# Redact sensitive data

Redact sensitive data to comply with privacy regulations and prevent unauthorized access. Critical for agent systems handling PII and credentials.

## Redaction Levels

1. **By Data Type**: Redact all instances of a data type (e.g., all API keys)
2. **By Collection**: Redact entire agent/MCP collection
3. **Global**: Redact all data across all agents

## Important Note

{% hint style="warning" %}
Redacting data affects AI Red Teaming. Without stored values, agent requests can't be replayed and scanned.
{% endhint %}

## How Redaction Works

Values are replaced with `*****`:

```json
{"agent_prompt": "*****", "llm_response": "*****"}
```

## Redact by Data Type

1. Go to **Agentic Discovery > Sensitive Data**
2. Select data type
3. Click **Edit**
4. Set **Redact this data type** to **True**

## Redact by Collection

1. Open the agent/MCP collection
2. Click **More options**
3. Select **Redact**
4. Click **Enable**

## Redact All Data

1. Go to **Settings > About**
2. Click **Redact data**
3. Confirm (affects all collections)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ai-security-docs.akto.io/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-ai-discovery/how-to/redact-sensitive-data.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.