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>
10 KiB
TRA-OPS-0001: AI Content Generation Policy v1.0
Document ID: TRA-OPS-0001 Version: 1.0 Classification: OPERATIONAL Status: DRAFT → ACTIVE (upon Phase 2 start) Created: 2025-10-07 Owner: John Stroh Review Cycle: Quarterly Next Review: 2026-01-07
Purpose
This document establishes the operational policy governing all AI-assisted content generation on the Tractatus Framework website. It ensures that AI operations align with the Tractatus framework's core principle: "What cannot be systematized must not be automated."
Scope
This policy applies to all content generated or assisted by AI systems, including but not limited to:
- Blog posts (topic suggestions, outlines, drafts)
- Media inquiry responses (classification, prioritization, draft responses)
- Case study analysis (relevance assessment, categorization)
- Documentation summaries
- Social media content (future)
Principles
1. Mandatory Human Approval
Principle: No AI-generated content shall be published, sent, or made public without explicit human approval.
Implementation:
- All AI outputs routed through moderation queue
- Two-person rule for sensitive content (admin + reviewer)
- Audit trail: who approved, when, why
- Rejection must include reason (for AI training)
Tractatus Mapping: TACTICAL quadrant (execution requires pre-approval)
2. Values Boundary Enforcement
Principle: AI systems must not make decisions involving values, ethics, or human agency.
Implementation:
- BoundaryEnforcer.service validates all AI actions
- Values decisions flagged for human review
- AI may present options but not choose
Examples:
- ✅ AI can suggest blog topics
- ❌ AI cannot decide editorial policy
- ✅ AI can classify inquiry priority
- ❌ AI cannot decide whether to respond
Tractatus Mapping: STRATEGIC quadrant (values require human judgment per §12.1-12.7)
3. Transparency & Attribution
Principle: Users must know when content is AI-assisted.
Implementation:
- All AI-assisted content labeled "AI-Assisted, Human-Reviewed"
- Disclosure in footer or metadata
- Option to view human review notes (future)
Example Labels:
---
AI-Assisted: Claude Sonnet 4.5
Human Reviewer: John Stroh
Reviewed: 2025-10-15
Changes: Minor edits for tone
---
4. Quality & Accuracy Standards
Principle: AI-assisted content must meet the same quality standards as human-authored content.
Implementation:
- Editorial guidelines (TRA-OPS-0002) apply to all content
- Fact-checking required for claims
- Citation validation (all sources verified by human)
- Tone/voice consistency with brand
Rejection Criteria:
- Factual errors
- Unsupported claims
- Inappropriate tone
- Plagiarism or copyright violation
- Hallucinated citations
5. Privacy & Data Protection
Principle: AI systems must not process personal data without consent.
Implementation:
- No user data sent to Claude API without anonymization
- Media inquiries: strip PII before AI analysis
- Case submissions: explicit consent checkbox
- Audit logs: no personal data retention
Compliance: GDPR-lite principles (even if not EU-based)
6. Cost & Resource Management
Principle: AI usage must be cost-effective and sustainable.
Implementation:
- Monthly budget cap: $200/month (see TRA-OPS-0005)
- Rate limiting: 1000 requests/day max
- Caching: 30-day TTL for identical queries
- Monitoring: alert if >80% of budget used
Governance: Quarterly cost review, adjust limits as needed
AI System Inventory
Approved AI Systems
| System | Provider | Model | Purpose | Status |
|---|---|---|---|---|
| Claude API | Anthropic | Sonnet 4.5 | Blog curation, media triage, case analysis | APPROVED |
Future Considerations
| System | Provider | Purpose | Status |
|---|---|---|---|
| GPT-4 | OpenAI | Fallback for Claude outages | EVALUATION |
| LLaMA 3 | Meta | Self-hosted alternative | RESEARCH |
Approval Process: Any new AI system requires:
- Technical evaluation (accuracy, cost, privacy)
- Governance review (Tractatus compliance)
- John Stroh approval
- 30-day pilot period
Operational Workflows
Blog Post Generation Workflow
graph TD
A[News Feed Ingestion] --> B[AI Topic Suggestion]
B --> C[Human Approval Queue]
C -->|Approved| D[AI Outline Generation]
C -->|Rejected| Z[End]
D --> E[Human Review & Edit]
E -->|Accept| F[Human Writes Draft]
E -->|Reject| Z
F --> G[Final Human Approval]
G -->|Approved| H[Publish]
G -->|Rejected| Z
Key Decision Points:
- Topic Approval: Human decides if topic is valuable (STRATEGIC)
- Outline Review: Human edits for accuracy/tone (OPERATIONAL)
- Draft Approval: Human decides to publish (STRATEGIC)
Media Inquiry Workflow
graph TD
A[Inquiry Received] --> B[Strip PII]
B --> C[AI Classification]
C --> D[AI Priority Scoring]
D --> E[AI Draft Response]
E --> F[Human Review Queue]
F -->|Approve & Send| G[Send Response]
F -->|Edit & Send| H[Human Edits]
F -->|Reject| Z[End]
H --> G
Key Decision Points:
- Classification Review: Human verifies AI categorization (OPERATIONAL)
- Send Decision: Human decides whether to respond (STRATEGIC)
Case Study Workflow
graph TD
A[Community Submission] --> B[Consent Check]
B -->|No Consent| Z[Reject]
B -->|Consent| C[AI Relevance Analysis]
C --> D[AI Tractatus Mapping]
D --> E[Human Moderation Queue]
E -->|Approve| F[Publish to Portal]
E -->|Request Edits| G[Contact Submitter]
E -->|Reject| H[Notify with Reason]
Key Decision Points:
- Consent Validation: Automated check (SYSTEM)
- Relevance Assessment: Human verifies AI analysis (OPERATIONAL)
- Publication Decision: Human decides to publish (STRATEGIC)
Human Oversight Requirements
Minimum Oversight Levels
| Content Type | Minimum Reviewers | Review SLA | Escalation |
|---|---|---|---|
| Blog Posts | 1 (admin) | 48 hours | N/A |
| Media Inquiries (High Priority) | 1 (admin) | 4 hours | John Stroh |
| Media Inquiries (Low Priority) | 1 (admin) | 7 days | N/A |
| Case Studies | 1 (admin) | 7 days | N/A |
| Documentation Changes | 1 (admin) | 14 days | John Stroh |
Reviewer Qualifications
Admin Reviewer (minimum requirements):
- Understands Tractatus framework
- Technical background (AI/ML familiarity)
- Editorial experience (writing, fact-checking)
- Authorized by John Stroh
Future: Multiple reviewer roles (technical, editorial, legal)
Audit & Compliance
Audit Trail Requirements
All AI-assisted content must log:
- Input: What was sent to AI (prompt + context)
- Output: Raw AI response (unedited)
- Review: Human changes (diff)
- Decision: Approve/reject + reason
- Metadata: Reviewer, timestamp, model version
Retention: 2 years minimum
Compliance Monitoring
Monthly Review:
- AI approval rate (target: 70-90%)
- Rejection reasons (categorized)
- Cost vs. budget
- SLA compliance
Quarterly Review:
- Policy effectiveness
- User feedback on AI content quality
- Boundary violations (should be 0)
- Cost-benefit analysis
Annual Review:
- Full policy revision
- AI system evaluation
- Governance alignment audit
Error Handling & Incidents
AI System Failures
Scenario: Claude API unavailable
Response:
- Graceful degradation: disable AI features
- Manual workflows: admins handle all tasks
- User notification: "AI features temporarily unavailable"
- Post-mortem: document incident, adjust SLAs
Content Quality Issues
Scenario: AI-generated content contains factual error
Response:
- Immediate retraction/correction (if published)
- Root cause analysis: prompt issue, AI hallucination, review failure?
- Process update: improve review checklist
- Reviewer training: flag similar errors
Boundary Violations
Scenario: AI makes values decision without human approval
Response:
- CRITICAL INCIDENT: Escalate to John Stroh immediately
- Rollback: revert to manual workflow
- Investigation: How did BoundaryEnforcer fail?
- System audit: Test all boundary checks
- Policy review: Update TRA-OPS-0001
Tractatus Mandate: Zero tolerance for boundary violations
Revision & Amendment Process
Minor Revisions (v1.0 → v1.1)
- Typos, clarifications, formatting
- Approval: Admin reviewer
- Notification: Email to stakeholders
Major Revisions (v1.0 → v2.0)
- Policy changes, new workflows, scope expansion
- Approval: John Stroh
- Review: 30-day comment period
- Notification: Blog post announcement
Emergency Amendments
- Security/privacy issues requiring immediate change
- Approval: John Stroh (verbal, documented within 24h)
- Review: Retrospective within 7 days
Related Documents
Strategic:
- STR-VAL-0001: Core Values & Principles (source: sydigital)
- STR-GOV-0001: Strategic Review Protocol (source: sydigital)
- STR-GOV-0002: Values Alignment Framework (source: sydigital)
Operational (Tractatus-specific):
- TRA-OPS-0002: Blog Editorial Guidelines
- TRA-OPS-0003: Media Inquiry Response Protocol
- TRA-OPS-0004: Case Study Moderation Standards
- TRA-OPS-0005: Human Oversight Requirements
Technical:
- API Documentation:
/docs/api-reference.html - Tractatus Framework Specification:
/docs/technical-proposal.md
Glossary
AI-Assisted Content: Content where AI contributed to generation (topic, outline, draft) but human made final decisions and edits.
Boundary Violation: AI system making a decision in STRATEGIC quadrant (values, ethics, policy) without human approval.
Human Approval: Explicit action by authorized reviewer to publish/send AI-assisted content.
Moderation Queue: System where AI outputs await human review before publication.
Values Decision: Any decision involving ethics, privacy, user agency, editorial policy, or mission alignment.
Approval
| Role | Name | Signature | Date |
|---|---|---|---|
| Policy Owner | John Stroh | [Pending] | [TBD] |
| Technical Reviewer | Claude Code | [Pending] | 2025-10-07 |
| Final Approval | John Stroh | [Pending] | [TBD] |
Status: DRAFT (awaiting John Stroh approval to activate) Effective Date: Upon Phase 2 deployment Next Review: 2026-01-07 (3 months post-activation)