What is the difference between explainability and interpretability in AI?

Explainability justifies specific decisions to users ('why did you do this'). Interpretability exposes internal model mechanisms ('how does this work'). A model can be explainable without being interpretable. In regulated domains, explainability is the practically achievable requirement under GDPR and the EU AI Act.

AI Trust Glossary · Canonical Definition

Explainability

The degree to which an AI system's decisions can be presented to users in understandable terms - justifying specific outputs without necessarily exposing internal model workings.

Borealis Research Team · Updated March 2026 · View all 47 terms

Explanation

Explainability focuses on the output side: 'why did you do this.' Interpretability focuses on internal mechanisms: 'how does this work.' A neural network can be explainable (LIME/SHAP feature attributions) without being interpretable (inspectable weights). In regulated domains, explainability is the practically achievable requirement.

Why it matters

The EU AI Act and GDPR's right to explanation require that automated decisions affecting individuals can be explained. Explainability is also a practical debugging tool - unexplainable failures are the hardest to fix.

How Borealis uses it

The decision transparency dimension measures explainability at the decision level. hasReasoningChain and reasoningDepth in the telemetry schema capture whether the agent produced a traceable justification for each decision.