Policy Presets

​

Available Presets

​

Default (Recommended)

• Security Level: Balanced protection
• PII Detection: Moderate
• Injection Detection: Moderate
• Exfiltration Detection: Moderate
• Output Safety: Moderate
• Use Cases: Most production applications, general business use

• Moderate prompt injection detection
• Standard PII redaction
• Balanced security vs usability
• Industry-standard protection

​

Support Bot

• Security Level: Enhanced for customer interactions
• PII Detection: Strict
• Injection Detection: Moderate
• Exfiltration Detection: Strict
• Output Safety: Moderate
• Use Cases: Customer service, help desks, support systems

• Strict PII protection (critical for customer data)
• Enhanced exfiltration prevention
• Custom patterns for password/account queries
• Blocked domains for admin/internal access

​

Code Assistant

• Security Level: Optimized for development tools
• PII Detection: Moderate
• Injection Detection: Strict
• Exfiltration Detection: Strict
• Output Safety: Permissive
• Use Cases: IDEs, code generation, development tools

• Strict injection detection (prevents code injection attacks)
• API key and secret detection patterns
• Allowed domains for GitHub, Stack Overflow, docs
• Permissive output safety (allows code generation)

​

RAG System

• Security Level: Maximum security for document-based AI
• PII Detection: Strict
• Injection Detection: Strict
• Exfiltration Detection: Strict
• Output Safety: Moderate
• Use Cases: Knowledge bases, document Q&A, enterprise RAG

• Maximum protection across all threat types
• Custom patterns for confidential/proprietary content
• Blocked domains for internal/staging systems
• Enhanced data leak prevention

​

Data Analysis

• Security Level: Strict PII protection
• PII Detection: Strict
• Injection Detection: Strict
• Exfiltration Detection: Strict
• Output Safety: Moderate
• Use Cases: Analytics, data pipelines, business intelligence

• Strict PII detection (SSN, DOB patterns)
• Enhanced data protection
• Blocked external/public domains
• Comprehensive exfiltration prevention

​

Creative Writing

• Security Level: Nuanced content filtering
• PII Detection: Moderate
• Injection Detection: Moderate
• Exfiltration Detection: Moderate
• Output Safety: Strict
• Use Cases: Content generation, writing tools, creative applications

• ML-based toxicity detection enabled
• Higher toxicity threshold (0.8) for creative content
• Category filtering (hate, sexual, violence)
• Strict output safety for content moderation

​

Choosing the Right Preset

​

Decision Matrix

​

Recommendation Flow

​

Configuring Presets

​

Via Dashboard

1. Access Project Settings
   • Login to app.promptguard.co
   • Navigate to Projects > [Your Project] > Overview
   • Find the “Policy Preset” section
2. Choose Preset
   • Review the available preset options
   • Consider your use case and requirements
   • Select the appropriate preset from the dropdown
3. Test Configuration
   • Make test requests to validate the preset
   • Monitor security events in the dashboard
   • Adjust with custom policies if needed

​

Via API

# Update project preset (dashboard API - requires session auth)
curl -X PUT https://api.promptguard.co/dashboard/presets/projects/{project_id}/preset \
  -H "Cookie: session=YOUR_SESSION_COOKIE" \
  -H "Content-Type: application/json" \
  -d '{
    "preset_name": "default"
  }'

# List available presets (developer API - requires API key)
curl https://api.promptguard.co/api/v1/presets \
  -H "X-API-Key: YOUR_PROMPTGUARD_API_KEY"

# Get specific preset details
curl https://api.promptguard.co/api/v1/presets/default \
  -H "X-API-Key: YOUR_PROMPTGUARD_API_KEY"

​

Preset Comparison

​

Detection Capabilities

​

Performance Impact

​

Customizing Presets

​

Adding Custom Policies

1. Navigate to Projects > [Your Project] > Policies
2. Click “Create Policy”
3. Define custom rules that complement your preset
4. Custom policies apply in addition to preset rules

​

Preset + Custom Policies

# Example: Using Default preset + custom policy for specific patterns
# 1. Set preset to "default" via dashboard
# 2. Create custom policy via dashboard or API
curl -X POST https://api.promptguard.co/dashboard/policies \
  -H "Cookie: session=YOUR_SESSION_COOKIE" \
  -H "Content-Type: application/json" \
  -d '{
    "project_id": "your-project-id",
    "name": "Block Specific Terms",
    "rules": [
      {
        "pattern": "confidential",
        "action": "block"
      }
    ]
  }'

​

Monitoring Preset Performance

​

Key Metrics to Track

1. Security Events
   • Track blocked requests by type
   • Monitor threat patterns
   • Validate detection accuracy
2. False Positive Rate
   • Monitor legitimate requests being blocked
   • Adjust with custom policies if needed
   • Target: 1% for most presets
3. Performance Impact
   • Measure latency overhead
   • Track error rates
   • Monitor user experience

​

Dashboard Views

• Projects > [Your Project] > Analytics
• Filter by time range and security events
• Compare metrics across different configurations
• Export data for detailed analysis

​

Best Practices

​

Development Workflow

1. Start with Default: Begin with the Default preset for most applications
2. Choose Use-Case Preset: If you have a specific use case, use the matching preset
3. Add Custom Policies: Enhance with custom rules for specific needs
4. Monitor Continuously: Track performance and adjust as needed

​

Preset Transitions

1. Test in Staging: Apply new preset to staging environment first
2. Monitor Metrics: Check security events and false positives for 24-48 hours
3. Gradual Rollout: Use feature flags for gradual production rollout if needed
4. Monitor and Adjust: Watch for issues and fine-tune with custom policies

​

Troubleshooting

​

Next Steps