Agentic AI Reference Architecture

Model Adaptation · Model asset

LoRA Adapter

Model assetModel AdaptationModelsarc:LoRAAdapter

A small set of trainable low-rank weight matrices that modify a frozen base model's behaviour for a domain or task.

Responsibility. Encodes task specialization separately from frozen base weights.

Also known as: Adapter weights, PEFT adapter

deployed onis trained byInference Server: deployed onInference ServerLoRA Fine-Tuner: is trained byLoRA Fine-Tuner
Direct neighbourhood (hover for relationship types)

Relationships

deployed on structural

is trained by lifecycle

Classification

Quality attributes
Maintainability (ISO/IEC 25010)Cost efficiency

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. Ch4.3: T. Nguyen, "Container Orchestration and Edge Deployment," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.3. ISBN: 9798244538229.