About

Threadmaze is where I write up the AI and data systems I build. My focus is practical and privacy-first: retrieval-augmented generation, locally hosted language models, vector search, and the data pipelines that feed them. These are systems that turn messy documents into grounded, cited answers without sending sensitive data to someone else's cloud.

Much of my background is in healthcare data and analytics, where the gap between "an AI demo" and "something you can actually deploy" is mostly about trust, privacy, and grounding. That gap is what these projects explore.

Each post follows the same shape: the problem, the analysis, the solution, the outcome, and what I learned. If any of it is useful to you, or you want to talk shop, reach out: research@threadmaze.com.