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

# Overview

Guardrails automatically check your LLM's inputs and outputs to keep them safe, compliant, and high-quality. Think of them as safety checks that run before content reaches your users or your language model.

# How Guardrails Work

<Steps>
  <Step title="Send content for validation" icon="paper-plane">
    This could be a user message before it reaches your LLM, or LLM-generated content before it reaches your users.
  </Step>

  <Step title="Guardrail analyzes the content" icon="magnifying-glass">
    This can take up to 3 seconds.
  </Step>

  <Step title="Receive validation result" icon="clipboard-check">
    The guardrail returns a status (pass, fail, or unsure), confidence score, and reason for the decision.
  </Step>

  <Step title="Make decisions based on results" icon="code-branch">
    Based on the result, you decide whether to allow the content, flag it for human review, or regenerate with different parameters.
  </Step>

  <Step title="Monitor in your dashboard" icon="chart-line">
    Every validation automatically creates a complete observation in ABV, capturing the input, result, configuration, timing, and token usage.
  </Step>
</Steps>

## Available Guardrails

Guardrails come in two categories based on how they work.

**LLM-Powered Guardrails** can understand context and nuance, but about 1-3 seconds per check:

<AccordionGroup>
  <Accordion title="Toxic Language" icon="message-slash">
    Detects hate speech, threats, insults, and harmful content that could damage your community or poison your LLM's context. Use this when you need to understand intent and tone, not just keywords.

    [Learn more →](/developer/guardrails/available/toxic-language)
  </Accordion>

  <Accordion title="Biased Language" icon="scale-unbalanced">
    Identifies stereotypes, discriminatory assumptions, and coded language that could harm your brand or violate compliance requirements. Essential for HR content, job postings, and customer-facing communications.

    [Learn more →](/developer/guardrails/available/biased-language)
  </Accordion>
</AccordionGroup>

**Rule-Based Guardrails** use deterministic logic for instant results in under 10 milliseconds:

<AccordionGroup>
  <Accordion title="Contains String" icon="text">
    Validates presence or absence of specific text—perfect for ensuring legal disclaimers appear in LLM outputs or blocking sensitive information like passwords and credit card numbers in user inputs.

    [Learn more →](/developer/guardrails/available/contains-string)
  </Accordion>

  <Accordion title="Valid JSON" icon="brackets-curly">
    Ensures LLM's structured outputs are properly formatted and match your expected schema, preventing application errors from malformed data.

    [Learn more →](/developer/guardrails/available/valid-json)
  </Accordion>
</AccordionGroup>

# Integrations

Guardrails integrate with ABV's core features:

<AccordionGroup>
  <Accordion title="Automatic Observability" icon="eye">
    Every guardrail check creates an observation in your traces. Monitor patterns, analyze confidence distributions, tune sensitivity settings based on real data.
  </Accordion>

  <Accordion title="SDK Integration" icon="code">
    Guardrails come with the [Python SDK](/developer/sdks/python/overview) and [JS/TS SDK](/developer/sdks/js-ts/overview). Native async support, type safety, and framework integration included.
  </Accordion>

  <Accordion title="Evaluation Tracking" icon="chart-bar">
    Track guardrail performance using [Evaluations](/developer/evaluations/overview). Measure false positive rates, analyze failure patterns, and optimize your validation strategy using the wizard.
  </Accordion>

  <Accordion title="Metrics Dashboard" icon="gauge">
    Monitor guardrail status in the [Metrics Dashboard](/developer/platform/metrics/overview). See failure rates by type, track costs, analyze latency, and identify optimization opportunities.
  </Accordion>
</AccordionGroup>

# Next Steps

Ready to implement guardrails in your application?

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/developer/guardrails/quickstart">
    Get up and running with your first guardrail in under 5 minutes
  </Card>

  <Card title="Core Concepts" icon="book" href="/developer/guardrails/concepts">
    Understand sensitivity levels, confidence scores, and validation strategies
  </Card>

  <Card title="Best Practices" icon="star" href="/developer/guardrails/best-practices">
    Learn optimal patterns for layering and combining guardrails
  </Card>

  <Card title="Security Guardrails" icon="shield" href="/developer/guardrails/llm-security-guardrails-overview">
    Explore security-focused guardrails for protecting against attacks
  </Card>
</CardGroup>