Agentic AI Reference Architecture

Cognition · Software component

Outcome Probability Estimator

Software componentCognitionCognition & Memoryarc:OutcomeProbabilityEstimator

A cognition component that estimates the conditional probability of each outcome state given a candidate action, from current state, models and historical outcome data.

Responsibility. Estimates P(outcome | action) distributions for candidate actions.

Also known as: Outcome model, Transition probability estimator

is invoked byreadsreadsis invoked byUtility-Based Decision Maker: is invoked byUtility-Based Decision M…World Model State: readsWorld Model StateDecision Outcome History Store: readsDecision Outcome History…MDP Policy Solver: is invoked byMDP Policy Solver
Direct neighbourhood (hover for relationship types)

Relationships

is invoked by dependency

reads dependency

Design guidance

Classification

Patterns
Bayesian full-distribution estimationConfidence-bounded probability estimatesProbability sensitivity analysis
Quality attributes
Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
False confidence from point probability estimates

Sources

  1. Ch5.10: T. Nguyen, "Utility-Based Decision Making Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.10. ISBN: 9798244538229.