# What is grounding?

> Tying an AI answer to specific source material, so every claim in it can be traced back to a page, article or document you provided.

URL: https://office.greatwork.company/glossary/grounding
Last updated: 2026-11-21

Tying an AI answer to specific source material, so every claim in it can be traced back to a page, article or document you provided.

A grounded answer is one the model wrote from passages it was given, not from its general training. Citations are the visible part: each answer lists the pages it used.

Grounding is a spectrum. A strict setup refuses anything the sources don't cover; a looser one lets the model add small talk or general facts. For support, strict is usually right.

## Where you'll use it

- [Answers with sources](https://office.greatwork.company/assist/features/answers-with-sources): Every answer shows the pages it came from. When your content doesn't cover a question, the assistant says so and offers your team instead of making something up.

## Related terms

- [Retrieval-augmented generation](https://office.greatwork.company/glossary/retrieval-augmented-generation): RAG: a method where an AI model first looks up the most relevant passages in your own content, then writes its answer only from those passages.
- [AI hallucination](https://office.greatwork.company/glossary/ai-hallucination): When an AI model states something that sounds right but isn't supported by any source, like an invented return policy, feature or price.

---

Office by Great Work. Questions or corrections: hello@greatwork.company
