fiNVIDIA

Empowering independent investors with Generative AI.
Screenshot of fiNVIDIA dashboard with a line chart of past and predicted trends, a valuation metrics table, and a pop up AI chat assistant with a conversation about creating a trend chart.
Role
Product Designer
Duration
Mar 2024 – Dec 2024
Team
Neha Choudhary
Mehul Sahni
Jessica Jiao
Anbang Xu
Project Brief
We collaborated with NVIDIA engineers Jessica Jiao and Anbang Xu for our HCI capstone project at UCSC. We designed concepts for an enterprise RAG AI chatbot that helps investors understand public financial data sources.

I conducted generative and evaluative research, deriving insights that led us from problem discovery to final design. I also took the lead on creating paper and digital prototypes for user testing. fiNVIDIA was positively received, with designs added as the next step for the product roadmap.
Context
An opportunity to empower investors.
Many people believe that investing is too complicated or risky – in fact, 48% of Americans don’t own any investment assets. NVIDIA saw the need for finance-focused AI and created an LLM called Scout Bot that breaks down reports into actionable insights.
BUSINESS NEED
AI beyond the chat box.
Scout Bot was an MVP enterprise concept that prioritized functionality over innovation. It only supported text-based input and output. NVIDIA tested the product internally, and employees had requested data visualizations to reduce investment research time.
Objective
Transform the investing experience by designing an intuitive AI experience that empowers investors to make informed, confident decisions.
Primary Research
Defining investors' top needs and goals.
It was critical that we understand how investors use public financial information to make decisions. We spoke to 4 expert investors and 2 beginner investors, discovering that investing priorities differ based on experience level.
Sally, Expert Investor
"I want to quickly analyze what's relevant so I can decide whether to continue investing or not."
Matthew, Beginner Investor
"I want to understand what's important and what these updates mean so I can invest confidently."
Identifying trusted sources.
User research insights from a survey (N=36) indicated that investors trust some sources of information more than others.
✅
Direct sources feel credible.
Earnings conference calls, SEC reports, and news articles that come from the company are viewed as truthful and unscripted.
⚠️
Skeptical about AI.
Investors worried about accuracy, reliability, and predictive ability. Even if they use AI, they double-check answers.
Ideation
Exploring AI use cases with engineers.
We sketched out two ideas for our product. Since dashboards are most common for data visualizations, we decided to prioritize the dashboard and AI chat features in our MVP. With our remaining time and resources we focused on differentiators to help our product stand out from other generative AI chat tools.
A sketch of the multi-source dashboard that has a list of uploaded sources on the left hand side. It also has an "AI insights" chat that spans the top of the page, a "watchlist" of stock tickers on the bottom left, and a "historical trends" chart on the bottom right. There is a chat message bar at the very bottom, like the ones that are present in iMessage and other chat applications.A sketch of the AI-assisted portfolio investment dashboard, showing an AI-generated portfolio score, how the score was calculated, and suggested buy or sell actions for some stock options.
Collaborative design with investors.
We wanted to bring investors into the design process through a participatory workshop. I developed a paper prototype that we tested with 6 peers to validate the concepts and initial user experience.  
We updated the mid-fidelity Figma prototype based on the feedback, focusing on AI discoverability, using plain language to improve understandability, and developing a robust citation feature.
Dashboard with embedded AI.
Chat view with pop-up citations.
Design Decisions
Evaluating & improving the user experience.
We tested key interactions like finding citations, using the AI chat, and visualizing data on the dashboard. Through 9 usability tests, we pinpointed 3 major usability issues that we addressed through design iterations.
Decision 1: Consistent sidebar affordances
6 of 9 participants to struggle with identifying clickable elements. We redesigned the UI with consistent components, added dropdown arrows, and standardized primary and secondary buttons to highlight interactive elements.
Decision 2: Shortening citations for clarity
Although participants easily found the citation pop-up, 5 out of 9 struggled to find and understand the source document link. We refined the design by experimenting with layouts and text length, landing on a shorter preview and descriptive button that prompts users to open a split-screen view.
Decision 3: Guiding investors to the AI chat
There was a 50% misclick rate when looking for the embedded AI chat on our dashboard. We redesigned our flow to emphasize the "Create with AI" feature, added suggested actions in the embedded chat, and included multiple entry points to the AI feature to improve discoverability.
Solution
Your personalized financial AI Assistant.
fiNVIDIA is a multimodal AI tool that combines Generative AI and Retrieval-Augmented Generation (RAG) to transform public financial data into trustworthy, actionable insights.
Visualize trends with AI.
The embedded AI chat helps users visualize past and predicted trends with natural language, so they can identify hidden trends to make strategic decisions.
Synthesize your documents.
Users can upload financial documents and customize their knowledge base. fiNVIDIA will search across sources to answer questions, becoming a personalized expert in the documents that matter most to investors.
Sentence-level sentiment analysis.
Color-coded highlights guide attention towards positive and negative statements in financial documents, so investors can focus on the important points.
Trustworthy AI insights.
To build credibility in AI-generated responses, every answer and visualization links to its original data source. With RAG citations, users see exactly where each answer comes from.
Next Steps
Proposed future work.
User testing with AI functionality
One limitation was the lack of AI interactions. I would conduct usability tests with the interactive MVP to improve the product experience based on customer feedback.
Enterprise-focused testing
We primarily tested with independent investors because of recruiting limitations. I would love to conduct user testing with NVIDIA's Scout Bot for financial earnings questions.
Reflections
Complex documents, clear insights.
Jessica's engineering perspective greatly streamlined our process from ideation to final design hand-off. As a designer, I learned to lead effective collaboration by presenting early concepts, testing ideas with an open mind, and balancing between customer needs and business goals.
We presented our designs to the internal NVIDIA team in January 2025, and the concept was well-received. It fulfilled Anbang's vision, aligned with engineering goals, and served as an ideal next step for Scout Bot once they iron out the LLM's reliability.

Tmpt.me

Back To Home
EmailLinkedIn