Confluent has introduced Streaming Agents in Confluent Cloud for Apache Flink, making it easier to build and scale AI agents that act on real-time data. The solution unifies data processing with AI workflows, offering secure connections to LLMs, embedding models, tools, and business systems. This helps enterprises adopt agentic AI faster, streamline workflows, and unlock new business opportunities.
“Agentic AI is on every organization’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 simplify 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.”
IDC research shows that while organizations ran an average of 23 generative AI proofs of concept between 2023 and 2024, only three reached production. Of those, just 62% met expectations. “While most enterprises are investing in agentic AI, their data architectures can’t support the autonomous decision-making capabilities these systems require,” said Stewart Bond, Vice President of Data Intelligence and Integration Software at IDC. “Organizations should prioritize agentic AI solutions that offer easy, secure integration and leverage real-time data for the essential context needed for intelligent action.”
Build, Scale Real Time AI Agents with Streaming Agents
Streaming Agents bring agentic AI into stream processing pipelines, enabling teams to build, deploy, and manage event-driven agents with Apache Kafka and Apache Flink. By combining data processing with AI reasoning, streaming agents can use real-time contextual data to adapt quickly and interact with other systems as conditions change. Always on, streaming agents process high volumes of data and respond instantly with context-aware decisions, much like human operators. For example, they can monitor prices across e-commerce sites and automatically adjust a retailer’s product prices to stay competitive
Key features of Streaming Agents include:
- Tool calling for context-aware automation: Tool invocation via Model Context Protocol (MCP) enables agents to select the right external tool, such as a database, software-as-a-service (SaaS), or API, to take meaningful action. Tool calling accounts for what’s happening in the business and what other systems and agents are doing.
- Connections for secure integrations: Securely connect to models, vector databases, and MCP directly using Flink. Connections also protect sensitive credentials, encourage more reusability by sharing connections across multiple tables, models, and functions, and centralize 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. This improves the accuracy of AI decision-making, vector search, and retrieval-augmented generation (RAG) applications, reduces cost and complexity by using Flink SQL, and leverages the security and networking capabilities of Confluent Cloud.
- Replayability for iteration and safety: Agents can be developed and evaluated using real data without live side effects, enabling dark launches, A/B testing, and faster iteration.
Streaming Agents are available today in open preview.
