Blog
Notes on self-hosted AI.
Practical, technical writing on running and building AI platforms — not announcements, just how things actually work.
Guide
Self-Hosting an Open-Source LLM Interface: A Practical Guide
A practical walkthrough of what it actually takes to self-host an open-source AI chat interface: architecture, model backends, storage, and the trade-offs versus SaaS.
Explainer
Retrieval-Augmented Generation (RAG), Explained Without the Hype
How retrieval-augmented generation actually works under the hood: chunking, embeddings, vector search, and where it breaks down in practice.
Operations
Role-Based Model Access Control for AI Tools: Why Teams Need It
Why organizations rolling out an AI chat tool to more than one team need per-group model permissions, and what happens when they skip it.