Retrieval

You'll learn how RAG retrieves, augments and generates answers, why tuning retrieval won't fix outdated documents, and how to keep a knowledge base trustworthy by managing it like code.

You'll learn to measure precision@k and distractor rate alongside recall@k, and to choose how much context a coding agent gets based on whether its output passes, not on whether the right file showed up.

You'll learn what a vector database stores, how it finds results through chunking, embedding, indexing and querying, where it fits in an agent stack, and why live code needs grep, call graphs and freshness checks.

You'll learn how a mid-sentence chunk split causes a RAG pipeline to confidently deny a fact that's actually in the source docs, and how to find and fix that failure in your own pipeline.

The relevance bug everyone blames on embeddings is usually one missing pipeline stage away from fixed — here's the two-line diagnostic that tells you which problem you actually have.

Three weeks of swapping embedding models and tuning rerankers won't fix a retriever that's been fed half a function signature — here's the 10-minute check that tells you if chunking, not your model, is the real problem.

A vector DB looked like an obvious upgrade until the numbers came back, and by then the agent had been quietly answering from the wrong documents for weeks.

It's not your prompt, your retriever, or your reranker — it's the embeddings you set once and never looked at again, and here's the diagnostic that catches it before it becomes an incident.

One afternoon of dialing alpha to a perfect 0.73 taught me why the boring, un-tunable fusion default quietly wins in production — and how to catch yourself before you memorize your own test set.

Most 'the AI got it wrong' tickets in a RAG system aren't model bugs at all — they're stale index entries in a hallucination costume, and a 3-question checklist tells you which one you're actually chasing.

Nine times out of ten, the chunk your model needs is already sitting in your retrieved set — just ranked too low to ever get read, and there's a one-hop fix that costs almost nothing to bolt on.

A cosine similarity score feels like proof of quality — until an exact SKU search comes back empty, and you realize 'semantic' was never something you'd actually measured.

The answer your user needed didn't get lost in search — it got cut in half before your embedding model ever laid eyes on it, and there's a 20-minute check that proves it.

A 10-minute audit of your actual query pattern — recall, corpus size, filters, writes — will tell you whether you need Pinecone or just Postgres, and for most RAG features the honest answer isn't the one every stack diagram assumes.

If your retrieval eval scores refuse to budge no matter which embedding model you throw at them, the fix isn't a bigger model — it's the chunk boundary that quietly amputated your answer before encoding ever happened.