Explainability

The ability of an AI system to provide human-understandable reasons and justifications for its outputs, predictions or decisions.

The ability to answer the question: "Why did the AI make that decision?" For example, if AI rejects a job applicant, explainability means being able to say exactly which factors led to that rejection.

Regulators are increasingly requiring that AI decisions can be explained to affected individuals. Organisations that invest in explainability are better prepared for compliance and can demonstrate responsible use to stakeholders and boards.