Overview
The Rules Engine automates comment moderation and responses using AI-powered rules or traditional keyword-based conditions. Choose between letting AI understand context and intent, or create specific keyword rules for exact scenarios.Rules execute automatically without manual review, saving hours of repetitive
work while maintaining brand consistency.
Rule Types
- LLM Rules (Recommended)
- Category Rules (Recommended)
- Traditional Rules
AI-powered rules that understand context, intent, and nuance rather than exact keywords.How it works:
- Describe what you want in plain English
- AI analyzes comment meaning and context
- Handles variations and edge cases automatically
- Learns from your brand voice and guidelines
“Reply to any comment asking about pricing with product information”The AI understands “how much?”, “what’s the cost”, “price check”, etc. without needing to list every variation.
LLM rules are more flexible and require less maintenance than traditional keyword rules.
Accessing Rules
1
Navigate to Rules
Click Rules in the sidebar navigation
2
Create New Rule
Click + New Rule and choose LLM or Traditional rule type
3
Configure & Activate
Set your conditions and actions, then toggle to enable
Rule Configuration
Conditions (When to Trigger)
Conditions (When to Trigger)
Define when the rule should activate:For LLM Rules:
- Describe the scenario in plain English
- Example: “When someone asks about shipping or delivery”
- Select from AI-detected categories:
- Positive, Product Qs, Brand Risk, Negative, Spam, Other
- Example: “When category is Spam” or “When category is Positive”
- Specific keywords (e.g., “price”, “shipping”)
- Phrase matching with AND/OR logic
- Specific usernames
- Follower count thresholds
- Verified or business accounts
- Specific posts or campaigns
- Platform (Instagram vs Facebook)
- Timing conditions
Actions (What Happens)
Actions (What Happens)
Choose what happens when conditions match:Automated Actions:
- Use AI Suggestion - Apply AI-recommended response
- Reply with Template - Send predefined message
- Hide Comment - Remove from public view
- Delete Comment - Remove entirely
- Block User - Prevent future comments
- High-Priority Review - Flag for immediate attention
Common Use Cases
Hide Spam
Automatically hide spam comments using category rules. No keyword management needed.
Engage with Positive Comments
Auto-reply to positive comments to build community and show appreciation.
FAQ Automation
Use LLM rules to automatically answer common questions about pricing, shipping, products, etc.
Creating a Rule
1
Name Your Rule
Click + New Rule and give it a descriptive name (e.g., “Auto-reply to shipping questions”)
2
Choose Rule Type
Select LLM Rule, Category Rule, or Traditional Rule
3
Set Conditions
For LLM Rules: Describe the scenario in plain EnglishFor Category Rules: Select categories (Spam, Positive, Product Qs, etc.)For Traditional Rules: Add specific keywords, user filters, or context conditions
4
Define Action
Choose what happens when the rule triggers: - Use AI suggestion, reply with
template, hide, delete, or flag for review
5
Test & Activate
Test with sample comments, then toggle the rule to Active
Start with manual review mode to validate accuracy before enabling auto-apply.
Rule Management
Edit Rules
Edit Rules
(1) Click on any rule to open its settings(2) Modify conditions, actions, or status(3) Click Save to apply changes immediately
Reorder Priority
Reorder Priority
Rules execute in order from top to bottom:(1) Drag and drop rules to change execution order(2) Specific rules should be higher priority than general rules(3) Once a rule matches, lower priority rules may be skipped
Higher priority rules are evaluated first, so order matters.
Monitor Performance
Monitor Performance
Track rule effectiveness in the dashboard:
- Match Count - How many times the rule has triggered
- Status - Auto-apply or manual review mode
- Toggle - Quick enable/disable switch
AI Fallback
What is AI Fallback?
What is AI Fallback?
Controls what happens to comments that don’t match any rules.When Enabled:
- Comments automatically get AI-suggested responses applied
- Reduces manual review queue
- Maintains fast response times
- All unmatched comments require manual review
- Maximum control over every response
- Best for strict brand guidelines
Best Practices
Start with LLM Rules
LLM rules are more flexible and require less maintenance. Use them for most scenarios unless you need exact keyword control.
Test Before Auto-Apply
Start new rules in manual review mode. Once you verify accuracy, switch to
auto-apply for automation.
Use Specific Rules First
Order matters. Put specific rules at the top so they execute before general
catch-all rules.
Monitor Performance
Check match counts. Adjust rules that are triggering too often or not enough.
Example Rules
Category Rule: Hide Spam
Category Rule: Hide Spam
Rule Type: CategoryCondition:Automatically hides all spam comments detected by AI. No keyword management needed.
LLM Rule: Respond to Emoji-Based Positive Comments
LLM Rule: Respond to Emoji-Based Positive Comments
Rule Type: LLMCondition: “Reply to positive comments that include emojis like fire, heart eyes, or celebration”Action: Use AI SuggestionThe AI understands emoji context and sentiment to craft appropriate responses that match the enthusiasm.
LLM Rule: FAQ Automation
LLM Rule: FAQ Automation
Rule Type: LLM (Recommended)Condition: “Reply to any comment asking about pricing, shipping, or product availability”Action: Use AI SuggestionThe AI understands all variations like “how much?”, “when will it ship?”, “in stock?”, etc.
Traditional Rule: Block Specific Accounts
Traditional Rule: Block Specific Accounts
Rule Type: TraditionalCondition:Automatically blocks specific problematic accounts from commenting on your posts.

