New capability in Confluent Cloud accelerates enterprise adoption of intelligent, context-aware AI agents
Confluent has launched Streaming Agents, a breakthrough capability in Confluent Cloud for Apache Flink® that enables enterprises to build and scale intelligent AI agents that act on real-time data. This innovation marks a significant leap in agentic AI, bridging the gap between prototype and production with secure, scalable, and context-rich automation.
Streaming Agents unify data processing and AI workflows, allowing agents to monitor, reason, and respond dynamically to business signals. By integrating with large language models (LLMs), embedding models, and enterprise tools, organizations can now deploy AI agents that deliver measurable outcomes and unlock new business models.
“Agentic AI is on every organization’s roadmap. But most companies are stuck in prototype purgatory.”
– Shaun Clowes, Chief Product Officer at Confluent.
“Agentic AI is on every organization’s roadmap. But most companies are stuck in prototype purgatory,” said Shaun Clowes, Chief Product Officer at Confluent. “Streaming Agents simplifies the messy work of integrating the tools and data that create real intelligence, giving organizations a solid foundation to deploy AI agents that drive meaningful change across the business.”
Key features include tool calling via Model Context Protocol (MCP), secure connections to models and databases, external table integration for enriched decision-making, and replayability for safe iteration and testing. These capabilities empower agents to operate autonomously, adapt in real time, and collaborate across systems—mirroring human-like reasoning.
IDC research highlights the urgency: while enterprises ran an average of 23 generative AI pilots, only three reached production. Streaming Agents addresses this gap, offering a robust path to scalable, real-time AI.
Streaming Agents are now available in open preview on Confluent Cloud.
