Data Storytelling Assistant with Gemini for Slides

Led UX design and conducted user research to a develop a tool for students and young professionals to tell better data stories.

Project Details

Company: Google (Industry Sponsor) | Team: 1 UX Researcher + 1 UX Designers + 1 UX Designer/Researcher, Industry Advisor, Academic Advisor

Role: UX Design Lead, Developer and Researcher | Timeline: Aug 2025 - Present

Tools: Figma, Qualtrics, Google AI Studio, Apps Script, Google Slides

The project is still in progress. While the design of the tool is done, research is still ongoing.

The Challenge

How can AI assist students in their data storytelling?

Most times, students are not taught how to make their presentations and tell their data stories effectively through their courses. They go off of information they have gathered over time and spend quite a bit of time in figuring out how to structure their outline.

Our work, therefore, aims to find out if AI and in particular, Gemini can have an effect on students' slide creation processes to tell a better data story.

Does AI have an effect on student’s slide creation processes during slide deck creation?

Therefore, we designed a tool, currently an Apps Script extension that can be integrated with Google Slides and uses the power of Gemini to assist students with better data storytelling.Through our work, we aimed to answer the following Research Question:

The Value I Delivered

I led the design & development of the tool while simultaneously acting as the bridge between the research and design processes.

In progress

The Solution

The tool gives tailored recommendations to build a narrative structural outline and recommend charts to improve data storytelling.

Contact me to view the solution

The Deep Dive

Here’s how I hatched the solution

Framing the Challenge

AI needs to assist students not directly replace their critical thinking abilities when it comes to data visualization.

This was the most intense part of the process. Targeting the right research direction was crucial to our project as we wanted to establish the role AI played in our project. From having informal discussions with students, teachers and even working professionals at Google to conducting intense literature reviews, we shifted our initial decision of helping students' critical thinking to providing students with an assistant leaving the critical thinking to what humans are the best at.

Therefore, our tool now lets our users be the ones taking the decisions but use the AI tool as a means to reach the decision.

Detailing out the research direction allowed us to think of the constraints we wanted our tool to have in order to maintain the autonomy with the user.

Keep an eye out for more details coming up soon!

Designing the Solution

Set constraints and remember what you are trying to build.

Framing the research question was crucial to this project. Once we had the details of the research, us 2 designers sat together to brainstorm various ways to manifest the outlined requirements. Constant back-and-forths of what worked and what did not allowed us to come up with a final set of prototypes, especially when tying it back to what we wanted our tool to do vs not.

We also sought feedback from Subject Matter Experts in the field. I then translated the feedback into new concepts which I prototyped on Figma.

At the same time, I also defined the tool's branding and helped define its design system. One that closely matched Google's design language but had its own twist.

Building the tool with AI

Being actively involved in framing the research question, I led the design of the extension whilst also solely developing the same.

In order to "vibe code" the tool, I suggested and strongly insisted on the need for a "Prompt" Requirements Document (as opposed to your regular Product Requirements Document). Contributing to its creation, I helped put together parts of the PRD alongside the UX Researcher on the team.

I then set out to build the tool using Google AI Studio to build an extension on Apps Script using Gemini's API.

PRD

The process

Wireframes

Google AI

Studio + Gemini

Apps Script

extension

While this was quite a process, spending some sleepless nights the result was satisfying. Sometimes, the code breaks but that is when I understood the importance of also knowing the programming language constructs yourself as the "vibe coder" to go in and make those little tweaks.

PRD

The process

Wireframes

Google AI

Studio + Gemini

Apps Script

extension

User Research

Ongoing and due to research restrictions, this process cannot be detailed out here.

Do students really find this useful?

We are currently testing out our tool. Most of the user research for this case study lies in the usability and user testing which is ongoing. Keep an eye out for updates on this page!

Reflection

This project taught me a lot about adding constraints and molding your research into something specific and actionable. We need to take things at a time and need to consider the reality.