---
title: "Drift"
description: "The gradual divergence of a model's inputs, outputs or performance from its validated baseline over time; a runtime signal that a control or eval must catch."
canonical: https://aigovernanceengineer.com/glossary/drift
author: "Jorge García Aibar"
license: "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)"
doi: https://doi.org/10.5281/zenodo.22956197
version: "0.5.0"
updated: 2026-09-25
---

# Drift

The gradual divergence of a model's inputs, outputs or performance from its validated baseline over time; a runtime signal that a control or eval must catch. The two kinds to tell apart are data drift, in the inputs, and concept drift, in the input-to-answer relationship.

- Developed in: [ch. 15, Drift: what moves and how to see it](https://aigovernanceengineer.com/bok/governing-deployment#drift-what-moves-and-how-to-see-it); [ch. 05, Pattern: Drift & Fairness Monitor](https://aigovernanceengineer.com/patterns/drift-fairness-monitor); [ch. 17, AI-specific failure modes](https://aigovernanceengineer.com/bok/incidents#ai-specific-failure-modes)
- Chapters: [ch. 04, The Stack](https://aigovernanceengineer.com/bok/the-stack) · [ch. 05, Patterns](https://aigovernanceengineer.com/bok/patterns) · [ch. 11, AI Defined](https://aigovernanceengineer.com/bok/ai-defined) · [ch. 15, Deployment](https://aigovernanceengineer.com/bok/governing-deployment) · [ch. 16, Fairness & XAI](https://aigovernanceengineer.com/bok/fairness-and-explainability) · [ch. 17, Incidents](https://aigovernanceengineer.com/bok/incidents)
- Contrast with: [Data drift](https://aigovernanceengineer.com/glossary/data-drift) · [Concept drift](https://aigovernanceengineer.com/glossary/concept-drift)
- In the glossary chapter: https://aigovernanceengineer.com/bok/glossary#t-drift

## Sources

Defined by this Body of Knowledge: the section it is developed in is the source.