout the booking experience.

Thanks for viewing! If you want the whole case study, email me at yuriko_zheng@fitnyc.edu :)