Explainability in AI refers to the ability to describe, in understandable terms, how an AI system reached a particular output or decision.
Many AI models — particularly deep learning models — are difficult to interpret. They may produce accurate results without providing a clear reason why. Explainability tools and techniques attempt to make model behaviour more transparent.
Explainability matters most in high-stakes contexts such as credit decisions, medical diagnosis, or legal proceedings, where affected people have a legitimate interest in understanding why a decision was made.