Glossary · 4 · Grounding: content, retrieval and knowledge
Grounding
Also known as: Grounded generation, Source attribution
Grounding is the practice of tying a generative AI model’s output to specific, verifiable sources — retrieved documents, databases, search results or tool outputs — so that answers can be traced and checked instead of relying on the model’s internal knowledge.
- Intermediate
- Technical writers
- Technical marketers
- Technical project managers
- Developers
In one sentence
Grounding in AI explained: tying model answers to verifiable sources — the main defense against hallucinations in documentation and support.
Example
A grounded assistant answers “The maximum operating temperature is 45 °C” and links to the data sheet section it took the value from.
Explained in context
This term is a station of a mini course
- The medical-device evidence chain: from intended purpose to post-market evidenceStation: Controlled retrieval from the fileStart the course
Context cards connect this term with others to answer one question. Also in British English and German.
- The answer function compiles — it doesn’t readIs an AI answer function a reader of the documentation?UKDeutsch
- From structured content to controlled evidence: five stages of AI-ready documentationIs structured content enough to make medical-device documentation ready for AI?UKDeutsch
- The medical-device evidence chain: from intended purpose to post-market evidenceHow do the parts of a medical device’s technical documentation connect — and what has to be in place before an AI function may answer from it?UKDeutsch
- What an answer function may read: retrieval permissions for a medical-device technical fileWhich parts of a medical-device technical file may an AI answer function retrieve?UKDeutsch
Why it matters on your learning path
- Technical writers: Grounded answers are only as good as their sources. Outdated or contradictory content produces confidently wrong answers.
- Technical marketers: Citations build trust in AI features; they also expose outdated public pages.
- Technical project managers: Require source citations as an acceptance criterion for customer-facing AI.
- Developers: Return source identifiers with every retrieved passage and show them in the answer.