Conducting an in-person user study examining how novice and expert users interact with LLMs when debugging NL2SQL queries, with the goal of informing more effective human-AI collaboration in data-driven tasks.

KathDB is an explainable multimodal DBMS that combines relational query optimization with foundation model reasoning, enabling natural language queries over text, images, and video while preserving structured semantics. My work focuses on the human-AI interaction layer, exploring how users query, debug, and interpret multimodal results, and how the system can best surface explanations and lineage to support understanding and trust.

Created an interactive dataset visualization tool with R to enable environmental justice community groups to explore air quality concerns in their community and create a story.

Attempting to provide probabilistic forescasts of sea levels using Gaussian Process, Neural Networks, and different variations of these models.

Exploratory survey and participatory design workshops aimed at gathering insights of Black and Latinx students' perspectives of campus services accessibility.

Aims to reduce impostor syndrome in underrepresented students through strengthening data structure skills with an agumented reality application.