Agentic AI Reference Architecture

Cognition · Data artifact

Conflict Resolution Policy

Data artifactCognitionCognition & MemoryVariation point (abstract)arc:ConflictResolutionPolicy

An abstract configuration that determines which rule fires when several rules match the current facts simultaneously.

Responsibility. Orders simultaneously matching rules so exactly one executes next.

Also known as: Conflict resolution strategy, Agenda strategy

configuresis specialized byis specialized byis specialized byis specialized byis specialized bySymbolic Logic Engine: configuresSymbolic Logic EngineLayered Conflict Resolution Policy: is specialized byLayered Conflict Resolut…Order-of-Entry Conflict Resolution Policy: is specialized byOrder-of-Entry Conflict …Recency Conflict Resolution Policy: is specialized byRecency Conflict Resolut…Salience (Priority) Conflict Resolution Policy: is specialized bySalience (Priority) Conf…Specificity Conflict Resolution Policy: is specialized bySpecificity Conflict Res…
Direct neighbourhood (hover for relationship types)

Variants

VariantWhen to choose
Layered Conflict Resolution PolicyChoose when fine-grained control is needed at scale: explicit priorities for business-critical rules, automatic specificity for most rules, and recency so updated rules take effect without re-prioritising.
Order-of-Entry Conflict Resolution PolicyChoose when simplicity and determinism matter most and the rule base can be maintained as a carefully sequenced decision list with specific rules placed before general fallbacks.
Recency Conflict Resolution PolicyChoose when knowledge evolves rapidly and newer rules encode more current understanding (e.g., new fraud patterns); requires rule modification timestamps and clear documentation.
Salience (Priority) Conflict Resolution PolicyChoose when explicit control is needed, e.g., safety-critical systems where emergency rules must pre-empt optimisation or routine rules; requires careful priority assignment and maintenance.
Specificity Conflict Resolution PolicyChoose when rules form natural general-to-specific hierarchies where nuanced policies should override broad defaults; needs a separate policy for equal-specificity conflicts.

Relationships

configures structural

Design guidance

Classification

Quality attributes
Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)Explainability (NIST AI RMF: explainable and interpretable)
Risks mitigated
Surprising decisions from ambiguous rule precedence

Sources

  1. 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.