Agentic AI Reference Architecture

Model Serving · Software component

Feature Steering Controller

Software componentModel ServingModelsarc:FeatureSteeringController

An inference-time component that suppresses error-associated features or amplifies correctness-associated features in model activations to correct reasoning in real time.

Responsibility. Adjusts targeted feature activations during inference.

Also known as: Feature intervention, Activation steering

deployed onguardsis triggered byInference Server: deployed onInference ServerFoundation LLM: guardsFoundation LLMFeature Activation Monitor: is triggered byFeature Activation Monitor
Direct neighbourhood (hover for relationship types)

Relationships

deployed on structural

is triggered by dynamic

guards control

Classification

Patterns
Feature suppressionFeature amplification
Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
Confirmation bias in causal reasoning

Sources

  1. Ch3.6: T. Nguyen, "Trace Analysis and Execution Debugging," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.6. ISBN: 9798244538229.