Writing
BLOG
Deep-dives on what I build — RAG systems, LLM engineering, and the decisions that separate production from demo.
Latest
Apr 2026
RAGLegal NLPArchitecture
How I'd Build a Production RAG System for Legal Documents
A design essay, not a tutorial. Starting from the constraints a law firm would actually impose — hallucinations as malpractice, jurisdictional context, privilege protection — and working backward to the architecture that survives them.
Apr 2026
Multi-AgentLLMsDistributed Systems
Building Multi-Agent Systems That Don't Fall Apart
Lessons from running 500+ concurrent agent sessions in production — orchestrator design, message routing with delivery guarantees, shared memory without race conditions, and the failure modes nobody writes tutorials about.
Apr 2026
RAGClinical NLPEmbeddings
How I Designed QuitTxt's RAG Pipeline
Chunking clinical documents, picking an embedding model, and calibrating a refusal threshold — lessons from building a grounded AI system for smoking cessation research.