Agentic AI Reference Architecture

Model Adaptation · Model asset

Domain-Adapted Base Model

Model assetModel AdaptationModelsarc:DomainAdaptedBaseModel

A base language model checkpoint whose weights have been continued-pretrained on a domain corpus, serving as the starting point for task fine-tuning.

Responsibility. Carries domain knowledge into subsequent fine-tuning.

Also known as: CPT checkpoint

Variant of Foundation LLM abstract

is evaluated byspecializesis trained byEvaluation Harness: is evaluated byEvaluation HarnessFoundation LLM: specializesFoundation LLMContinued Pretrainer: is trained byContinued Pretrainer
Direct neighbourhood (hover for relationship types)

Relationships

is evaluated by assurance

is trained by lifecycle

Classification

Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)

Sources

  1. Ch3.5: T. Nguyen, "Prompt Optimization, Few-Shot Learning, Fine-Tuning," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.5. ISBN: 9798244538229.
  2. Ch7.5: T. Nguyen, "NeMo Curator, Riva Speech AI & Multimodal Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.5. ISBN: 9798244538229.