Overview

Platform Purpose

The Village is a member-owned community platform providing sovereign data storage, AI-assisted features, and privacy-by-design architecture. Communities operate with full data ownership and governance-protected AI assistance.

Deployment Facts

  • Duration: 11+ months in production
  • Tenant Model: Single-tenant (multi-tenant planned)
  • AI Features: 4 governed features live
  • Services/Response: 6 governance checks

Architecture Mapping

Each Village AI feature maps to specific Tractatus governance services. The table below shows how the six services coordinate for each feature.

Village Feature Primary Service Function
Home AI Responses BoundaryEnforcer Blocks values judgments, defers to human
User Query Processing CrossReferenceValidator Prevents prompt injection, validates intent
Session Management ContextPressureMonitor Tracks session health, triggers handoffs
Multi-Step Operations MetacognitiveVerifier Detects scope creep, requires review
Feature Flags InstructionPersistenceClassifier Persistence classification for settings
Consent Handling PluralisticDeliberationOrchestrator Multi-stakeholder decisions

The Home AI Flow

When a user submits a query to Home AI, it passes through six verification stages before a response is generated. This flow operates in the critical execution path.

  1. 1

    User Query Received

    User submits query via Help Chat widget or story assistance

  2. 2

    BoundaryEnforcer Check

    Is this a values question requiring human judgment?

  3. 3

    CrossReferenceValidator Check

    Does this conflict with stored instructions or attempt injection?

  4. 4

    ContextPressureMonitor Check

    Is session health within acceptable bounds?

  5. 5

    Query Processing

    RAG system retrieves context with permission filtering

  6. 6

    Response Generation

    AI generates response (Claude Haiku for non-EN, local Llama for EN)

  7. 7

    MetacognitiveVerifier Check

    Is response appropriate to query scope?

  8. 8

    Delivery

    Response delivered to user with source attribution

Governed Features in Detail

RAG-Based Help Centre

Vector search over indexed help content, stories, and documentation. Results filtered by user permissions before inclusion in context.

Services: CrossReferenceValidator, BoundaryEnforcer

Document OCR

Automated text extraction from uploaded documents. Operates under explicit consent controls with audit logging.

Services: PluralisticDeliberationOrchestrator (consent)

Story Assistance

AI-assisted writing suggestions for family stories. Content suggestions filtered through BoundaryEnforcer to prevent inappropriate recommendations.

Services: BoundaryEnforcer, MetacognitiveVerifier

AI Memory Transparency

User-controlled summarisation with full audit dashboard. Members can view, edit, and delete what AI "remembers" about them.

Services: InstructionPersistenceClassifier, PluralisticDeliberationOrchestrator

Honest Limitations

This case study documents preliminary evidence from a single implementation. We are transparent about the following limitations:

  • Single Implementation: Village is one platform. Generalisability to other contexts is unknown.
  • Self-Reported Metrics: No independent verification of logged data has been conducted.
  • Operator-Developer Overlap: Framework developer also operates Village (conflict of interest).
  • Limited Adversarial Testing: No formal red-team evaluation has been conducted.
  • Voluntary Invocation: AI could theoretically bypass governance if not configured to use it.

What This Demonstrates

Evidence Supports

  • • Architectural governance can operate in production without prohibitive overhead
  • • Six-service coordination is technically feasible
  • • Governance violations are detectable and auditable
  • • The framework learns from failures (documented incident responses)

Evidence Does NOT Support

  • • Framework effectiveness at scale (thousands of concurrent users)
  • • Generalisability across different AI systems
  • • Resistance to sophisticated adversarial attacks
  • • Regulatory sufficiency (EU AI Act compliance untested)

Explore Further

See the Village platform in action, or dive deeper into the technical architecture.

Visit the Village → System Architecture → Research Details →