Projects
Explorations in AI engineering — built to learn, measure, and understand.
-
A diagnostic assistant for distributed systems incidents. Builds bounded diagnostic state across iterations instead of producing free-form answers.
-
A modular environment for studying how different parts of a RAG pipeline affect final answer quality. Built to separate the effects of chunking, retrieval, reranking, and prompting and compare them cleanly.
-
A note memory system that supports natural-language retrieval, note updates, and Slack integration.