Confluent is launching Streaming Agents, a new feature that enables real-time AI agents with access to up-to-date data. The solution combines data streaming with AI workflows to deliver enterprise-grade agentic AI.
The challenge lies not in the technology itself, but in its implementation. AI agents have potential, but organizations struggle with practical application. The problem lies mainly in data complexity. “Agentic AI is on every organization’s roadmap. But most companies are stuck in prototype purgatory, falling behind as others race toward measurable outcomes,” says Shaun Clowes, Chief Product Officer at Confluent. AI agents are only as powerful as the tools and data they have access to.
Real-time context as a foundation
Streaming Agents focuses on event-driven agents built with Apache Kafka and Apache Flink. By combining data processing and AI reasoning, agents gain access to up-to-date contextual data from real-time sources. They can quickly adapt to changing circumstances and communicate with other systems.
A practical example: automatically updating competitive prices by continuously monitoring prices on various e-commerce sites. The AI agent automatically adjusts product prices on the company’s own site so that customers see the most attractive offer.
Enterprise functionalities
The solution offers four core components. Tool calling via Model Context Protocol (MCP) enables agents to select the right external tool for meaningful action. Connections provide secure integrations with models, vector databases, and MCP via Flink, while sensitive data remains protected.
External Tables and Search enrich streaming data with non-Kafka data sources such as relational databases and REST APIs. This improves AI accuracy and vector search applications. Replayability enables development and evaluation with real data without live updates.
Streaming Agents is available today in open preview. The functionality addresses the growing demand for AI agents that deliver real value in production environments, not just in lab settings.
Tip: Confluent makes Kubernetes version of its Kafka service