Orchestration · Software component
Clarification Manager
Software componentOrchestrationOrchestration & Toolsarc:ClarificationManager
A dialogue-control component that, when intent inference is ambiguous or low-confidence, asks progressively more structured follow-up questions to resolve the user's intent.
Responsibility. Resolves ambiguous user intent through staged clarification turns.
Also known as: Progressive clarification, Disambiguation dialog
Relationships
is configured by structural
reads dependency
- Conversation State Store abstract Ch10.1
writes dependency
is routed to by dynamic
sends data to dynamic
Design guidance
- SHOULD acknowledge uncertainty transparently and offer specific options when multiple intents have similar confidence.
- SHOULD escalate from open-ended rephrasing to targeted multiple-choice options to guided examples only as ambiguity persists.
- SHOULD log failed intent inferences with eventual clarifications as training data.
Quantitative guidance
As stated by the sources; verify before use.
- Erica's targeted clarification resolves ambiguity within a single follow-up turn (Ch10.1).
Classification
- Patterns
- Progressive clarificationMulti-stage fallback hierarchy
- Quality attributes
- Interaction capability (ISO/IEC 25010)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
- Risks mitigated
- Generic 'I don't know' responses that abandon usersMisrouted intents
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.