Agentic AI Reference Architecture

Cognition · Model asset

User Trajectory Model

Model assetCognitionCognition & Memoryarc:UserTrajectoryModel

Machine-learning model weights trained on user trajectories, i.e., typical transitions from current to future states, predicting what users will need next and when they typically recognise that need.

Responsibility. Encodes learned user state-transition patterns for need prediction.

Also known as: Trajectory model, Behavioural prediction model

is monitored bydeployed onis trained byData Drift Detector: is monitored byData Drift DetectorUser Need Predictor: deployed onUser Need PredictorContinual Learning Trainer: is trained byContinual Learning Trainer
Direct neighbourhood (hover for relationship types)

Relationships

deployed on structural

is monitored by assurance

is trained by lifecycle

Design guidance

Classification

Risks mitigated
Generic population-level suggestions

Sources

  1. Ch10.2: T. Nguyen, "Proactive Agents," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.2. ISBN: 9798244538229.