All Projects

AI systems, research methods, and the workflows that connect them.

NHIS Health Inequality Trends

Data Harmonization & Survey Analysis

Manuscript in preparation

Harmonized NHIS survey data across more than two decades, with reproducible SAS pipelines and documented quality checks.

SASComplex Survey DesignHealth InequalitySurvey HarmonizationReproducible Research
Read case study →

Intersectionality & Health Disparities

Analytic Design & Survey Harmonization

Manuscript under review

Survey harmonization and reproducible analysis for intersectional health-disparities research on pooled NHIS data, supporting a manuscript under review.

SASNHISIntersectionalityHealth DisparitiesSurvey HarmonizationComplex Survey Design
Read case study →

Propensity-Score Matching

Causal Inference & Survey Analysis

Restricted-data research

A mentored causal-inference analysis on restricted-access vital-statistics data, run in a secure computing environment, supporting a manuscript in preparation.

Causal InferencePropensity Score MatchingSASRestricted DataReproducible Research
Read case study →

BRAT Research Platform

Product Lead & AI Engineer

Research platform

Built conversational practice, study onboarding, and researcher review tools for a UT Austin parenting study.

Conversational AIPMTO-informedMulti-agent LLMAzurePostgreSQLQualtrics
Read case study →

Research Atlas

Creator & Lead Developer

Public methods platform

Built a research-methods site and citation-verification skill that cross-checks references against scholarly databases.

Research MethodsCitation VerificationAgent SkillsCrossRef / OpenAlexReactTypeScript
Read case study →

AI Advisory Board

Creator & Lead Developer

Public source code

A desktop model council with retrieval, persistent memory, and per-session budgets. Model inference is routed through OpenRouter.

Multi-agent LLMDesktop AppPageIndex RAGOpenRouterPythonFastAPI
Read case study →

VedAI Clinical Psychiatry AI Assistant

AI Researcher (prior work, 2024 to 2025)

Prior work · 2024–2025 · Confidential

Designed reusable LLM instruction and context templates for psychiatric workflows, with a multi-agent human-in-the-loop review layer for sensitive clinical outputs.

LLM SystemsPrompt & Context DesignClinical AIMulti-agent ReviewHuman-in-the-loop
Read case study →