Retrieval-Augmented Generation (RAG): the practical guide to building grounded LLM appsJan 30, 2026·10 min read
RepoRAG: Repo-Native RAG for Local Folders & Remote Git ReposWhen I am dropped into a new codebase, I don’t want “general advice.” I want specific, grounded answers: Where is the main LLM pipeline entry point? How does the end-to-end inference flow work? Where is retrieval feature implemented? The problem...Feb 2, 2026·7 min read
