Skip to main content

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.

The fastest way to get started is with our interactive CLI: 
npx continum init
This will:
  • Detect your existing framework (Next.js, Fastify, etc.) or help you set one up
  • Guide you through configuration (product type, providers, compliance frameworks)
  • Install the SDK automatically
  • Generate config files and example code
  • Set up real-time alerts (Slack, PagerDuty, Discord, Webhooks)
Starting from scratch? Run npx continum init in an empty folder and it will help you set up a complete project with your chosen framework and Continum built-in!

​
Manual Setup

​
1. Get your API key

Get your API key from the dashboard:
  1. Sign in with GitHub
  2. Create a customer account (Individual or Company)
  3. Generate an API key
  4. Save it securely (you won’t see it again)

​
2. Install the SDK

npm install @continum/sdk

​
3. Basic usage

Wrap any LLM call with protect(): 
import { protect } from '@continum/sdk';
import OpenAI from 'openai';

const openai = new OpenAI();

const response = await protect(
  () => openai.chat.completions.create({
    model: 'gpt-4',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'What is the capital of France?' }
    ]
  }),
  {
    apiKey: process.env.CONTINUM_API_KEY!
  },
  {
    preset: 'customer-support',
    comply: ['GDPR', 'SOC2']
  }
);

console.log(response.choices[0].message.content);
For production, configure once and use everywhere: 
import { continum } from '@continum/sdk';

continum.configure({
  apiKey: process.env.CONTINUM_API_KEY!,
  preset: 'customer-support',
  comply: ['GDPR', 'SOC2'],
  alerts: {
    slack: process.env.SLACK_WEBHOOK_URL,
    pagerduty: process.env.PAGERDUTY_KEY
  }
});

// Now use protect() without passing config every time
const response = await continum.protect(
  () => openai.chat.completions.create({...})
);

​
What happens next?

  1. Instant response: Your user gets the LLM response immediately (0ms added latency)
  2. Async audit: The interaction is audited for compliance violations
  3. Real-time alerts: Violations trigger alerts to your configured channels
  4. Signal stored: Results appear in your dashboard within seconds

​
Presets & Compliance Frameworks

Continum uses presets to automatically configure the right detection types for your use case: 
// Customer support bot
{ preset: 'customer-support' }  // → PII, content policy, bias

// Financial services
{ preset: 'fintech-ai', comply: ['FINRA', 'SOC2'] }  // → PII, financial compliance, security

// Healthcare application
{ preset: 'healthcare-ai', comply: ['HIPAA'] }  // → PII, content policy, bias, hallucination

// AI agent with tool use
{ preset: 'agent' }  // → Agent safety, prompt injection, data exfiltration
Available presets:
  • customer-support, legal-ai, fintech-ai, healthcare-ai
  • coding-assistant, agent, content-generation
  • internal-tool, data-pipeline, education-ai
Supported compliance frameworks:
  • GDPR, CCPA, HIPAA, SOC2, ISO_27001
  • EU_AI_ACT, FINRA, PCI_DSS, NIST_AI_RMF

​
Real-time Alerts

Get notified instantly when violations are detected: 
continum.configure({
  apiKey: process.env.CONTINUM_API_KEY!,
  preset: 'customer-support',
  alerts: {
    slack: process.env.SLACK_WEBHOOK_URL,      // HIGH/CRITICAL violations
    pagerduty: process.env.PAGERDUTY_KEY,      // CRITICAL violations only
    discord: process.env.DISCORD_WEBHOOK_URL,  // MEDIUM/LOW violations
    webhook: process.env.CUSTOM_WEBHOOK_URL    // All violations
  }
});
Alerts are automatically routed by risk level without any dashboard configuration needed.

​
Blocking Mode

For high-risk scenarios, use blocking mode to wait for audit results: 
import { protect, ContinumBlockedError } from '@continum/sdk';

try {
  const response = await protect(
    () => openai.chat.completions.create({...}),
    {
      apiKey: process.env.CONTINUM_API_KEY!,
      blockOn: 'HIGH'  // Block if risk level is HIGH or CRITICAL
    }
  );
} catch (error) {
  if (error instanceof ContinumBlockedError) {
    console.log('Blocked:', error.signal.violations);
    console.log('Risk level:', error.signal.riskLevel);
    // Handle blocked request
  }
}

​
View your signals

Navigate to your dashboard to see compliance signals:
  • Risk level breakdown (LOW, MEDIUM, HIGH, CRITICAL)
  • Violation types and reasoning
  • Filter by provider, model, date range
  • Export for compliance reports

​
Next steps

Configure SDK

Learn about advanced SDK configuration options

Interactive CLI

Use npx continum init for guided setup

Presets & Compliance

Explore presets and compliance frameworks

API reference

Explore the REST API endpoints
Dev plan limits: The DEV plan includes 1,000 audits per month. Upgrade to PRO for unlimited audits and advanced features.