> ## Documentation Index
> Fetch the complete documentation index at: https://docs.declaw.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# PII Actions

> Compare the three PII action modes — redact, block, and log_only — and understand when to use each.

## What You'll Learn

* Creating sandboxes with each of the three PII action modes: `redact`, `block`, and `log_only`
* The full `SecurityPolicy` JSON produced by each mode
* What each mode does when the guardrails service is active

## The Three PII Action Modes

| Action     | What Happens When PII Is Detected                                   |
| ---------- | ------------------------------------------------------------------- |
| `redact`   | PII tokens are replaced with placeholders; request is forwarded     |
| `block`    | The entire HTTP request is rejected; sandbox code receives an error |
| `log_only` | Detection is logged but the request passes through unchanged        |

## Prerequisites

<Snippet file="snippets/env-setup.mdx" />

<Note>This example is available in Python. TypeScript version coming soon.</Note>

## Code Walkthrough

The example creates a sandbox for each action mode and prints the resulting policy. A helper function keeps the pattern clean:

```python theme={null}
from declaw import Sandbox, SecurityPolicy, PIIConfig, RedactionAction

def demonstrate_action(action: RedactionAction) -> None:
    policy = SecurityPolicy(
        pii=PIIConfig(
            enabled=True,
            types=["email", "phone", "ssn", "credit_card"],
            action=action.value,
        )
    )

    print(f"Policy configuration:\n{policy.to_json()}")

    sbx = Sandbox.create(template="base", timeout=300, security=policy)
    try:
        print(f"Sandbox created: {sbx.sandbox_id}")
        info = sbx.get_info()
        print(f"  State: {info.state.value}")
    finally:
        sbx.kill()
        print("Sandbox killed.")
```

Iterate over all actions:

```python theme={null}
for action in RedactionAction:
    demonstrate_action(action)
```

**`redact` mode** replaces PII with placeholder tokens, then forwards the request:

```
"jane@example.com"     ->  "[REDACTED_EMAIL]"
"555-867-5309"         ->  "[REDACTED_PHONE]"
"123-45-6789"          ->  "[REDACTED_SSN]"
"4111-1111-1111-1111"  ->  "[REDACTED_CREDIT_CARD]"
```

**`block` mode** rejects the entire HTTP request when PII is detected. The sandbox code receives an error response from the proxy.

**`log_only` mode** detects and records PII in the audit log but passes the HTTP traffic unchanged. Useful for monitoring PII exposure without disrupting the application.

## Choosing the Right Action

* Use **`redact`** when you want to call external APIs but prevent PII from leaving the sandbox in plaintext.
* Use **`block`** for the strictest posture — if any PII is detected, the request must not proceed.
* Use **`log_only`** during development to understand how much PII is flowing before enforcing redaction.