Confluent, Inc. has launched Streaming Agents, a new capability in Confluent Cloud for Apache Flink that builds and scales AI agents that monitor, reason, and act on real-time data.
"Agentic AI is on every organisation's roadmap. But most companies are stuck in prototype purgatory, falling behind as others race toward measurable outcomes," said Shaun Clowes, chief product officer at Confluent. "Even your smartest AI agents are flying blind if they don't have fresh business context. Streaming Agents simplifies the messy work of integrating the tools and data that create real intelligence, giving organisations a solid foundation to deploy AI agents that drive meaningful change across the business."
Streaming Agents
Key features of Streaming Agents include the following:
- Tool calling for context-aware automation: Tool invocation via Model Context Protocol (MCP) claims to enable agents to select the right external tool, such as a database, software-as-a-service (SaaS), or API, to take meaningful action.
- Connections for secure integrations: It claims to connect directly to models, vector databases, and MCP using Flink for secure integration. Connections aim to protect sensitive credentials, encourage more reusability by sharing connections across multiple tables, models, and functions, and centralise management for large-scale deployments.
- External Tables and Search to boost AI accuracy: Ensure that streaming data is enriched with non-Kafka data sources, such as relational databases and REST APIs, to provide the most current and complete view of data.
- Replayability for iteration and safety: Users can develop and evaluate agents through real data without live side effects. The method enables dark launches, A/B testing, and faster iteration.
