What is Groundedness?

The degree to which a model's behavior can be interpreted and explained to humans.

A structured argument, supported by evidence, that an AI system is safe for a defined context of use.

A policy where request/response payloads are not stored after processing beyond short-lived operational windows.

References to source passages or documents included in a model's response to support its claims.

How well a model performs on new, unseen data outside the training set.

Systematic unfairness in model outputs caused by skewed data, assumptions, or modeling choices.