Spec In, Verified Code Out: Building an Agentic AI Pipeline for Automatic Code Generation

LLMs can already write code from a spec. The hard part is trusting that code without a human re-reading every line. The answer I landed on is not a better prompt but a better workflow: a small team of AI agents, each with one job, handing each other structured, checkable artifacts. Most codebases have a … Continue reading Spec In, Verified Code Out: Building an Agentic AI Pipeline for Automatic Code Generation

Build a RAG System that knows when to shut up

A local document chatbot with hybrid search, reranking, and a confidence check that refuses to answer when it isn't sure. That last part turned out to be the most important piece. Why Not Just Use ChatGPT? I had a big pile of PDFs — runbooks, playbooks, technical docs — and I wanted to ask questions … Continue reading Build a RAG System that knows when to shut up