# Explainable AI (XAI)

> Ways to show people why an AI made a choice.

**Field:** Artificial Intelligence  
**Category:** Ethics & Regulation  
**Also known as:** XAI, AI Explainability, Explainability

## Think of it like

It is like a teacher who shows you how they marked your test.

## Definition

Explainable AI is a set of methods that show people why an AI made a choice. A model may turn down a loan, and the person asks why. An explainable system can point to the inputs that weighed most, such as income or missed payments. Common tools score how much each input pushed the answer up or down. Some laws give people a right to a real reason when a machine's choice affects them.

## Example

Lucy's loan request is turned down by an app. The app shows that her high debt and two missed payments weighed most, so she knows what to fix before trying again.

## Why it matters

People trust what they understand. They can only push back on a choice if they know the reason.

## Common mistake

Taking the reason as the whole truth. Most tools give a short summary of a big model, and the summary can mislead.

## Three principles

- **Why, not just what.** Show the reason.
- **Inputs that mattered.** Ranked.
- **A summary.** Not the whole truth.

## Related terms

- [Interpretability (AI)](https://learn.benibix.com/term/ai/interpretability)
- [Model Card](https://learn.benibix.com/term/ai/model-card)
- [AI Bias](https://learn.benibix.com/term/ai/ai-bias)
- [Responsible AI](https://learn.benibix.com/term/ai/responsible-ai)

## Told apart from

- [Explainable AI vs Interpretability](https://learn.benibix.com/compare/explainable-ai-vs-interpretability): People often think explainable AI and interpretability are the same thing. The first gives a person a reason for one choice, such as what mattered most for a loan. The second looks inside the model to see how it works, part by part. A reason can help and still be a short summary. It may hide how the model truly chose.

![A loan is turned down. Beside the answer, a bar chart shows the three reasons that weighed most: income, debt and missed payments.](https://learn.benibix.com/diagrams/et-explainable-ai.svg)

---

Source: https://learn.benibix.com/term/ai/explainable-ai
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
