Overview
AI support chatbots face unique moderation challenges:- Users may attempt to manipulate the AI into providing harmful advice or bypassing guidelines
- AI responses might inadvertently share sensitive information or give inappropriate recommendations
- Long conversations require maintaining context while checking each new message
- Repeat offenders need to be identified across multiple support sessions
Only the last message is evaluated for violations. When you send a conversation with multiple messages, White Circle evaluates only the final message against your policies. Previous messages provide context but are not flagged. This means you should send user messages and AI responses separately for individual moderation.
Prerequisites
Before you begin, make sure you have:- A White Circle account with access to the dashboard
- A working AI chatbot (this guide uses examples with OpenAI’s API, but works with any provider)
Architecture
Here’s how White Circle fits into your support chatbot architecture:Step 1: Create an API Key
Create an API key to authenticate your requests to White Circle.- Go to the API Keys page
- Click Create API Key
- Name it something descriptive like
support-chatbot-production - Copy the key and store it securely — you won’t be able to see it again
Step 2: Create Policies
Create policies that define what content should be flagged. For a support chatbot, you’ll need policies to protect users and maintain safe conversations. Go to the Policies page and create the following:Adult Content Policy
Adult Content Policy
Prevents explicit sexual content in support conversations.
Prompt Injection Policy
Prompt Injection Policy
Detects manipulation attempts targeting the AI system.
CSAM Policy
CSAM Policy
Detects and blocks child sexual abuse material references.
Harm to Others Policy
Harm to Others Policy
Prevents threats of violence and harm.
Step 3: Create a Deployment
Create a deployment that groups your policies together.- Go to the Deployments page
- Click Add Deployment
- Name it
support-chatbot-production - Select all the policies you created above
- Save the deployment and copy the Deployment ID
Consider creating separate deployments for different environments:
support-chatbot-development— for dev and QA testingsupport-chatbot-production— for live traffic
Step 4: Integrate the API
Now integrate White Circle into your chatbot. Below is a complete implementation example.Configuration
First, set up your configuration and White Circle client:Main Chatbot Logic
Here’s the core chatbot implementation with White Circle integration:API Endpoint
Expose the chatbot as an API endpoint in your web framework:Step 5: Add User Risk Scoring
Use White Circle’s Radar feature to identify users with a history of violations. This helps you proactively protect your support agents.Step 6: Set Up Slack Alerts
Get instant Slack notifications for critical policy violations. You can configure alerts for specific policies only — for example, receive notifications for abuse or jailbreak attempts while skipping less urgent violations.- Go to Integrations → Slack
- Click Connect to Slack and authorize the app
- Select a channel (e.g.,
#support-alerts) - Select only critical policies — choose high-priority policies like “Harm to Others” or “CSAM” to avoid alert fatigue
- Save the integration
For private channels, first invite the bot with
/invite @White Circle NotificationsStep 7: Track Metrics
Beyond moderation, use White Circle’s metrics to gain insights into your support conversations. Create metrics on the Metrics page:User Refunds
User Refunds
Track when users request refunds or monetary compensation.
User Praise
User Praise
Capture genuine expressions of gratitude and positive feedback.
Escalation Request
Escalation Request
Detect when users want to speak with a human agent.
Best Practices
Always check both directions
Always check both directions
Check user messages and AI responses. Users can manipulate AI into generating harmful content even when their own messages appear innocent.
Use context merging for efficiency
Use context merging for efficiency
For multi-turn conversations, use
include_context: true with an external_session_id. This reduces payload size and ensures White Circle has full conversation context.Include user metadata consistently
Include user metadata consistently
Always include
metadata.user.id and metadata.user.email to enable risk scoring. This builds a violation history that helps identify repeat offenders.Moderate image attachments
Moderate image attachments
If your chatbot accepts image uploads (e.g., screenshots, product photos), use the Artifact Check endpoint to moderate them before processing:This checks the image independently against your policies before it enters the conversation.
Handle flagged AI responses with fallbacks
Handle flagged AI responses with fallbacks
When White Circle flags an AI response as harmful, have a fallback strategy ready:
- Return a safe, pre-written response that offers to help differently
- Retry with a more capable model (e.g., upgrade from gpt-5-mini to gpt-5.2)
- Escalate to a human agent for sensitive topics
- Log the incident for later review and model fine-tuning
Start with shadow mode
Start with shadow mode
Enable shadow mode on new policies to test them without blocking content. Review flagged sessions in the dashboard before enabling enforcement.
Log flagged content for review
Log flagged content for review
Store flagged sessions and the policies they violated. This helps you:
- Identify false positives and tune policies
- Build training data for your AI model
- Document incidents for compliance
Example Conversation Flow
Here’s how a typical moderated conversation looks:Next Steps
View Sessions Dashboard
Monitor flagged sessions and review moderation decisions
Artifact Moderation
Moderate image uploads and file attachments
Risk Scoring
Deep dive into user risk assessment with Radar
Webhooks
Set up custom integrations with webhook events
