Skip to main content
Custom security rules let you go beyond built-in detection. Define policies that match your exact business requirements — block specific topics, protect entity names, enforce natural-language constraints, and more.

​
Policy Types

PromptGuard supports seven policy types. Each policy has a type, an action (block, redact, flag, allow), and either rules (condition-based) or a system prompt (LLM-judged).
TypeHow it worksWhen to use
input_filterEvaluates rules against incoming promptsBlock injection patterns, forbidden terms
output_filterEvaluates rules against LLM responsesRedact PII in output, block toxic content
topic_filterLLM judge evaluates a natural-language descriptionKeep conversations on-topic
llm_guardLLM judge evaluates a natural-language descriptionCustom business logic too complex for regex
entity_blocklistPattern matching on both input and outputBlock specific names, terms, or identifiers
rate_limitRate-based enforcementThrottle requests per time window
customFlexible rule-based evaluationAnything else

​
Creating Policies

​
Via Dashboard

  1. Navigate to Dashboard → [Project] → Policies
  2. Click “Create Policy”
  3. Select the policy type
  4. Configure rules or system prompt description
  5. Click “Create Policy”

​
Via API

curl -X POST https://api.promptguard.co/api/v1/policies \
  -H "X-API-Key: $PROMPTGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Block Competitor Mentions",
    "policy_type": "entity_blocklist",
    "is_active": true,
    "rules": [
      {
        "condition": "contains_text_any",
        "value": "Acme Corp|Globex|Initech",
        "action": "block"
      }
    ]
  }'

​
Rule Conditions

Rule-based policies (input_filter, output_filter, entity_blocklist, custom) use condition/value/action triples:
ConditionDescriptionExample Value
contains_piiMatches PII entities (email, SSN, etc.)true
prompt_injectionMatches injection patternstrue
contains_textExact substring matchconfidential
contains_text_anyMatch any of pipe-separated termspassword|secret|credential
natural_languageLLM-judged conditionRequest asks about pricing

​
Actions

Each rule specifies what happens when the condition matches:
ActionBehavior
blockReject the request entirely (HTTP 400)
redactRemove or mask the matched content
flagAllow the request but log the violation
allowExplicitly permit (useful for allowlist rules)

​
Topic Filter

Topic filters use natural language to define what a conversation should be about. An LLM judge evaluates each request against your description and blocks off-topic queries. 
curl -X POST https://api.promptguard.co/api/v1/policies \
  -H "X-API-Key: $PROMPTGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Support Bot Scope",
    "policy_type": "topic_filter",
    "is_active": true,
    "system_prompt_details": "This bot handles Azure cloud infrastructure support only. Block questions about billing, HR, competitor products, or anything unrelated to Azure services, networking, and deployment."
  }'
When to use topic_filter vs. input_filter:
  • Use topic_filter when the boundary is semantic (“stay on topic”)
  • Use input_filter with contains_text rules when the boundary is lexical (“block this exact word”)

​
LLM Guard

LLM Guard policies define custom business rules in natural language, evaluated by an LLM judge. Use these for constraints that are too nuanced for pattern matching. 
curl -X POST https://api.promptguard.co/api/v1/policies \
  -H "X-API-Key: $PROMPTGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "No Financial Advice",
    "policy_type": "llm_guard",
    "is_active": true,
    "system_prompt_details": "Block any response that provides specific financial advice, stock recommendations, or investment guidance. General financial education is acceptable."
  }'

​
Entity Blocklist

Entity blocklists protect specific names, terms, or identifiers from appearing in prompts or responses. They evaluate against both input and output. 
curl -X POST https://api.promptguard.co/api/v1/policies \
  -H "X-API-Key: $PROMPTGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Client Name Protection",
    "policy_type": "entity_blocklist",
    "is_active": true,
    "rules": [
      {
        "condition": "contains_text_any",
        "value": "Acuity Analytics|John Smith|Project Phoenix",
        "action": "redact"
      }
    ]
  }'
The contains_text_any condition accepts pipe-separated (|) terms and matches any of them. This is more efficient than creating multiple contains_text rules.

​
Policy Presets

PromptGuard also provides six use-case-specific presets that combine multiple built-in detectors:
PresetOptimized For
DefaultBalanced security for general AI apps
Support BotStrict PII and exfiltration protection
Code AssistantInjection detection, API key/secret scanning
RAG SystemMaximum security, enhanced leak prevention
Data AnalysisStrict PII, SSN/DOB detection
Creative WritingNuanced content filtering, higher thresholds
See Policy Presets for detailed configuration.

​
Feature Comparison by Tier

FeatureFreeProScale
Policy Presets✅ Default✅ All Presets✅ All Presets
Custom Policies (rules-based)✅ 5 policies✅ 25 policies✅ Unlimited
Topic Filter❌✅✅
LLM Guard❌✅✅
Entity Blocklist✅✅✅
Regex Detection✅ 70-80%✅ 70-80%✅ 70-80%
ML Detection❌✅ ~95%✅ ~95%

​
Next Steps

Policy Presets

Pre-configured security policies

Threat Detection

Built-in detection capabilities

Observability

Trace policy decisions and debug

API Reference

Full policy management API