TAG ARCHIVE
HITL
5 MARIA OS blog articles tagged HITL. Safety, accountability, fail-closed gates, auditability, and human-in-the-loop control for AI agents. This canonical topic archive supports search engines and LLM retrieval.
Judgment OS / Decision Intelligence OS
Core MARIA OS research on turning organizational judgment into executable decision systems.
Agentic Company Architecture
Research on human-agent organizations, delegation boundaries, role topology, and governed autonomy.
Responsibility Gates and AI Governance
Safety, accountability, fail-closed gates, auditability, and human-in-the-loop control for AI agents.
Multi-Agent Mathematics
Formal models for convergence, stability, game theory, graph dynamics, and multi-agent evaluation.
Evidence, RAG, and Knowledge Governance
Evidence bundles, retrieval architecture, Graph RAG, knowledge trust, and auditable reasoning pipelines.
Agentic R&D and Judgment Science
Research operations, simulation labs, judgment science, recursive improvement, and experimental AI governance.
Why AI Agents Fail at Real Work: It Is Not the LLM, It Is the Harness Shortage
Understanding why agents work in PoC but never reach production — through the design of purpose, authority, memory, stop conditions, recovery paths, and audit trails
The primary reason enterprise AI agents fail is not model performance alone. The essence of the failure is letting AI act without a harness that encloses purpose, authority, memory, quality, stop conditions, recovery paths, and audit trails.
Operational AI Governance as a Technical Moat: A Realistic Assessment of MARIA OS
Why internal auto-recovery, external HITL, responsibility envelopes, and fail-closed gates matter more than another agent demo
The next credible enterprise AI advantage will not come from claiming full autonomy. It will come from knowing where autonomy must stop, how recovery paths are tested, and how human accountability survives at production speed. This article gives a realistic assessment of Bonginkan's MARIA OS architecture and the operational evidence required to turn that architecture into a durable technical moat.
Recursive Self-Improvement Under Governance Constraints: Governed Recursion via Contraction Mapping and Lyapunov Stability
How MARIA OS's Meta-Insight turns unbounded recursive self-improvement into convergent self-correction while preserving governance constraints
Recursive self-improvement (RSI) — an AI system improving its own capabilities — is both promising and risky. Unbounded RSI raises intelligence-explosion concerns: a system improving faster than human operators can evaluate or constrain. This paper presents governed recursion, a Meta-Insight framework in MARIA OS for bounded RSI with explicit convergence guarantees. We show that the composition operator M_{t+1} = R_sys ∘ R_team ∘ R_self(M_t, E_t) implements recursive improvement in meta-cognitive quality, while a contraction condition (gamma < 1) yields convergence to a fixed point instead of divergence. We also provide a Lyapunov-style stability analysis where Human-in-the-Loop gates define safe boundaries in state space. The multiplicative SRI form, SRI = product_{l=1..3} (1 - BS_l) * (1 - CCE_l), adds damping: degradation in any one layer lowers overall autonomy readiness. Across simulation and governance scenarios, governed recursion retained 89% of the unconstrained improvement rate while preserving measured alignment stability.
Responsibility-Tiered RAG Output Control: A Mathematical Framework for Gate-Governed Retrieval Accuracy
Why controlling RAG accuracy through responsibility structure outperforms Top-k optimization alone
Many RAG systems optimize retrieval quality primarily through Top-k tuning and embedding similarity. This paper adds a governance-oriented approach: responsibility-tiered gates that adjust validation intensity by risk classification. The framework reports an 82% hallucination-rate reduction on enterprise document corpora while maintaining sub-second response times for low-risk queries.
Fail-Closed Gate Design for Agent Governance: Responsibility Decomposition and Optimal Human Escalation
Responsibility decomposition-point control for enterprise AI agents
When an AI agent modifies production code, calls external APIs, or alters contracts, responsibility boundaries must remain explicit. This paper formalizes fail-closed gates as a core architectural primitive for responsibility decomposition in multi-agent systems. We derive gate configurations via constrained optimization and use internal simulations to illustrate how a 30/70 human-agent ratio can preserve responsibility coverage while reducing decision latency versus full human review.