Particle.news
Download on the App Store

Confluent Introduces Confluent Intelligence for Real-Time AI Context, Now in Early Access

The effort channels Kafka and Flink data into continuously updated snapshots that let AI agents operate with fresh state under existing governance.

Overview

  • A new Real-Time Context Engine, offered as a managed service, streams materialized views to AI agents and applications via the Model Context Protocol and is available in early access.
  • Streaming Agents run natively on Apache Flink to observe, decide, and act on live event streams, with Anthropic’s Claude set as the default large language model.
  • Confluent added an Agent Definition service to create production-ready agents in a few lines of code with built-in observability and debugging.
  • Built-in machine learning functions written in Flink SQL for anomaly detection, forecasting, model inference, and real-time visualization are available on Confluent Cloud.
  • Confluent says delivering context through continuous streams can cut token and API costs and allows organizations to reuse existing governance, compliance, and security controls for AI data flows.