AI engineering glossary · Prompt context engineering
What is grounding?
Grounding: Tying a model's answer to supplied source material or verified data, and telling it to answer only from that material. It reduces invented facts and lets users check claims against the source.
Grounding: an example
'Answer using only the policy text below; if the answer is not there, say you do not know.'
Related terms
More Prompt context engineering terms
- In-context learning
- Instruction following
- Instruction hierarchy
- Instructor library
- JSON mode
- Least-to-most prompting
- Logit bias
- Logprobs
Where you learn it
Grounding is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.