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

# Guardrails Configuration

> Step-by-step guide to configuring and applying Guardrails to your agents

# Guardrails Configuration

Learn how to configure and apply Guardrails to protect your agents with intelligent content filtering. This guide covers everything from understanding the default guardrail to creating and managing custom guardrails.

## Prerequisites

Before configuring Guardrails, ensure you have:

<Check>**Agent Created**: You need an existing agent to apply guardrails to</Check>
<Check>**Admin Access**: Only project Admins and Owners can configure guardrails</Check>
<Check>**Requirements Identified**: Know what content needs protection</Check>

<Info>
  Guardrails are managed in the **Guardrails** section of the agent dashboard.
</Info>

***

## Understanding the Default Guardrail

Every agent in PLai Framework comes with a **default INPUT guardrail** automatically active:

### Default Guardrail Coverage

<CardGroup cols={2}>
  <Card title="Sexual Content" icon="ban" color="red">
    Blocks explicit sexual material, inappropriate content, or sexual advances
  </Card>

  <Card title="Hate Speech" icon="ban" color="red">
    Blocks discrimination, prejudice, hateful content, or targeted harassment
  </Card>

  <Card title="Insults & Abuse" icon="ban" color="red">
    Blocks personal attacks, abusive language, or aggressive insults
  </Card>

  <Card title="Politics & Religion" icon="ban" color="red">
    Blocks political debates, partisan content, religious disputes, or divisive topics
  </Card>
</CardGroup>

<Note>
  **Important**: Default guardrail is optional enabled. It provides baseline protection for all agents without requiring any configuration.
</Note>

***

## Guardrail Types

Guardrails can be configured with different directions and actions:

### 1. Direction: INPUT vs OUTPUT

<Tabs>
  <Tab title="INPUT Guardrails">
    **Applied to user messages before AI processing**

    **Purpose:**

    * Protect AI model from harmful inputs
    * Filter malicious prompts
    * Mask sensitive user data
    * Block prohibited topics

    **Use Cases:**

    * User-facing chatbots
    * Public interfaces
    * Customer service applications
    * Community platforms

    **Processing Flow:**

    ```
    User Message → INPUT Guardrail → AI Model → Response
    ```

    <Info>
      INPUT guardrails run before the AI model sees the content, providing first-line defense against inappropriate inputs.
    </Info>
  </Tab>

  <Tab title="OUTPUT Guardrails">
    **Applied to AI-generated responses before delivery**

    **Purpose:**

    * Ensure safe AI outputs
    * Prevent harmful responses
    * Mask PII in responses
    * Maintain brand compliance

    **Use Cases:**

    * Content generation
    * Public communications
    * Regulated industries
    * Brand-sensitive applications

    **Processing Flow:**

    ```
    User Message → AI Model → AI Response → OUTPUT Guardrail → User
    ```

    <Info>
      OUTPUT guardrails validate AI-generated content before users see it, ensuring safe and compliant responses.
    </Info>
  </Tab>

  <Tab title="Both (INPUT + OUTPUT)">
    **Comprehensive protection on both sides**

    **Purpose:**

    * Maximum safety coverage
    * End-to-end protection
    * Full compliance assurance
    * Complete audit trail

    **Use Cases:**

    * Highly regulated industries
    * High-risk applications
    * Maximum security requirements
    * Sensitive domains

    **Processing Flow:**

    ```
    User Message → INPUT Guardrail → AI Model → 
    AI Response → OUTPUT Guardrail → User
    ```

    <Warning>
      Using both INPUT and OUTPUT guardrails provides maximum protection but adds latency to each interaction. Balance security needs with performance requirements.
    </Warning>
  </Tab>
</Tabs>

***

### 2. Action: Block vs Mask

<Tabs>
  <Tab title="Block">
    **Completely prevent content from passing**

    **When to use:**

    * Harmful content (hate speech, violence)
    * Prohibited topics (politics, religion)
    * Policy violations
    * Security threats
    * Inappropriate requests

    **Behavior:**

    ```
    Content Detected → BLOCKED → Safety Message Displayed
    ```

    **Example Configuration:**

    ```json theme={null}
    {
      "type": "INPUT",
      "action": "BLOCK",
      "categories": [
        "hate_speech",
        "violence",
        "sexual_content"
      ]
    }
    ```

    **User Experience:**

    * Request is not processed
    * Polite safety message displayed
    * User prompted to rephrase
    * Interaction logged for monitoring
  </Tab>

  <Tab title="Mask (Anonymize)">
    **Redact sensitive information while allowing flow**

    **When to use:**

    * PII protection (emails, phones, SSN)
    * Financial data (credit cards, accounts)
    * Personal identifiers (names, addresses)
    * Health information (PHI)
    * Confidential data

    **Behavior:**

    ```
    Content Detected → PII MASKED → Processing Continues
    ```

    **Example Configuration:**

    ```json theme={null}
    {
      "type": "INPUT",
      "action": "MASK",
      "pii_types": [
        "email",
        "phone",
        "credit_card",
        "ssn",
        "name",
        "address"
      ]
    }
    ```

    **Masking Examples:**

    ```
    Original: "My email is john.doe@example.com"
    Masked:   "My email is [EMAIL_REDACTED]"

    Original: "Call me at 555-123-4567"
    Masked:   "Call me at [PHONE_REDACTED]"

    Original: "My credit card is 4532-1234-5678-9012"
    Masked:   "My credit card is [CREDIT_CARD_REDACTED]"

    Original: "I'm John Smith from 123 Main St"
    Masked:   "I'm [NAME_REDACTED] from [ADDRESS_REDACTED]"
    ```

    <Info>
      Masking allows conversations to continue while protecting sensitive information from being processed, stored, or included in responses.
    </Info>
  </Tab>
</Tabs>

***

## Creating Custom Guardrails

Custom guardrails are created **on-demand** through Amazon Bedrock Guardrails service to meet your specific requirements.

### When to Create Custom Guardrails

<AccordionGroup>
  <Accordion title="Industry-Specific Compliance" icon="building">
    **Healthcare (HIPAA):**

    * Mask protected health information (PHI)
    * Block medical advice outside scope
    * Prevent patient data disclosure

    **Financial Services (PCI-DSS):**

    * Mask financial account details
    * Block unauthorized financial advice
    * Protect transaction information

    **Legal:**

    * Prevent unauthorized legal advice
    * Protect privileged information
    * Maintain confidentiality
  </Accordion>

  <Accordion title="Organization-Specific Policies" icon="shield-halved">
    * Custom prohibited topics
    * Brand-specific content rules
    * Internal data protection
    * Proprietary information safeguards
    * Employee information protection
  </Accordion>

  <Accordion title="Advanced PII Protection" icon="user-shield">
    * Custom PII types (employee IDs, patient numbers)
    * Industry-specific identifiers
    * Regional data protection (EU vs US)
    * Multi-language PII detection
  </Accordion>

  <Accordion title="Special Use Cases" icon="sparkles">
    * Content generation safety
    * Academic integrity
    * Child safety protections
    * Community guidelines enforcement
    * Custom safety categories
  </Accordion>
</AccordionGroup>

***

### Custom Guardrail Creation Process

<Steps>
  <Step title="Define Requirements">
    Document your specific needs:

    **Required Information:**

    * **Purpose**: What should this guardrail protect?
    * **Direction**: INPUT, OUTPUT, or both?
    * **Action**: Block or Mask?
    * **Content Categories**: What to filter?
    * **PII Types**: What to mask (if applicable)?
    * **Scope**: General or organization-only?
  </Step>

  <Step title="Request Creation">
    Contact your PLai Framework administrator or account manager:

    **Provide:**

    * Requirements document
    * Use case description
    * Compliance regulations
    * Timeline needs
    * Testing requirements

    **Methods:**

    * Support ticket
    * Account manager email
    * Admin dashboard request
    * API (for enterprise customers)

    <Info>
      Guardrail creation typically takes 2-5 business days depending on complexity and testing requirements.
    </Info>
  </Step>

  <Step title="Review and Testing">
    Once created, thoroughly test the guardrail:

    **Test Scenarios:**

    * Positive cases (should trigger)
    * Negative cases (should not trigger)
    * Edge cases
    * Performance impact
    * False positives
    * False negatives

    **Testing Checklist:**

    ```
    ✅ Blocks/masks intended content
    ✅ Allows safe content through
    ✅ No excessive false positives
    ✅ Acceptable latency impact
    ✅ Works across different phrasings
    ✅ Handles edge cases appropriately
    ✅ Logs triggers correctly
    ```
  </Step>

  <Step title="Apply to Agents">
    Add the guardrail to your agents through:

    * Agent dashboard UI
    * API endpoint
    * Bulk application (multiple agents)

    See "Applying Guardrails" section below for details.
  </Step>

  <Step title="Monitor and Refine">
    After deployment:

    * Monitor trigger rates
    * Review blocked content
    * Check for false positives
    * Adjust configuration as needed
    * Collect user feedback
  </Step>
</Steps>

***

## Applying Guardrails to Agents

### Via Dashboard UI

<Steps>
  <Step title="Navigate to Guardrails Section">
    1. Open your **Agent Dashboard**
    2. Select the **Guardrails** tab
    3. Select the guardrail(s) you want to apply.
  </Step>

  <Step title="Configure Settings">
    For each selected guardrail:

    **Direction:**

    * ◉ INPUT only
    * ◯ OUTPUT only
    * ◯ Both INPUT and OUTPUT

    **Priority** (if multiple guardrails):

    * Higher priority guardrails run first
    * Range: 1 (highest) to 10 (lowest)
  </Step>
</Steps>

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Best Practices" icon="star" href="/agents/guardrails/best-practices">
    Learn expert tips for optimal guardrail implementation
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/guardrails">
    Explore the complete Guardrails API documentation
  </Card>

  <Card title="Overview" icon="book-open" href="/agents/guardrails/overview">
    Review Guardrails concepts and capabilities
  </Card>

  <Card title="Analytics" icon="chart-line" href="/agents/analytics/overview">
    Monitor guardrail effectiveness and performance
  </Card>
</CardGroup>

***

## Additional Resources

<AccordionGroup>
  <Accordion title="Amazon Bedrock Guardrails Documentation">
    Guardrails in PLai Framework are powered by Amazon Bedrock Guardrails. For technical details on the underlying service:

    * [AWS Bedrock Guardrails Overview](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html)
    * Detection capabilities and models
    * PII types supported
    * Language support
    * Technical specifications
  </Accordion>

  <Accordion title="Compliance Resources">
    **GDPR Compliance:**

    * PII masking for EU users
    * Data protection requirements
    * Right to be forgotten

    **HIPAA Compliance:**

    * PHI protection requirements
    * HIPAA Security Rule
    * HIPAA Privacy Rule

    **PCI-DSS Compliance:**

    * Payment card data protection
    * Cardholder data environment
    * Security assessment procedures
  </Accordion>

  <Accordion title="Support and Assistance">
    **For custom guardrail creation:**

    * Contact your account manager
    * Submit detailed requirements document
    * Expected turnaround: 2-5 business days
  </Accordion>
</AccordionGroup>