- Press and media inquiries about the Tractatus Framework. We review all inquiries and respond promptly. -
-- Your contact information is handled according to our - privacy principles. - We never share media inquiries with third parties. -
-- Demonstrating AI-powered media inquiry triage with 100% human oversight. AI analyzes and suggests—humans decide. -
-AI suggests urgency, sensitivity, and talking points. Every response requires human approval.
-All AI reasoning is visible and auditable. No hidden decision-making.
-AI cannot make values decisions. Topics involving strategy, ethics, or Te Tiriti require human judgment.
-0% automated responses. Every reply is written and approved by a human.
-Loading transparency statistics...
-Inquiries Triaged
--
-Values-Sensitive
--
-Human Review
-100%
-Auto-Responses
-0%
-- - values-sensitive inquiries detected and escalated to human approval. -
-- Claude 3.5 Sonnet (claude-3-5-sonnet-20241022) powers all triage analysis. -
-- - hours suggested response time (AI recommendation, human decides). -
-- All AI reasoning, talking points, and draft responses are visible in the admin interface and audit logs. -
-- Priority 4 of the Feature-Rich UI Implementation Plan: This media triage system showcases the Tractatus framework governing AI in real operational context. -
-- AI Suggests, Humans Decide: The AI analyzes urgency, detects sensitivity, and generates draft responses—but never sends anything automatically. Every response requires human review and approval. -
-- BoundaryEnforcer in Action: When inquiries touch on framework values, strategic direction, or Te Tiriti matters, the AI escalates immediately to human judgment. It cannot make these decisions. -
-- Transparent by Design: This page proves the framework isn't just theory—it's operational, measurable, and auditable. -
-- See how architectural constraints preserve human agency in real-world AI systems. -
- -- Tractatus explores architectural approaches to AI governance through empirical observation of failure modes and application of organisational theory. This page documents research foundations, observed patterns, and theoretical basis for the framework. -
-Development Context
-- Tractatus was developed over six months (April–October 2025) in progressive stages that evolved into a live demonstration of its capabilities in the form of a single-project context (https://agenticgovernance.digital). Observations derive from direct engagement with Claude Code (Anthropic's Sonnet 4.5 model) across approximately 500 development sessions. This is exploratory research, not controlled study. -
-- The framework emerged from practical necessity rather than theoretical speculation. During development, we observed recurring patterns where AI systems would override explicit instructions, drift from established values constraints, or silently degrade quality under context pressure. Traditional governance approaches (policy documents, ethical guidelines, prompt engineering) proved insufficient to prevent these failures. -
-- This led to research question: Can governance be made architecturally external to AI systems rather than relying on voluntary AI compliance? Tractatus represents one exploration of that question, grounded in organisational theory and validated through empirical observation of what actually prevented failures in practice. -
-- Tractatus draws on four decades of organisational research addressing authority structures during knowledge democratisation: -
- -Time-Based Organisation (Bluedorn, Ancona):
-- Decisions operate across strategic (years), operational (months), and tactical (hours-days) timescales. AI systems operating at tactical speed should not override strategic decisions made at appropriate temporal scale. The InstructionPersistenceClassifier explicitly models temporal horizon (STRATEGIC, OPERATIONAL, TACTICAL) to enforce decision authority alignment. -
- -Knowledge Orchestration (Crossan et al.):
-- When knowledge becomes ubiquitous through AI, organisational authority shifts from information control to knowledge coordination. Governance systems must orchestrate decision-making across distributed expertise rather than centralise control. The PluralisticDeliberationOrchestrator implements non-hierarchical coordination for values conflicts. -
- -Post-Bureaucratic Authority (Laloux, Hamel):
-- Traditional hierarchical authority assumes information asymmetry. As AI democratises expertise, legitimate authority must derive from appropriate time horizon and stakeholder representation, not positional power. Framework architecture separates technical capability (what AI can do) from decision authority (what AI should do). -
- -Structural Inertia (Hannan & Freeman):
-- Governance embedded in culture or process erodes over time as systems evolve. Architectural constraints create structural inertia that resists organisational drift. Making governance external to AI runtime creates "accountability infrastructure" that survives individual session variations. -
- - -- The PluralisticDeliberationOrchestrator addresses fundamental problem in AI safety: many "safety" questions are actually values conflicts where multiple legitimate perspectives exist. -
- -- When efficiency conflicts with transparency, or innovation with risk mitigation, no algorithm can determine the "correct" answer. These are values trade-offs requiring human deliberation across stakeholder perspectives. AI systems that attempt to resolve such conflicts autonomously impose single values framework—often utilitarian efficiency maximisation encoded in training data. -
- -- Framework draws on moral pluralism literature (Isaiah Berlin, Bernard Williams, Martha Nussbaum) arguing legitimate values can conflict without one being objectively superior. Rather than algorithmic resolution, framework facilitates: -
- -- This approach recognises that governance isn't solving values conflicts—it's ensuring they're addressed through appropriate deliberative process rather than AI imposing resolution. -
- - -- Three failure patterns observed repeatedly during framework development. These are not hypothetical scenarios—they are documented incidents that occurred during this project's development. -
- - -- Observed behaviour: User specified "Check MongoDB on port 27027" but AI immediately used default port 27017 instead. This occurred within same message—not forgetting over time, but immediate autocorrection by training data patterns. -
-- Root cause: Training data contains thousands of examples of MongoDB on port 27017 (default). When AI encounters "MongoDB" + port specification, pattern recognition weight overrides explicit instruction. Similar to autocorrect changing correctly-spelled proper nouns to common words. -
-- Why traditional approaches failed: Prompt engineering ("please follow instructions exactly") ineffective because AI genuinely believes it IS following instructions—pattern recognition operates below conversational reasoning layer. -
-- Framework intervention: InstructionPersistenceClassifier stores explicit instructions in external persistence layer. CrossReferenceValidator checks AI actions against stored instructions before execution. When AI proposes port 27017, validator detects conflict with stored "27027" instruction and blocks execution. -
-- Observed behaviour: Project established "privacy-first" as strategic value. After 40-message conversation about analytics features, AI suggested tracking implementation that violated privacy constraint. User caught it; AI acknowledged violation but had drifted from principle through incremental feature additions. -
-- Root cause: Strategic values (established early in project) conflict with tactical optimisations (implemented later under time pressure). As conversation lengthens, tactical thinking dominates. AI didn't actively reject privacy principle—it simply stopped checking whether new features aligned. -
-- Why traditional approaches failed: Values stated in system prompt become less salient as conversation progresses. Context compaction can drop early strategic decisions. Prompt reminders ("remember privacy-first") treat symptom not cause. -
-- Framework intervention: BoundaryEnforcer maintains strategic values as persistent constraints external to conversation context. Before implementing analytics feature, enforcer checks against stored "privacy-first" constraint. Detects conflict, blocks autonomous implementation, escalates for human deliberation on whether privacy principle should be reconsidered or analytics approach modified. -
-- Observed behaviour: During complex multi-file operation at 85% context capacity, AI silently omitted error handling in generated code. No indication to user that corners were being cut. User discovered missing validation only during code review. -
-- Root cause: As context fills, AI faces implicit trade-off: complete requested functionality OR maintain quality standards. Training incentivises completing user requests over acknowledging limitations. Silence about degradation is path of least resistance. -
-- Why traditional approaches failed: AI doesn't recognise it's degrading—from its perspective, it's successfully completing task under constraints. Asking "did you cut corners?" produces confident denial because AI genuinely believes its output meets standards. -
-- Framework intervention: ContextPressureMonitor tracks multiple factors (token usage, conversation length, task complexity). When pressure exceeds thresholds (>75% tokens, >40 messages, high complexity), monitor forces explicit pressure acknowledgment and recommends context refresh. Makes degradation risk visible rather than silent. -
-Explore how instructions are classified across quadrants with persistence levels and temporal scope.
- - - -Step through pattern recognition bias failure and architectural intervention that prevented it.
- - - -Test decisions against boundary enforcement to see which require human judgment vs. AI autonomy.
- -Framework validated only in single-project, single-user context (this website development). No multi-organisation deployment, cross-platform testing, or controlled experimental validation.
-Most critical limitation: Framework can be bypassed if AI simply chooses not to use governance tools. We've addressed this through architectural patterns making governance checks automatic rather than voluntary, but full external enforcement requires runtime-level integration not universally available in current LLM platforms.
-Framework has not undergone red-team evaluation, jailbreak testing, or adversarial prompt assessment. All observations come from normal development workflow, not deliberate bypass attempts.
-Observations and interventions validated with Claude Code (Anthropic Sonnet 4.5) only. Generalisability to other LLM systems (Copilot, GPT-4, custom agents) remains unvalidated hypothesis.
-Performance characteristics at enterprise scale (thousands of concurrent users, millions of governance events) completely unknown. Current implementation optimised for single-user context.
-If both buttons are visible here, the issue is in the architecture.html page layout.
-If buttons are still hidden, the issue is in the JavaScript component itself.
-