RAG is the standard approach whenever answers must be verifiable, the underlying information changes, or different users are permitted to see different documents. Because entitlements can be applied to the retrieval step, two users asking the same question can legitimately receive different answers — something a model with knowledge baked into its weights cannot do.
Most failed RAG projects fail at retrieval rather than generation. The pattern is consistent: a pilot works on twenty clean documents, then collapses against forty thousand real ones with scanned PDFs, superseded versions and tables that lost their structure during parsing. Chunking that ignores document structure and pure vector search on exact identifiers are the two most common defects, and both are fixable.
| RAG | Fine-tuning | |
|---|---|---|
| Solves | Model lacks information | Model responds in the wrong way |
| Updating knowledge | Edit a document — instant | Retrain — slow and costly |
| Citations | Yes — every claim traceable | No — knowledge is baked in |
| Permission filtering | Yes, at query time | No |
Codazz builds this in production — RAG Development.