Explainability

AIGP glossary · Last reviewed: 2026-07-08 · By Victor Humenhuk (AIGP certified)

Explainability - The degree someone can consistently predict a model's result; essential for fairness, privacy, reliability, robustness, causality and trust.

In the AIGP body of knowledge, Explainability comes up under Module 2: AI Impacts & Responsible AI · BoK II.A; Module 6: Governing AI Development · BoK III.A; Module 8: AI Governance Vocabulary.

Explainability in context

• [[Explainability]] and transparency are the keys to trust; [[PETs]] support privacy-enhanced AI. (Trustworthy AI: the HAT test)
• Feature engineering decides which ones matter, with three purposes - ==improve performance== (the most important), cut cost, and boost ==explainability==. (Features and Feature Engineering)
• ==Conformity assessment is the EU AI Act gate for high-risk systems before market==, and explainability (why an output) is distinct from interpretability (how the model works inside). (Governance, assurance and oversight)

Where Explainability is covered in the AIGP study notes

• Trustworthy AI: the HAT test
• Features and Feature Engineering
• Governance, assurance and oversight

Related terms

• HAT test
• PETs
• Distrustful AI
• Feature
• Feature engineering
• Feature flags
• AI governance
• Accountability
• AI assurance
• AI audit

Test yourself on Explainability

Recognising a definition is not the same as applying it in an exam scenario. Work through the free AIGP practice questions, or read the full AIGP study guide - every study note is free.

← Back to the AIGP glossary