Agentic AI Reference Architecture

Model Serving · Software component

Rule-Based Complexity Classifier

Software componentModel ServingModelsarc:RuleBasedComplexityClassifier

A query complexity assessor that matches predefined keyword patterns to label queries as simple or complex quickly and deterministically.

Responsibility. Assigns query complexity from keyword pattern rules.

Also known as: Keyword-pattern complexity classification

Variant of Query Complexity Assessor abstract

When to choose. Choose when query classes follow clear lexical patterns and zero added latency and cost matter more than robustness to phrasing variation.

is target of alternativeTospecializesis configured byQuery Complexity Classifier: is target of alternativeToQuery Complexity Classif…Query Complexity Assessor: specializesQuery Complexity AssessorComplexity Pattern Rule Set: is configured byComplexity Pattern Rule …
Direct neighbourhood (hover for relationship types)

Relationships

is configured by structural

alternative to variability

Design guidance

Classification

Patterns
Rule-based classification
Quality attributes
Performance efficiency (ISO/IEC 25010)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
Risks mitigated
Misclassification from phrasing variations (brittleness)

Sources

  1. Ch8.3: T. Nguyen, "Token Economics and Architecture," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 8.3. ISBN: 9798244538229.