Phase 2 Planning Documents Created: 1. PHASE-2-ROADMAP.md (Comprehensive 3-month plan) - Timeline & milestones (Month 1: Infrastructure, Month 2: AI features, Month 3: Soft launch) - 5 workstreams: Infrastructure, AI features, Governance, Content, Analytics - Success criteria (technical, governance, user, business) - Risk assessment with mitigation strategies - Decision points requiring approval 2. PHASE-2-COST-ESTIMATES.md (Budget planning) - Total Phase 2 cost: $550 USD (~$900 NZD) for 3 months - Recommended: VPS Essential ($30/mo) + Claude API ($50/mo) - Usage scenarios: Minimal, Standard (recommended), High - Cost optimization strategies (30-50% savings potential) - Monthly budget template for post-launch 3. PHASE-2-INFRASTRUCTURE-PLAN.md (Technical specifications) - Architecture: Cloudflare → Nginx → Node.js → MongoDB - Server specs: OVHCloud VPS Essential (2 vCore, 4GB RAM, 80GB SSD) - Deployment procedures (step-by-step server setup) - Security hardening (UFW, Fail2ban, SSH, MongoDB) - SSL/TLS with Let's Encrypt - Monitoring, logging, backup & disaster recovery - Complete deployment checklist (60+ verification steps) 4. Governance Documents (TRA-OPS-0001 through TRA-OPS-0005) TRA-OPS-0001: AI Content Generation Policy (Master policy) - Mandatory human approval for all AI content - Values boundary enforcement (Tractatus §12.1-12.7) - Transparency & attribution requirements - Quality & accuracy standards - Privacy & data protection (GDPR-lite) - Cost & resource management ($200/month cap) TRA-OPS-0002: Blog Editorial Guidelines - Editorial mission & content principles - 4 content categories (Framework updates, Case studies, Technical, Commentary) - AI-assisted workflow (topic → outline → human draft → approval) - Citation standards (APA-lite, 100% verification) - Writing standards (tone, voice, format, structure) - Publishing schedule (2-4 posts/month) TRA-OPS-0003: Media Inquiry Response Protocol - Inquiry classification (Press, Academic, Commercial, Community, Spam) - AI-assisted triage with priority scoring - Human approval for all responses (no auto-send) - PII anonymization before AI processing - Response templates & SLAs (4h for HIGH priority) - Escalation procedures to John Stroh TRA-OPS-0004: Case Study Moderation Standards - Submission requirements (title, summary, source, failure mode) - AI-assisted relevance assessment & Tractatus mapping - Quality checklist (completeness, clarity, sources) - Moderation workflow (approve/edit/request changes/reject) - Attribution & licensing (CC BY-SA 4.0) - Seed content: 3-5 curated case studies for launch TRA-OPS-0005: Human Oversight Requirements - 3 oversight models: MHA (mandatory approval), HITL (human-in-loop), HOTL (human-on-loop) - Admin reviewer role & responsibilities - Service level agreements (4h for media HIGH, 7 days for case studies) - Approval authority matrix (admin vs. John Stroh) - Quality assurance checklists - Incident response (boundary violations, poor quality) - Training & onboarding procedures Key Principles Across All Documents: - Tractatus dogfooding: Framework governs its own AI operations - "What cannot be systematized must not be automated" - Zero tolerance for AI values decisions without human approval - Transparency in all AI assistance (clear attribution) - Human-in-the-loop for STRATEGIC/OPERATIONAL quadrants - Audit trail for all AI decisions (2-year retention) Next Steps (Awaiting Approval): - [ ] John Stroh reviews all 8 documents - [ ] Budget approval ($550 for Phase 2, $100-150/month ongoing) - [ ] Phase 2 start date confirmed - [ ] OVHCloud VPS provisioned - [ ] Anthropic Claude API account created Phase 2 Status: PLANNING COMPLETE → Awaiting approval to begin deployment 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> |
||
|---|---|---|
| .claude | ||
| data/mongodb | ||
| docs | ||
| governance | ||
| public | ||
| scripts | ||
| src | ||
| tests | ||
| .env.example | ||
| .gitignore | ||
| CLAUDE.md | ||
| ClaudeWeb conversation transcription.md | ||
| NEXT_SESSION.md | ||
| package.json | ||
| README.md | ||
| SESSION_CLOSEDOWN_20251006.md | ||
| SETUP_INSTRUCTIONS.md | ||
| tailwind.config.js | ||
| Tractatus-Website-Complete-Specification-v2.0.md | ||
Tractatus AI Safety Framework Website
Status: Development - Phase 1 Implementation Domain: mysy.digital Project Start: 2025-10-06
Overview
A world-class platform demonstrating the Tractatus-Based LLM Safety Framework through three audience paths (Researcher, Implementer, Advocate), AI-powered features with human oversight, and interactive demonstrations.
Key Innovation: The website implements the Tractatus framework to govern its own AI operations (dogfooding).
Project Structure
tractatus/
├── docs/ # Source markdown & governance documents
├── public/ # Frontend assets (CSS, JS, images)
├── src/ # Backend code (Express, MongoDB)
│ ├── routes/ # API route handlers
│ ├── controllers/ # Business logic
│ ├── models/ # MongoDB models
│ ├── middleware/ # Express middleware
│ │ └── tractatus/ # Framework enforcement
│ ├── services/ # Core services (AI, governance)
│ └── utils/ # Utility functions
├── scripts/ # Setup & migration scripts
├── tests/ # Test suites (unit, integration, security)
├── data/ # MongoDB data directory
└── logs/ # Application & MongoDB logs
Quick Start
Prerequisites
- Node.js 18+
- MongoDB 7+
- Git
Installation
# Clone repository (once GitHub account is set up)
cd /home/theflow/projects/tractatus
# Install dependencies
npm install
# Copy environment variables
cp .env.example .env
# Edit .env with your configuration
# Initialize database
npm run init:db
# Migrate documents
npm run migrate:docs
# Create admin user
npm run seed:admin
# Start development server
npm run dev
The application will be available at http://localhost:9000
Technical Stack
- Backend: Node.js, Express, MongoDB
- Frontend: Vanilla JavaScript, Tailwind CSS
- Authentication: JWT
- AI Integration: Claude API (Sonnet 4.5) - Phase 2+
- Testing: Jest, Supertest
Infrastructure
- MongoDB Port: 27017
- Application Port: 9000
- Database: tractatus_dev
- Systemd Service: mongodb-tractatus.service, tractatus.service
Phase 1 Deliverables (3-4 Months)
Must-Have for Complete Prototype:
- Infrastructure setup
- Document migration pipeline
- Three audience paths (Researcher/Implementer/Advocate)
- Tractatus governance services (Classifier, Validator, Boundary Enforcer)
- AI-curated blog with human oversight
- Media inquiry triage system
- Case study submission portal
- Resource directory
- Interactive demonstrations (classification, 27027, boundary enforcement)
- Human oversight dashboard
- Comprehensive testing suite
Development Workflow
Running Tests
npm test # All tests with coverage
npm run test:unit # Unit tests only
npm run test:integration # Integration tests
npm run test:security # Security tests
npm run test:watch # Watch mode
Code Quality
npm run lint # Check code style
npm run lint:fix # Fix linting issues
Database Operations
npm run init:db # Initialize database & indexes
npm run migrate:docs # Import markdown documents
npm run generate:pdfs # Generate PDF downloads
Governance
This project adheres to the Tractatus framework principles:
- Sovereignty & Self-determination: No tracking, user control, open source
- Transparency & Honesty: Public moderation queue, AI reasoning visible
- Harmlessness & Protection: Privacy-first design, security audits
- Community & Accessibility: WCAG compliance, three audience paths
All AI actions are governed by:
- InstructionPersistenceClassifier
- CrossReferenceValidator
- BoundaryEnforcer
- ContextPressureMonitor
- MetacognitiveVerifier
Human Approval Required
All major decisions require human approval:
- Architectural changes
- Database schema modifications
- Security implementations
- Third-party integrations
- Values-sensitive content
- Cost-incurring services
See: CLAUDE.md for complete project context and conventions
Te Tiriti & Indigenous Perspective
This project acknowledges Te Tiriti o Waitangi and indigenous leadership in digital sovereignty. Implementation follows documented indigenous data sovereignty principles (CARE Principles) with respect and without tokenism.
No premature engagement: We will not approach Māori organizations until we have something valuable to offer post-launch.
Links & Resources
- Project Context:
CLAUDE.md - Specification:
Tractatus-Website-Complete-Specification-v2.0.md - Framework Documentation:
/home/theflow/projects/sydigital/stochastic/innovation-exploration/ - Governance References:
/home/theflow/projects/sydigital/strategic/
License
MIT License - See LICENSE file for details
Contact
Project Owner: John Stroh Email: john.stroh.nz@pm.me Repository: GitHub (primary) + Codeberg/Gitea (mirrors)
Last Updated: 2025-10-06 Next Milestone: Complete MongoDB setup and systemd service