# Guardrails prebuilt policies

Coralogix Guardrails includes prebuilt policies that you can apply immediately to protect your LLM applications. Each policy performs a real-time, deterministic check on model inputs or outputs and throws an exception when a violation is detected.

## Available prebuilt policies

| Policy                                | What it detects                                                                                                              | When to use                                                                 |
| ------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------- |
| [Prompt Injection](#prompt-injection) | Attempts to manipulate model behavior by injecting malicious instructions into user prompts                                  | All production AI applications that accept user input                       |
| [PII Detection](#pii-detection)       | Personally identifiable information such as email addresses, phone numbers, credit card numbers, and Social Security Numbers | Data privacy compliance (GDPR, HIPAA) and sensitive data leakage prevention |
| [Toxicity](#toxicity)                 | Toxic, harmful, or offensive content including hate speech, threats, harassment, and abusive language                        | Customer-facing AI and brand safety                                         |

For domain-specific protection beyond the prebuilt options, see [Custom Policies](https://coralogix.com/docs/user-guides/ai/guardrails/custom_policies/index.md).

## What you need

- `cx-guardrails` installed. See [Getting Started with Guardrails](https://coralogix.com/docs/user-guides/ai/guardrails/getting_started/index.md).
- The `AI-GUARDRAILS:MANAGE` [permission](https://coralogix.com/docs/user-guides/aaa/access-control/permissions/permissions-list/index.md).
- A [Team API key](https://coralogix.com/docs/user-guides/account-management/api-keys/api-keys/index.md) with the **AiObservability** role preset, used as `CX_GUARDRAILS_TOKEN`. The AiObservability preset includes `AI-GUARDRAILS:MANAGE` and all other permissions required to use Guardrails.

## Understanding thresholds

All prebuilt policies return a score between 0 and 1.

| Score range | Meaning                                 | Action taken?          |
| ----------- | --------------------------------------- | ---------------------- |
| Closer to 1 | Violation detected with high confidence | Yes — exception thrown |
| Closer to 0 | Low severity — probably not a violation | No                     |

Guardrail policies use **configurable thresholds** in the code. The threshold defines the value from which a guardrail action is triggered — when the score meets or exceeds the threshold you set, the policy throws an exception, blocks the interaction, and the system marks the event as an issue.

## Prompt injection

The prompt injection detection policy identifies and blocks attempts to manipulate model behavior through malicious instructions injected into user prompts — such as attempts to ignore system instructions, leak system prompts, or perform unintended actions.

### Configuration

**Custom threshold**

Adjust detection sensitivity (0.0 to 1.0, default 0.7):

```python
# Lower threshold — more sensitive
await guardrails.guard_prompt(
    prompt=user_input,
    guardrails=[PromptInjection(threshold=0.5)],
)

# Higher threshold — less sensitive
await guardrails.guard_prompt(
    prompt=user_input,
    guardrails=[PromptInjection(threshold=0.9)],
)
```

For full setup including SDK installation and environment variables, see [Prompt Injection Detection](https://coralogix.com/docs/user-guides/ai/guardrails/prompt_injection/index.md).

## PII detection

The PII detection policy identifies personally identifiable information in prompts or responses, preventing sensitive personal data from being processed or exposed by your LLM applications.

### Available PII categories

| Category      | Enum value                  | Description                |
| ------------- | --------------------------- | -------------------------- |
| Email Address | `PIICategory.EMAIL_ADDRESS` | Email addresses            |
| Phone Number  | `PIICategory.PHONE_NUMBER`  | Phone numbers              |
| Credit Card   | `PIICategory.CREDIT_CARD`   | Credit/debit card numbers  |
| US SSN        | `PIICategory.US_SSN`        | US Social Security Numbers |

### Configuration

**Specific categories**

Detect only specific PII types:

```python
await guardrails.guard_prompt(
    prompt=user_input,
    guardrails=[PII(categories=[PIICategory.EMAIL_ADDRESS, PIICategory.CREDIT_CARD])],
)
```

**Custom threshold**

Adjust detection sensitivity (0.0 to 1.0, default 0.7):

```python
# Lower threshold — more sensitive
await guardrails.guard_prompt(
    prompt=user_input,
    guardrails=[PII(threshold=0.5)],
)

# Higher threshold — less sensitive
await guardrails.guard_prompt(
    prompt=user_input,
    guardrails=[PII(threshold=0.9)],
)
```

For full setup including SDK installation and environment variables, see [PII Detection](https://coralogix.com/docs/user-guides/ai/guardrails/pii/index.md).

## Toxicity

The toxicity detection policy identifies harmful, offensive, or inappropriate content — including hate speech, threats, harassment, and abusive language — in prompts or responses before they reach users.

### Configuration

**Custom threshold**

Adjust detection sensitivity (0.0 to 1.0, default 0.7):

```python
# Lower threshold — more sensitive
await guardrails.guard_prompt(
    prompt=user_input,
    guardrails=[Toxicity(threshold=0.5)],
)

# Higher threshold — less sensitive
await guardrails.guard_prompt(
    prompt=user_input,
    guardrails=[Toxicity(threshold=0.9)],
)
```

For full setup including SDK installation and environment variables, see [Toxicity Detection](https://coralogix.com/docs/user-guides/ai/guardrails/toxicity/index.md).

## Next steps

Set up prompt injection detection for your LLM applications with [Prompt injection](https://coralogix.com/docs/user-guides/ai/guardrails/prompt_injection/index.md).