Explainable AI
Quick Answer
Explainable AI (XAI) is a set of techniques and design practices that make AI systems' decisions understandable to humans. Explainability supports trust, debugging, accountability and regulatory compliance, particularly in consequential decisions.
In Depth
What Explainable AI really means
Approaches range from inherently interpretable models (e.g. linear models, decision trees) to post-hoc techniques such as SHAP or LIME that approximate what drives individual predictions in complex models.
Explainability is not a single metric; it is a capability matched to an audience. An engineer needs different explanations than a customer, a regulator or an auditor. Designing for each audience is part of the product.
Why It Matters
Business relevance for UK organisations
UK financial services, insurance, healthcare and HR use cases increasingly require demonstrable explainability, both to satisfy regulators and to sustain customer trust.
Real-world example
How this shows up in practice
A Cardiff lender introduced SHAP-based explanations for every automated credit decision, reducing customer complaints about declined applications by 37%.
Related Terms
Continue exploring
AI Governance
AI governance is the set of policies, roles, controls and oversight mechanisms that ensure AI is used responsibly, safely and in line with law and organisational values. Effective governance is proportionate — tight where risk is high, light where risk is low.
BusinessAI Ethics
AI ethics is the discipline of ensuring AI systems are designed, deployed and monitored in ways that respect fairness, transparency, privacy, human autonomy and wider societal impact. It goes beyond legal minimums to reflect organisational values.
BusinessAI Policy
An AI policy is an internal document that sets out how employees and vendors may — and may not — use AI within an organisation. A strong policy covers approved tools, prohibited use cases, data handling, intellectual property, disclosure, and responsibilities.