Agentic AI Reference Architecture

Memory · Data artifact

Memory Retrieval Policy

Data artifactMemoryCognition & Memoryarc:MemoryRetrievalPolicy

A configuration specifying memory retrieval parameters: ranking weights, decay rate, similarity threshold, top-k limit, token budget share and context metadata filters.

Responsibility. Declares how many and which memories retrieval may return and how they are ranked.

Also known as: Retrieval strategy weights, Retrieval limits, Graduated retrieval order

configuresconfiguresMemory Retriever: configuresMemory RetrieverMulti-Signal Relevance Ranker: configuresMulti-Signal Relevance R…
Direct neighbourhood (hover for relationship types)

Relationships

configures structural

Classification

Quality attributes
Maintainability (ISO/IEC 25010)Performance efficiency (ISO/IEC 25010)

Sources

  1. Ch5.7: T. Nguyen, "Episodic Memory," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.7. ISBN: 9798244538229.
  2. 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.