EngineeringJune 1, 202619 min read

AIエージェントが業務で失敗する理由は、LLMではなくハーネス不足である

PoCでは動くのに本番化できない原因を、目的・権限・記憶・停止条件・復旧経路・監査証跡の設計から捉える

企業AIエージェントが失敗する主因は、モデル性能だけではない。目的、権限、記憶、品質、停止条件、復旧経路、監査証跡を囲うハーネスがないまま、AIに行動させようとしていることが本質である。

AI-agentDynamic-Harnessenterprise-AIHITLMARIA-OSjapanese
IntelligenceFebruary 14, 202632 min read

Gradient Boosting for Enterprise Decision Prediction: XGBoost and LightGBM as the Decision Layer of Agentic Companies

Why enterprise data is often tabular and how gradient boosting ensembles support approval prediction, risk scoring, and outcome estimation

While deep learning dominates many unstructured tasks, enterprise decision data is frequently tabular: structured features describing decisions, agents, contexts, and outcomes. This paper formalizes gradient boosting (XGBoost/LightGBM) as the Decision Layer (Layer 2) of the agentic company stack, details feature-engineering patterns for enterprise decision tables, and introduces SHAP-based explainability workflows for governance audits. Across evaluated datasets, the approach achieved 91.3% approval-prediction accuracy, 0.94 AUC on risk scoring, and full SHAP traceability integrated with MARIA OS responsibility gates.

gradient-boostingXGBoosttabular-dataapproval-predictionrisk-scoringdecision-predictionensemble-methodsenterprise-AIagentic-companyMARIA OS