> ## Documentation Index > Fetch the complete documentation index at: https://docs.continum.co/llms.txt > Use this file to discover all available pages before exploring further. # Presets & Compliance > Automatic detection configuration with presets and compliance frameworks ## Overview Presets automatically configure the right detection types for your use case. Instead of manually selecting sandbox types, specify a preset and Continum will enable the appropriate checks. ## Available Presets ### customer-support For customer support bots, help desks, and Q\&A systems. ```typescript theme={null} { preset: 'customer-support' } ``` **Automatically enables:** * PII Detection * Content Policy * Bias Detection * Hallucination Detection **Best for:** Chat support, help desk automation, FAQ bots *** ### legal-ai For legal research, document analysis, and compliance tools. ```typescript theme={null} { preset: 'legal-ai' } ``` **Automatically enables:** * PII Detection * Legal Compliance * Hallucination Detection * Bias Detection * Citation Verification **Best for:** Legal research, contract analysis, compliance tools *** ### fintech-ai For financial services, trading, and investment advice. ```typescript theme={null} { preset: 'fintech-ai' } ``` **Automatically enables:** * PII Detection * Financial Compliance * Security Audit * Bias Detection * Hallucination Detection **Best for:** Trading bots, financial advisors, investment analysis *** ### healthcare-ai For medical advice, diagnosis, and healthcare applications. ```typescript theme={null} { preset: 'healthcare-ai' } ``` **Automatically enables:** * PII Detection (including health data) * Content Policy * Bias Detection * Hallucination Detection * Medical Compliance **Best for:** Medical chatbots, diagnosis tools, health records *** ### coding-assistant For code generation, review, and development tools. ```typescript theme={null} { preset: 'coding-assistant' } ``` **Automatically enables:** * Security Audit * Supply Chain Integrity * Prompt Injection * Secret Leak Detection **Best for:** Code generation, code review, IDE assistants *** ### agent For AI agents with tool use and autonomous actions. ```typescript theme={null} { preset: 'agent' } ``` **Automatically enables:** * Agent Safety * Prompt Injection * Data Exfiltration * Security Audit * Scope Creep Detection **Best for:** Autonomous agents, tool-using AI, multi-step workflows *** ### content-generation For writing, marketing, and creative content. ```typescript theme={null} { preset: 'content-generation' } ``` **Automatically enables:** * Content Policy * Bias Detection * Hallucination Detection * Copyright Compliance **Best for:** Content writing, marketing copy, creative tools *** ### internal-tool For internal team productivity and automation. ```typescript theme={null} { preset: 'internal-tool' } ``` **Automatically enables:** * PII Detection * Security Audit * Data Exfiltration **Best for:** Internal chatbots, productivity tools, automation *** ### data-pipeline For ETL, data processing, and analysis. ```typescript theme={null} { preset: 'data-pipeline' } ``` **Automatically enables:** * PII Detection * Data Exfiltration * Security Audit **Best for:** Data processing, ETL pipelines, analytics *** ### education-ai For tutoring, learning, and training applications. ```typescript theme={null} { preset: 'education-ai' } ``` **Automatically enables:** * Content Policy * Bias Detection * Hallucination Detection * Age-Appropriate Content **Best for:** Tutoring bots, learning platforms, training tools ## Compliance Frameworks Specify compliance frameworks to automatically enable required checks: ```typescript theme={null} { preset: 'customer-support', comply: ['GDPR', 'SOC2', 'HIPAA'] } ``` ### Supported Frameworks | Framework | Description | Automatically Enables | | ------------- | ------------------------- | -------------------------------------------------- | | `GDPR` | EU data protection | PII detection, data minimization, consent tracking | | `CCPA` | California privacy | PII detection, data rights, opt-out mechanisms | | `HIPAA` | US healthcare data | Health data detection, access controls, audit logs | | `SOC2` | Security & availability | Security audit, access controls, monitoring | | `ISO_27001` | Information security | Security audit, risk management, incident response | | `EU_AI_ACT` | EU AI regulation | Bias detection, transparency, human oversight | | `FINRA` | US financial services | Financial compliance, record keeping, supervision | | `PCI_DSS` | Payment card security | Security audit, encryption, access controls | | `NIST_AI_RMF` | AI risk management | Risk assessment, bias detection, transparency | | `FCA` | UK financial conduct | Financial compliance, consumer protection | | `PDPA` | Singapore data protection | PII detection, consent, data rights | | `PIPEDA` | Canada privacy | PII detection, consent, accountability | | `UK_DPA_2018` | UK data protection | PII detection, data rights, lawful basis | ## Combining Presets and Frameworks Presets and frameworks work together to provide comprehensive coverage: ```typescript theme={null} import { continum } from '@continum/sdk'; continum.configure({ apiKey: process.env.CONTINUM_API_KEY!, preset: 'fintech-ai', // Base detection types comply: ['FINRA', 'SOC2'] // Additional compliance checks }); ``` This configuration will enable: * All checks from `fintech-ai` preset * Additional checks required by FINRA and SOC2 ## Custom Detection Types For advanced use cases, you can specify detection types directly: ```typescript theme={null} import { continum } from '@continum/sdk'; continum.configure({ apiKey: process.env.CONTINUM_API_KEY!, sandbox: { types: [ 'PII_DETECTION', 'SECURITY_AUDIT', 'PROMPT_INJECTION', 'CUSTOM' ], customRules: ['CUSTOM_RULE_1', 'CUSTOM_RULE_2'] } }); ``` **Available detection types:** * `PII_DETECTION` - Personal information * `BIAS_DETECTION` - Discrimination and bias * `SECURITY_AUDIT` - Code injection, vulnerabilities * `PROMPT_INJECTION` - Jailbreaks, goal hijacking * `DATA_EXFILTRATION` - Data leaks, cross-user leaks * `AGENT_SAFETY` - Irreversible actions, scope creep * `HALLUCINATION_DETECTION` - False information * `CONTENT_POLICY` - Harmful content * `FINANCIAL_COMPLIANCE` - Financial regulations * `LEGAL_COMPLIANCE` - Legal requirements * `MULTI_TURN_ATTACK` - Multi-step attacks * `SUPPLY_CHAIN_INTEGRITY` - Dependency security * `FULL_SPECTRUM` - All detection types * `CUSTOM` - Custom rules ## Environment-Specific Configuration Use different presets for different environments: ```typescript theme={null} import { continum } from '@continum/sdk'; const preset = process.env.NODE_ENV === 'production' ? 'customer-support' : 'internal-tool'; continum.configure({ apiKey: process.env.CONTINUM_API_KEY!, preset, environment: process.env.NODE_ENV as 'production' | 'staging' | 'development' }); ``` ## Best Practices ### 1. Start with a Preset Always start with a preset that matches your use case: ```typescript theme={null} // ✅ Good { preset: 'customer-support', comply: ['GDPR'] } // ❌ Avoid (unless you have specific requirements) { sandbox: { types: ['PII_DETECTION', 'BIAS_DETECTION', ...] } } ``` ### 2. Add Compliance Frameworks Specify all applicable frameworks: ```typescript theme={null} { preset: 'healthcare-ai', comply: ['HIPAA', 'GDPR', 'SOC2'] } ``` ### 3. Use Environment Variables Keep configuration flexible: ```typescript theme={null} const frameworks = process.env.COMPLIANCE_FRAMEWORKS?.split(',') || []; continum.configure({ apiKey: process.env.CONTINUM_API_KEY!, preset: 'customer-support', comply: frameworks as ComplianceFramework[] }); ``` ### 4. Use Environment Variables Keep configuration flexible: ```typescript theme={null} const frameworks = process.env.COMPLIANCE_FRAMEWORKS?.split(',') || []; continum.configure({ apiKey: process.env.CONTINUM_API_KEY!, preset: 'customer-support', comply: frameworks as ComplianceFramework[] }); ``` ## Next Steps Set up real-time alerts for violations Use blocking mode for high-risk scenarios React to specific violations in code Advanced SDK configuration