Agentic AI Reference Architecture

Orchestration · Data artifact

Knowledge Refresh Policy

Data artifactOrchestrationOrchestration & ToolsVariation point (abstract)arc:KnowledgeRefreshPolicy

An abstract configuration choosing whether a pipeline run processes only the delta since the last successful run or reprocesses the full corpus.

Responsibility. Determines the scope of data a pipeline run reprocesses.

Also known as: Incremental vs full update mode

configuresis specialized byis specialized byIngestion Pipeline Orchestrator: configuresIngestion Pipeline Orche…Incremental Refresh Policy: is specialized byIncremental Refresh PolicyFull Refresh Policy: is specialized byFull Refresh Policy
Direct neighbourhood (hover for relationship types)

Variants

VariantWhen to choose
Full Refresh PolicyChoose for initial population, after chunking or schema parameter changes, or to remediate quality issues from earlier permissive filters.
Incremental Refresh PolicyChoose as the default for scheduled (hourly or daily) runs that keep the knowledge base fresh.

Relationships

configures structural

Sources

  1. Ch6.3B: T. Nguyen, "ETL Worked Example - Load Phase & Pipeline Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.3B. ISBN: 9798244538229.