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

# Overview

> Learn about Guardion's AI runtime guardrails for safe and reliable AI systems.

# AI Runtime Guardrails

Guardion provides multiple guardrails to protect your AI systems from various threats and ensure safe, reliable outputs.

## Available Guardrails

<CardGroup cols={2}>
  <Card title="Prompt Security" icon="shield-check" href="/injection">
    Detect and block prompt injections, jailbreaks, and context hijacking attempts. Backed by ModernGuard models.
  </Card>

  <Card title="Data Protection" icon="user-lock" href="/pii">
    Identify and control exposure of personally identifiable information across inputs and outputs.
  </Card>

  <Card title="Content Moderation" icon="filter-circle-xmark" href="/moderation">
    Classify and filter unsafe or policy-violating content across multiple safety categories.
  </Card>

  <Card title="Grounding" icon="brain-circuit" href="/grounding">
    Detect hallucinations and verify that AI responses are grounded in provided context, documents, or tool results.
  </Card>

  <Card title="Custom" icon="sliders" href="/custom">
    Define your own safety criteria and policies for domain-specific AI content evaluation.
  </Card>
</CardGroup>

## Guardrail Configuration

Each guardrail can be configured with custom thresholds and policies through the Guardion dashboard or API.

<AccordionGroup>
  <Accordion title="How do guardrails work?">
    Guardion's guardrails use advanced machine learning models to analyze inputs and outputs, identifying patterns that match known attack vectors, unsafe content, or ungrounded claims.
  </Accordion>

  <Accordion title="Can I customize detection thresholds?">
    Yes, each guardrail allows for custom confidence thresholds to balance security with usability for your specific use case.
  </Accordion>

  <Accordion title="How do I implement guardrails?">
    Guardrails can be implemented via our API or SDK. Check our Quickstart guide for implementation details.
  </Accordion>
</AccordionGroup>

Need help configuring your guardrails? [Contact our Support Team](mailto:support@guardion.ai).