Chunking and source hygiene

Most RAG failures are content failures When a grounded assistant gives bad answers, the retrieval step is usually fine — the content it was pointed at was the problem. Two things dominate: how documents are split, and what is in the knowledge base at all. Chunking Documents are split into chunks before embedding, because you […]

Keeping the corpus honest

A grounded system is only as good as what it is grounded in RAG answers faithfully from your documents. If your documents contain three versions of the expenses policy, two of them obsolete, the system will answer faithfully from the wrong one — and it will cite its source while doing it, which makes the […]

When not to build RAG

The most expensive RAG system is the one that should have been a search box RAG is genuinely the right answer for a large body of documents and open-ended questions. It is also proposed constantly for problems it does not fit, at considerable cost. Four cases where something simpler wins The corpus is small and […]