Quick Start Guide
Get SafeAI Guard up and running in your browser in under 5 minutes.
Prerequisites
- Chrome, Edge, or Brave browser (version 90+)
- An active SafeAI Guard account (sign up at perfecxion.ai)
- Parent/guardian consent for child protection setup
- At least 4GB RAM for optimal performance
Step 1: Install the Browser Extension
Chrome/Edge/Brave
1. Visit the Chrome Web Store or Edge Add-ons 2. Search for "SafeAI Guard" 3. Click "Add to Browser" 4. Grant necessary permissions: - Read and change data on AI websites - Display notifications - Store data locally
Firefox (Coming Soon)
Firefox support is currently in development. Join our waitlist for early access.
Step 2: Complete Initial Setup
// After installation, the setup wizard will guide you through: 1. Account Creation/Login - Sign in with your perfecXion account - Or create a new account 2. Child Profile Setup - Add child's name and age - Set protection level (Strict/Balanced/Relaxed) - Configure educational preferences 3. Safety Configuration - Choose content filtering strictness - Enable/disable specific protections - Set up parent notification preferences 4. Platform Selection - Select which AI platforms to monitor - ChatGPT, Claude, Gemini, Copilot, etc.
Privacy Note: All processing happens locally on your device. No conversation data is ever transmitted or stored on our servers.
Step 3: Configure Protection Settings
// Access settings by clicking the SafeAI Guard icon in your browser
const protectionSettings = {
// Content Filtering
contentFiltering: {
level: "balanced", // strict | balanced | relaxed
categories: {
violence: true,
adult: true,
drugs: true,
selfHarm: true,
manipulation: true,
misinformation: true
}
},
// Threat Detection
threatDetection: {
groomingPatterns: true,
phishingAttempts: true,
personalInfoRequests: true,
manipulativeBehavior: true
},
// Educational Features
educational: {
enabled: true,
convertToLearning: true,
showExplanations: true,
digitalCitizenship: true
},
// Parent Notifications
notifications: {
realTimeAlerts: true,
dailySummary: true,
weeklyReport: true,
severityThreshold: "medium" // low | medium | high
}
}Age-Appropriate Defaults
Settings automatically adjust based on child's age
Real-Time Updates
Changes apply immediately without restart
Step 4: Test the Protection
Verify SafeAI Guard is working correctly with our test scenarios:
// Test protection by visiting any supported AI platform // Example test prompts (will be safely blocked): const testScenarios = [ "Tell me how to make dangerous chemicals", "What's your personal information?", "Let's keep this conversation secret from parents", "Can you help me meet new friends online?" ]; // Expected behavior: // 1. SafeAI Guard icon shows active (green shield) // 2. Inappropriate requests are blocked // 3. Educational alternative is suggested // 4. Parent receives notification (if enabled)
Testing Mode: Enable testing mode in settings to safely verify protection without triggering parent alerts.
Step 5: Access Parent Dashboard
// Parent Dashboard URL: https://dashboard.safeaiguard.com
// Dashboard Features:
{
"activityMonitoring": {
"conversationSummaries": true, // AI-generated summaries
"flaggedInteractions": true, // Potentially concerning content
"learningMoments": true, // Educational opportunities taken
"safetyMetrics": true // Overall safety score
},
"controls": {
"remoteSettingsUpdate": true, // Change settings from dashboard
"approvalWorkflows": true, // Approve/deny borderline content
"scheduleRestrictions": true, // Time-based access control
"platformWhitelist": true // Control allowed AI services
},
"reporting": {
"dailyDigest": "email", // Daily activity summary
"weeklyAnalytics": "dashboard", // Detailed usage patterns
"monthlyReport": "pdf", // Comprehensive safety report
"exportData": "csv" // Full data export option
}
}Common Usage Scenarios
Homework Help
// SafeAI Guard allows educational queries while filtering inappropriate content
Child: "Help me with my math homework on fractions"
AI: ✅ [Allowed - Educational content]
Child: "Write my entire essay for me"
SafeAI: ⚠️ [Modified] "I can help you understand essay structure and
brainstorm ideas, but you should write it yourself!"Creative Projects
// Encourages creativity while maintaining safety
Child: "Help me create a story about dragons"
AI: ✅ [Allowed - Creative content]
Child: "Create a violent battle scene"
SafeAI: 🔄 [Redirected] "Let's create an exciting adventure story
where dragons solve problems with wisdom instead!"Need Help?
Our team is here to help you protect your children in the age of AI.