Agentic AI Reference Architecture

Knowledge & Data · Software component

Citation Extractor

Software componentKnowledge & DataKnowledge & Dataarc:CitationExtractor

A post-generation component that links each statement in a generated answer to the retrieved source documents it relies on, producing structured source attributions for the response.

Responsibility. Links generated statements to their source documents.

Also known as: Citation extraction, Source attribution, Source tracking

receives data fromsends data tois orchestrated byis audited byreadsAnswer Synthesizer: receives data fromAnswer SynthesizerExplanation Presenter: sends data toExplanation PresenterRAG Query Orchestrator: is orchestrated byRAG Query OrchestratorHuman Evaluator: is audited byHuman EvaluatorDocument Metadata Store: readsDocument Metadata Store
Direct neighbourhood (hover for relationship types)

Relationships

reads dependency

receives data from dynamic

sends data to dynamic

is orchestrated by control

is audited by assurance

Design guidance

Quantitative guidance

As stated by the sources; verify before use.

Classification

Quality attributes
Transparency and accountability (NIST AI RMF: accountable and transparent)Interaction capability (ISO/IEC 25010)
Risks mitigated
Unsourced or unverifiable claims

Sources

  1. Ch6.5: T. Nguyen, "Production RAG Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.5. ISBN: 9798244538229.
  2. Ch9.3: T. Nguyen, "Sandboxing and Transparency Foundations," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.3. ISBN: 9798244538229.