Every retrieval vector in this series earns its place by resolving cases the others get wrong. Past that point, adding another one doesn't add coverage, it adds noise for the reranker to clean up, and the corpus gets harder to filter exactly as it grows large enough to need filtering most.

A knowledge base doesn't just retrieve facts, it retrieves claims, and claims come with sources of wildly different quality. The policy doc and the offhand Teams message can say the same thing with completely different authority behind them. Most retrieval systems can't tell the difference.

Access control and metadata filtering both narrow the candidate pool before search runs, which makes people treat them as the same mechanism. They aren't, and the difference is exactly where a query classifier can quietly cost you the right answer.

A document's publish date tells you when it was written. It doesn't tell you when the facts inside it stopped being true. That gap is where knowledge management systems get confidently wrong answers, and it's the same gap that makes a graph worth building.

Every enterprise knowledge project starts with a request for 'semantic search.' What actually works is six retrieval methods arguing with each other until a reranker decides who's right.