# Set Sensitivity of a Data Type

Control where data types are flagged as sensitive - in agent inputs, outputs, tool calls, or context.

## Why Set Sensitivity

Example: Flag "TOKEN" as sensitive only in agent responses, not in requests. This reduces noise while ensuring leaked credentials are caught.

## How to Configure

1. Go to **Agentic Discovery > Sensitive Data**
2. Click **"..."** on the data type
3. Select **Edit**
4. Choose sensitivity locations:
   * Agent Inputs (prompts, requests)
   * Agent Outputs (LLM responses)
   * Tool Invocations (MCP calls)
   * Context/Memory (conversation history)
   * All locations

## Agentic-Specific Sensitivity

**Agent Inputs**: User prompts, questions

* Sensitive: PII, credentials, secrets

**Agent Outputs**: LLM-generated responses

* Sensitive: Leaked credentials, PII in responses

**Tool Invocations**: MCP tool calls

* Sensitive: Database queries, file paths, API keys

**Context/Memory**: Agent conversation history

* Sensitive: Accumulated PII, session data

## Example: API Keys

Set API\_KEY sensitive in:

* ✅ Agent Outputs (catch leaks)
* ✅ Tool Invocations (monitor access)
* ❌ Agent Inputs (expected to receive keys)


---

# 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/set-sensitivity-of-a-data-type.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.