📊Console Overview

The Console provides a comprehensive interface for managing your content moderation projects. Each project has its own dedicated workspace with six main sections accessible through the sidebar navigation.

🏷️

Schemas

Define content structures that match your application's data model with text and image components.

🤖

Automated

Configure AI-powered moderation with confidence thresholds and subscription management.

👥

Manual

Set up human review workflows with webhook notifications for moderation decisions.

🔑

Tokens

Generate and manage API tokens for authenticating your application's requests.

⚙️

Settings

Manage project settings, billing information, and account preferences.

🚶Step-by-Step Walkthrough

Configure Categories

Start by selecting which types of harmful content you want to detect. Categories are displayed as cards with toggle switches for easy enable/disable functionality.

Available Categories Include:

Sexual Content

Violence & Aggression

Hate Speech

Harassment

Self-Harm & Suicide

And 15+ more...

💡 Pro Tip

Each category shows supported content types (text/image) and provides detailed descriptions to help you make informed decisions about what to enable.

Create Schemas

Define the structure of content you'll be moderating. Schemas act as templates that validate your API requests and ensure consistent data formatting.

Schema Builder Features:

• Visual component editor - Add text and image components with drag-and-drop
• Component validation - Ensure field names and types are correctly configured
• Real-time preview - See how your schema will look in API requests
• Schema management - Edit, duplicate, or delete existing schemas

⚠️ Important

Schema changes affect your API integration. Test thoroughly before deploying schema updates to production environments.

Configure Automated Moderation

Set up AI-powered content analysis with customizable confidence thresholds. The system provides instant moderation decisions based on your configured sensitivity levels.

Confidence Threshold Settings:

0-49%

More lenient - catches obvious violations

Lenient

50-80%

Balanced - good precision and recall

Balanced

81-100%

Strict - high confidence required

Strict

🎯 Best Practice

Start with a balanced threshold (60-70%) and adjust based on your content patterns and false positive rates. Monitor performance through the analytics dashboard.

Set Up Manual Moderation

Configure human review workflows for content that requires nuanced decision-making. Set up webhook notifications to receive real-time updates when moderation decisions are complete.

Webhook Configuration:

• Webhook URL - Endpoint to receive moderation decision notifications
• Secret verification - Secure webhook payload validation
• Test functionality - Verify webhook connectivity before going live

🔗 Integration

Manual moderation works seamlessly with automated moderation. Use both together for comprehensive content review workflows.

Generate API Tokens

Create and manage API tokens for authenticating your application's requests. Each token can be named and revoked independently for security management.

Token Management Features:

• Named tokens - Organize tokens by environment or application
• Instant revocation - Immediately disable compromised tokens

🔒 Security

Store tokens securely in environment variables. Never commit tokens to version control or expose them in client-side code.

💡Console Tips & Best Practices

🎯Start Small, Scale Up

Begin with a few essential categories and a balanced confidence threshold. Monitor performance and gradually expand your configuration based on real usage patterns.

🔄Test Before Production

Use separate projects for development and production environments. Test schema changes, webhook configurations, and threshold adjustments thoroughly before deploying.

📊Monitor Performance

Regularly review your moderation results and adjust thresholds based on false positive rates. Use both automated and manual moderation for optimal coverage.

🔐Security First

Rotate API tokens regularly, use descriptive names for easy management, and immediately revoke any tokens that may have been compromised.

🚀Ready to Get Started?

Now that you understand the Console, you're ready to set up your first moderation project with our comprehensive management interface.

Quick Start Guide

Step-by-step implementation instructions

→

Automated Moderation

Learn about AI-powered content analysis

→

Console Walkthrough