Agentic AI Reference Architecture

Memory · Data store

Procedural Memory Store

Data storeMemoryCognition & Memoryarc:ProceduralMemoryStore

Long-term memory of learned rules, task-execution patterns and strategies, activated by context pattern matching.

Responsibility. Stores learned procedures and strategies.

Also known as: Procedural memory, Learned heuristics, Reasoning pattern library, System non-parametric long-term memory (Quadrant VI), Workflow memory, Standard diagnostic procedures

is read byis written byis written byis read byis written byis read byis written byis guarded byis written byis read byMemory Retriever: is read byMemory RetrieverMemory Consolidator: is written byMemory ConsolidatorSelf-Reflection Critic: is written bySelf-Reflection CriticThought Exploration Controller: is read byThought Exploration Cont…Memory Lifecycle Manager: is written byMemory Lifecycle ManagerAdaptive Sample Allocator: is read byAdaptive Sample AllocatorEpisode Pattern Abstractor: is written byEpisode Pattern AbstractorMemory Write Validator: is guarded byMemory Write ValidatorPlan Template Extractor: is written byPlan Template ExtractorProcedural Skill Executor: is read byProcedural Skill Executor
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

is guarded by control

Design guidance

Quantitative guidance

As stated by the sources; verify before use.

Classification

Patterns
Context pattern matchingExperience-based reasoning adaptation (no parameter updates)Learned sampling configurations per problem classConsolidation of successful reasoning patterns into reusable templatesSkill libraries and learned policies (Ref5.04)
Technologies
SQLite
Quality attributes
Interaction capability (ISO/IEC 25010)

Sources

  1. Ch1.4: T. Nguyen, "Memory and Perception Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.4. ISBN: 9798244538229.
  2. Ch5.1: T. Nguyen, "Chain-of-Thought (CoT) Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.1. ISBN: 9798244538229.
  3. Ch5.2: T. Nguyen, "Tree-of-Thought (ToT) Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.2. ISBN: 9798244538229.
  4. Ch5.3: T. Nguyen, "Self-Consistency Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.3. ISBN: 9798244538229.
  5. 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.
  6. Ch5.9: T. Nguyen, "Working Memory," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.9. ISBN: 9798244538229.
  7. Ref5.04: C. Stryker, "What is AI agent memory?," IBM Think. Accessed: Sep. 27, 2026. [Online]. Available: https://www.ibm.com/think/topics/ai-agent-memory