Orchestration · Data artifact

Intent Taxonomy

Data artifactOrchestrationOrchestration & Toolsarc:IntentTaxonomy

A catalogue of discrete user-intent categories, aligned with actual user needs, each mapped to a distinct handling pathway.

Responsibility. Defines the intent categories an intent classifier may assign and the pathway each maps to.

Also known as: Intent framework, Intent categories

Direct neighbourhood (hover for relationship types)

Relationships

configures structural

Intent Router Ch10.1

Design guidance

SHOULD define intent categories from actual user needs rather than system capabilities.
SHOULD expand categories when logged clarification failures reveal recurring unmet intents.

Quantitative guidance

As stated by the sources; verify before use.

Klarna maintains 35 discrete intent categories for common customer service requests (Ch10.1).

Classification

Patterns: Intent-to-pathway mapping
Quality attributes: Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)Maintainability (ISO/IEC 25010)
Risks mitigated: Coverage gaps for real user needs (e.g., missing 'partial refund' intent)

Sources

Ch10.1: T. Nguyen, "Conversational UI," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.1. ISBN: 9798244538229.