Skip to main content

​
Overview

Guardrails in Bifrost provide enterprise-grade content safety, security validation, and policy enforcement for LLM requests and responses. The system validates inputs and outputs in real-time against your specified policies, ensuring responsible AI deployment with comprehensive protection against harmful content, prompt injection, PII leakage, and policy violations.

​
Key Features

FeatureDescription
Multi-Provider SupportAWS Bedrock, Azure Content Safety, and Patronus AI integration
Dual-Stage ValidationGuard both inputs (prompts) and outputs (responses)
Real-Time ProcessingSynchronous and asynchronous validation modes
Custom PoliciesDefine organization-specific guardrail rules
Automatic RemediationBlock, redact, or modify content based on policy
Comprehensive LoggingDetailed audit trails for compliance

​
Supported Guardrail Providers

Bifrost integrates with leading guardrail providers to offer comprehensive protection:

​
AWS Bedrock Guardrails

Amazon Bedrock Guardrails provides enterprise-grade content filtering and safety features with deep AWS integration. Capabilities:
  • Content Filters: Hate speech, insults, sexual content, violence, misconduct
  • Denied Topics: Block specific topics or categories
  • Word Filters: Custom profanity and sensitive word blocking
  • PII Protection: Detect and redact 50+ PII entity types
  • Contextual Grounding: Verify responses against source documents
  • Prompt Attack Detection: Identify injection and jailbreak attempts
Supported PII Types:
  • Personal identifiers (SSN, passport, driver’s license)
  • Financial information (credit cards, bank accounts)
  • Contact information (email, phone, address)
  • Medical information (health records, insurance)
  • Device identifiers (IP addresses, MAC addresses)

​
Azure Content Safety

Azure AI Content Safety provides multi-modal content moderation powered by Microsoft’s advanced AI models. Capabilities:
  • Severity-Based Filtering: 4-level severity classification (Safe, Low, Medium, High)
  • Multi-Category Detection: Hate, sexual, violence, self-harm content
  • Prompt Shield: Advanced jailbreak and injection detection
  • Groundedness Detection: Verify factual accuracy against sources
  • Protected Material: Detect copyrighted content
  • Custom Categories: Define organization-specific content policies
Detection Categories:
  • Hate and fairness
  • Sexual content
  • Violence
  • Self-harm
  • Profanity
  • Jailbreak attempts

​
Patronus AI

Patronus AI specializes in LLM security and safety with advanced evaluation capabilities. Capabilities:
  • Hallucination Detection: Identify factually incorrect responses
  • PII Detection: Comprehensive personal data identification
  • Toxicity Screening: Multi-language toxic content detection
  • Prompt Injection Defense: Advanced attack pattern recognition
  • Custom Evaluators: Build organization-specific safety checks
  • Real-Time Monitoring: Continuous safety validation
Advanced Features:
  • Context-aware evaluation
  • Multi-turn conversation analysis
  • Custom policy templates
  • Integration with existing safety workflows

​
Configuration

​
AWS Bedrock Guardrails Setup

  • Web UI
  • API
  • config.json
  1. Navigate to Guardrails
    • Open Bifrost UI at http://localhost:8080
    • Go to Enterprise → Guardrails
    • Click Add Guardrail Provider
  2. Configure AWS Bedrock
Required Fields:
  • Provider Name: Descriptive name for this guardrail
  • Provider Type: Select “AWS Bedrock”
  • AWS Region: Your Bedrock region (e.g., us-east-1)
  • Guardrail ID: Your Bedrock guardrail identifier
  • Guardrail Version: Version number or DRAFT
AWS Credentials:
  • Access Key ID: AWS IAM access key
  • Secret Access Key: AWS IAM secret key
  • Session Token: (Optional) For temporary credentials
Validation Settings:
  • Input Validation: Enable for prompt validation
  • Output Validation: Enable for response validation
  • Action on Violation: Block, Log, or Redact
  • Timeout: Max validation time (default: 5s)
  1. Test Configuration
    • Click Test Guardrail
    • Send sample prompt to verify detection
    • Review detection results

​
Azure Content Safety Setup

  • Web UI
  • API
  • config.json
  1. Navigate to Guardrails
    • Go to Enterprise → Guardrails
    • Click Add Guardrail Provider
  2. Configure Azure Content Safety
Required Fields:
  • Provider Name: Descriptive name
  • Provider Type: Select “Azure Content Safety”
  • Endpoint: Your Azure Content Safety endpoint
  • API Key: Azure subscription key
Content Filters:
  • Hate: Enable with severity threshold
  • Sexual: Enable with severity threshold
  • Violence: Enable with severity threshold
  • Self-Harm: Enable with severity threshold
Advanced Features:
  • Prompt Shield: Enable jailbreak detection
  • Groundedness Detection: Enable for factual verification
  • Custom Categories: Define organization policies

​
Patronus AI Setup

  • Web UI
  • API
  • config.json
  1. Navigate to Guardrails
    • Go to Enterprise → Guardrails
    • Click Add Guardrail Provider
  2. Configure Patronus AI
Required Fields:
  • Provider Name: Descriptive name
  • Provider Type: Select “Patronus AI”
  • API Key: Your Patronus API key
  • Environment: Production or Development
Evaluators:
  • Hallucination Detection: Enable factual accuracy checks
  • PII Detection: Enable personal data identification
  • Toxicity: Enable harmful content detection
  • Prompt Injection: Enable attack detection
Custom Policies:
  • Upload organization-specific evaluators
  • Define custom safety criteria

​
Using Guardrails in Requests

​
Attaching Guardrails to API Calls

Once configured, attach guardrails to your LLM requests using custom headers: Single Guardrail: 
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "x-bf-guardrail-id: bedrock-prod-guardrail" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "Help me with this task"
      }
    ]
  }'
Multiple Guardrails (Sequential): 
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "x-bf-guardrail-ids: bedrock-prod-guardrail,azure-content-safety-001" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "Help me with this task"
      }
    ]
  }'
Guardrail Configuration in Request: 
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "Help me with this task"
      }
    ],
    "bifrost_config": {
      "guardrails": {
        "input": ["bedrock-prod-guardrail"],
        "output": ["patronus-ai-001"],
        "async": false
      }
    }
  }'

​
Guardrail Response Handling

Successful Validation (200): 
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1699564800,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'd be happy to help you with your task..."
      },
      "finish_reason": "stop"
    }
  ],
  "extra_fields": {
    "guardrails": {
      "input_validation": {
        "guardrail_id": "bedrock-prod-guardrail",
        "status": "passed",
        "violations": [],
        "processing_time_ms": 245
      },
      "output_validation": {
        "guardrail_id": "patronus-ai-001",
        "status": "passed",
        "violations": [],
        "processing_time_ms": 312
      }
    }
  }
}
Validation Failure - Blocked (446): 
{
  "error": {
    "message": "Request blocked by guardrails",
    "type": "guardrail_violation",
    "code": 446,
    "details": {
      "guardrail_id": "bedrock-prod-guardrail",
      "validation_stage": "input",
      "violations": [
        {
          "type": "PII",
          "category": "SSN",
          "severity": "HIGH",
          "action": "block",
          "text_excerpt": "My SSN is ***-**-****"
        },
        {
          "type": "prompt_injection",
          "severity": "CRITICAL",
          "action": "block",
          "confidence": 0.95
        }
      ],
      "processing_time_ms": 198
    }
  }
}
Validation Warning - Logged (246): 
{
  "id": "chatcmpl-def456",
  "object": "chat.completion",
  "created": 1699564800,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response with redacted content..."
      },
      "finish_reason": "stop"
    }
  ],
  "bifrost_metadata": {
    "guardrails": {
      "output_validation": {
        "guardrail_id": "azure-content-safety-001",
        "status": "warning",
        "violations": [
          {
            "type": "profanity",
            "severity": "LOW",
            "action": "redact",
            "modifications": 2
          }
        ],
        "processing_time_ms": 187
      }
    }
  }
}