Who I am

I'm a Cloud Engineer at CVS Health, where I work on GCP-based data systems, pipelines, and infrastructure. I lead development on an AI Model Inventory — an enterprise platform that ingests every AI model in the organization, runs automated compliance checks against our team's AI standards, and gives management the visibility they need to govern AI at scale. The platform handles ~50 new models per month across multiple business domains.

Before CVS, I spent five years at Infosys as a Lead Technical Analyst doing data engineering work that eventually migrated almost entirely onto Google Cloud. I led a multi-year on-premise to GCP data migration for a major healthcare client — building Airflow DAGs in Cloud Composer, developing BigQuery query patterns, and putting data quality rules in place that made ingested data actually trustworthy.

I studied Computer Science at Ball State University and went back for a Master's in Data Science — not for the credential, but because I wanted to understand the full picture of how data moves, transforms, and gets used to make decisions. That combination of systems thinking and data reasoning is what drives most of how I approach problems.

I care about correctness over cleverness, observable systems over opaque ones, and documentation that actually helps the next person instead of covering the author's tracks. Pipelines are boring until they break — at which point they're the most important thing anyone cares about. I find that constraint clarifying.

This site is personal and not affiliated with my employer. Everything here reflects my own views and work.

Privacy by default. I use tools that respect it. I build things that don't require it to be sacrificed. This site has no analytics, no trackers, and no cookies — not because I couldn't add them, but because I don't want them.

Open knowledge. I built The Prompt Kitchen because I kept seeing people struggle with AI tools in ways that had obvious solutions — solutions nobody had written down clearly. Good information should be findable, not gatekept behind paywalls or buried in YouTube comments.

Practical over hype. I've watched a lot of technology arrive with enormous fanfare and leave having solved a much smaller problem than advertised. I try to stay curious without getting swept up. The question I always come back to: does this actually help someone do something?

Specificity. Vague is easy. Specific is hard and usually more useful. In writing, in engineering, in explaining something to someone who doesn't know what you know yet.

The Prompt Kitchen is a free knowledge base about using AI practically — for everyday people, not just developers. It lives at thepromptkitchen.fyi.

I built it because the AI conversation has two speeds: "this will change everything" and "I tried it once and it didn't work." Neither is helpful. The people I wanted to reach are somewhere in the middle — they know these tools exist, they sense there's something useful there, and they just need someone to show them concretely how to get value out of them without a PhD in machine learning or a six-week course.

It makes sense given who I am: someone who thinks about data systems, has to communicate complex ideas clearly, and believes useful knowledge should be accessible. It's not a random side project — it's a logical extension of what I already care about.