# What is Presidio? Definition and meaning

Microsoft's open-source toolkit for finding and anonymizing personally identifiable information in text and images.

## Definition

**Presidio**: Microsoft's open-source toolkit for finding and anonymizing personally identifiable information in text and images.

In short: Detecting and redacting personal data.

## When it is used

De-identifying data before it reaches a model or a log.

## Where it fits

Presidio belongs to **LLM safety** in the [Generative AI and LLMs](/topics/generative-ai-llms) topic. These are the other terms in the same group:

- **[Guardrails AI](/glossary/guardrails-ai)**: A framework that checks model responses against validators for structure, safety and content rules.
- **[NeMo Guardrails](/glossary/nemo-guardrails)**: A toolkit that adds topic, safety and security rails to LLM applications using a dedicated rule language.
- **[Red-teaming](/glossary/red-teaming)**: Systematically testing a model or application with adversarial inputs to find unsafe or unintended behaviour.

## Learn more

The full guide to **[Presidio](/tools/presidio)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [Prefix tuning](/glossary/prefix-tuning) · Next term: [Principal component analysis](/glossary/principal-component-analysis)
