Production Rule Base

Data artifactKnowledge & DataKnowledge & Dataarc:ProductionRuleBase

A versioned knowledge base of explicit if-then decision rules, each with conditions, actions, priority (salience), optional confidence score and documented rationale, that applies across all cases.

Responsibility. Holds the permanent, domain-general decision rules that the inference engine applies to case facts.

Also known as: Knowledge base, Rule base, Rule set, Clinical decision rules

Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

Rule Base Updater Ch5.11

is audited by assurance

Compliance Officer Ch5.11

Design guidance

MUST NOT store case-specific facts; these belong in working memory, or later cases will inherit them.
SHOULD document each rule with clear naming, business or clinical rationale and hierarchical organisation so traces remain understandable.
SHOULD attach validated confidence scores to rules so inference can prefer and weight reliable rules.

Quantitative guidance

As stated by the sources; verify before use.

Fraud case: initial base of 85 expert rules achieved 78% detection at 12% false positives (Ch5.11).

Classification

Patterns: If-then production rulesRule salienceRule-level confidence scoresHierarchical rule organisation
Quality attributes: Explainability (NIST AI RMF: explainable and interpretable)Maintainability (ISO/IEC 25010)Transparency and accountability (NIST AI RMF: accountable and transparent)
Risks mitigated: Case-specific facts leaking into general knowledgeIncomprehensible explanations from poorly designed rules

Sources

Ch5.11: T. Nguyen, "Rule-Based Decision Making Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.11. ISBN: 9798244538229.