n8n-nodes-compliance-web-intel

The scraper AI agents trust. n8n community node for Compliance-Grade Web Intelligence.

Extract grounded facts with source citations, entities, claims, and RAG-ready chunks. Built for LangChain, LlamaIndex, AutoGPT, and compliance audits.

🚨 Colorado SB 25B-004 Ready

This node generates audit-ready output for AI compliance requirements effective June 30, 2026:

• Source documentation with sourceBlockId and exactQuote
• Auto-generated citations (APA, MLA, Chicago)
• Full provenance tracking with timestamps and hashes

Features

• 7 Task Modes - Optimized presets for different use cases
• Grounded Extraction - Facts with exact quotes and source references
• RAG-Ready Chunks - 500-900 tokens with semantic boundaries
• Entity Detection - People, organizations, money, dates, contact info
• Claim Analysis - Marketing claims, guarantees, compliance statements
• Quality Scoring - 0-100 score with completeness and confidence metrics
• Auto-Citations - APA, MLA, Chicago, inline, and markdown formats
• Change Monitoring - Detect material changes with diff baselines

Installation

In n8n (Recommended)

1. Go to Settings → Community Nodes
2. Click Install a community node
3. Enter: n8n-nodes-compliance-web-intel
4. Click Install

Via npm

npm install n8n-nodes-compliance-web-intel

Credentials

You need an Apify API token to use this node:

1. Sign up at apify.com
2. Go to Account → Integrations → API tokens
3. Create a new token
4. Add the token to n8n credentials

Task Modes

| Mode | Description | Best For | |------|-------------|----------| | general | Balanced extraction | Any website | | competitor_teardown | Positioning, pricing, features | Competitive analysis | | compliance_discovery | Policies, legal terms, privacy | Compliance audits | | sales_research | Contacts, pricing, company info | Account research | | local_seo_audit | NAP, reviews, schema.org | Local business SEO | | docs_extraction | Documentation to JSON specs | API/product docs | | pricing_intelligence | Pricing tiers and features | Market research |

Output Modes

| Mode | Returns | Use Case | |------|---------|----------| | full | Complete Reasoning Pack | Full analysis | | chunks | RAG-ready text chunks | Vector databases | | summary | Agent-ready summary | Quick briefs | | entities | Extracted entities | Data enrichment | | claims | Marketing claims | Competitive intel |

Example Workflows

RAG Pipeline

[Compliance Web Intel] → [Pinecone/Weaviate] → [LangChain Agent]
     ↓ chunks mode
   Returns individual chunks with metadata ready for embedding

Competitor Monitoring

[Schedule Trigger] → [Compliance Web Intel] → [IF Changed] → [Slack]
                         ↓ competitor_teardown
                       Compare with diffBaseline from previous run

Sales Research

[HTTP Request (leads)] → [Compliance Web Intel] → [Google Sheets]
                              ↓ sales_research
                            Extract contacts, pricing, company info

Output Schema

Full Reasoning Pack

{
  "url": "https://example.com/pricing",
  "domain": "example.com",
  "taskMode": "pricing_intelligence",
  
  "content": {
    "markdown": "...",
    "title": "Pricing - Example",
    "blocks": [...]
  },
  
  "extraction": {
    "facts": [{
      "statement": "Enterprise plan starts at $99/month",
      "sourceBlockId": "blk_5_abc",
      "exactQuote": "Our Enterprise plan, starting at just $99/month...",
      "confidence": 0.92
    }],
    "entities": [...],
    "claims": [...],
    "pricing": [...]
  },
  
  "quality": {
    "overallScore": 88,
    "completeness": 95,
    "confidence": 82
  },
  
  "summary": {
    "oneLiner": "SaaS pricing page with 3 tiers from $29-$299/month",
    "keyFacts": [...],
    "recommendedActions": [...]
  },
  
  "citation": {
    "apa": "Example. (2026). Pricing - Example. Retrieved...",
    "mla": "...",
    "inline": "[Pricing - Example](https://example.com/pricing) (accessed 2026-01-28)"
  },
  
  "chunks": [{
    "id": "chunk_001",
    "text": "...",
    "tokenCount": 687,
    "metadata": {...}
  }]
}

Pricing

This node uses the Compliance Web Intel Apify Actor:

• Actor Start: $0.001 per run
• Per Result: $0.002 per page (~$2 per 1,000 pages)

Resources

• Apify Actor Documentation
• n8n Community Nodes Documentation
• Colorado SB 25B-004

License

MIT

Author

AI Solutionist - [email protected]

Built with the HYPERCOGNATE methodology 🦉