TECHNICAL CASE STUDIES

Context-aware data-governance service at IBM (HashiCorp). Applies policy decisions using business and service context, instead of static field-only matching, across distributed production pipelines, with ML classification of sensitive data on AWS Bedrock and an auditable draft → review → publish → revoke lifecycle. The control layer that determines what data is safe for downstream AI and analytics systems to use.

Proprietary work: no public repository or write-up.

Modernized high-throughput data pipeline at Moody's Analytics using PySpark and Databricks, reducing processing time by 54% while handling larger datasets. This is the data-velocity foundation that downstream analytics and AI workloads depend on.

Proprietary work: no public repository or write-up.

Built a sanctions screening product at Moody's Analytics that generated $1.2M in first-year revenue. Automated compliance checks across financial transaction datasets with SQL, PostgreSQL, and the data architecture behind them, at a 99.7% EU privacy compliance rate.

Proprietary work: no public repository or write-up. Public references are linked.

Developed LangChain-powered RAG citation system at Moody's Analytics using GPT-4 Turbo, achieving 92% citation accuracy. Solved the hallucination problem with page-level source verification: LLM evaluation and grounding work, before it had a job title.

Proprietary work: no public repository or write-up. Public references are linked.

A Wayback Machine archiver that keeps retrying while the Internet Archive is busy, until your pages are actually preserved.

Natural-language query system over 60,000+ anime titles: PostgreSQL, a local ReAct SQL agent, and a Streamlit frontend. CMU capstone, presented at Anime Boston 2026.

ETL pipeline that turns Twitter/X export files into a searchable dataset with NLP sentiment and topic classification, built for longitudinal self-analysis.

Interactive case study mining a decade of personal social media data (26,720 Twitter likes, 4,500 saved YouTube videos, 500+ LinkedIn connections) to reveal what the algorithm sees. CMU data mining final project, published as a scrollytelling site.

17-agent AI system for personal life management, built in Craft on Claude MCP. Each agent owns one life domain: triage, career, finance, events.

A porting practice: adopting cute Windows-only desktop apps and giving them a second life on native macOS. Two Chiikawa pets so far, with prominent credit to the original developers and fixes offered back upstream, including an open PR for Mac support.

Maker studio producing laser-cut items, sublimation prints, acrylic charms, and button sets, with automated design-to-production workflows. Commissions open for conventions, events, nonprofits, and artist collabs. Charity donations (GDQ, Frost Fatales) stay at the core.

Substack newsletter on AI tools and data systems for practitioners: the intersection of technical work with everyday life.

Citation-first RAG Discord bot for Uma Musume game mechanics, answering with page-level source attribution from a 200+ page community reference doc.