Agentic AI Reference Architecture

Knowledge & Data · Software component

Event Stream Consumer

Software componentKnowledge & DataKnowledge & Dataarc:EventStreamConsumer

A data source connector that continuously consumes messages from event streams or message queues so new knowledge is integrated in near real time.

Responsibility. Pulls messages from an event stream as they arrive for downstream transformation.

Also known as: Kafka consumer, Streaming extractor

Variant of Data Source Connector abstract

When to choose. Choose for real-time or semi-structured event sources when near-instant knowledge updates justify the added complexity.

specializesreceives data fromis configured byData Source Connector: specializesData Source ConnectorEvent Stream Log: receives data fromEvent Stream LogStreaming Extraction Policy: is configured byStreaming Extraction Pol…
Direct neighbourhood (hover for relationship types)

Relationships

is configured by structural

receives data from dynamic

Classification

Patterns
Streaming extraction
Technologies
Apache KafkaRabbitMQAmazon Kinesis
Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)

Sources

  1. Ch6.3A: T. Nguyen, "ETL Pipeline Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.3A. ISBN: 9798244538229.