Explainability
The degree to which the mechanisms behind an AI system's output can be described in terms people understand.
In NIST's AI Risk Management Framework, explainability refers to a representation of the mechanisms underlying an AI system's operation, while interpretability refers to the meaning of its output in the context of its purpose, and both are listed among the characteristics of trustworthy AI. In finance, explanation duties also come from law, such as the obligation to give applicants specific reasons for adverse credit decisions. For agents, a useful explanation covers what the agent did, on what authority, using which data, and why it chose that action.
Agent Minute explains this term on 11 December 2026.
Related terms
Adverse action noticeA US notice telling a credit applicant about an adverse decision and the specific principal reasons for it.AI Risk Management FrameworkNIST's voluntary framework for managing AI risks, organised into the functions Govern, Map, Measure and Manage.Audit trailA chronological record of who accessed a system and what operations they performed, enough to reconstruct events.Automated individual decision-makingA decision about a person made solely by automated means that has legal or similarly significant effects.