Data · We run it ourselves
Answering from a body of documents the model retrieves at question time, rather than from what it absorbed in training.
A model that answers from training answers plausibly. A model that answers from your catalogue answers correctly, and the difference is entirely in the retrieval — which is where nearly all the engineering is, and nearly none of the attention.
01
It makes an answer traceable. When a reply can be pointed back to the passage it came from, a wrong answer becomes a fixable retrieval problem instead of an argument about the model.
02
It changes what an update costs. Correcting a fact means editing a document, not retraining anything, so the people who own the knowledge can own the corrections.
03
Grounding is what makes a sales conversation survivable. A buyer comparing a serious purchase asks specific questions, and an assistant that invents an accreditation has done more damage than one that stayed silent.
04
Embeddings are only the index. Chunking, ranking, what gets shown to the model and what happens when nothing relevant is found are the parts that decide the answer, and they are ordinary engineering rather than magic.
An entry that cannot point at something you can open, run or read does not compile. That is a property of the type, not a promise in a paragraph.
Invariant
Retrieval cannot fix a corpus that disagrees with itself. Where two documents state different prices, the system will confidently return one of them, and the work that follows is editorial rather than technical. We say this before the build, because it is the most common reason a grounded assistant disappoints.