How I got 80% code retrieval accuracy without vectors, embeddings, or any ML

I wanted to answer one question: how far can pure heuristic retrieval go before you actually need embeddings? The answer surprised me. The problem with AI coding tools today When you paste your codebase into an LLM, you're typically sending 60,000–100,000 tokens of raw source code. Most of that is noise — loop bodies, imports, boilerplate — that never shows up in the answer. The model reads the wrong file. Guesses the rest. You retry 2–3 times. The insight Code ident...