Confluent, Inc. has expanded its Confluent Intelligence portfolio with new capabilities designed to connect AI agents in real time and deliver more precise data monitoring across the enterprise. Announced from Mountain View, the update introduces support for the Agent2Agent (A2A) protocol and launches Multivariate Anomaly Detection, strengthening how organizations operationalize AI at scale.
At the core of the release are Confluent’s Streaming Agents, which leverage the A2A protocol to enable AI agents to communicate and coordinate across systems. Using Anthropic’s Model Context Protocol (MCP) allows Streaming Agents to analyze data streams continuously. This enables actions across enterprise platforms. AI systems, usually siloed in departments, can share context. They can collaborate and respond to live business conditions more dynamically.
“If you want to be competitive, your AI can’t be looking in the rearview mirror,” said Sean Falconer, Head of AI at Confluent. “You need a system of AI agents that work together and constantly learn and share insights in real time. Confluent Intelligence connects teams’ AI investments and systems no matter where they’re built—so AI can automatically react to live data, take action, coordinate systems, and escalate to team members as needed.”
Also Read: Amplitude Unveils Agentic AI Analytics to Redefine Product Insight and Revenue Outcomes
Through A2A support, enterprises can build reusable AI agents, orchestrate inter-agent communication via Apache Kafka®, and maintain immutable logs for governance and auditability. The capability is designed to power use cases ranging from personalized retail promotions to predictive maintenance in manufacturing and risk reduction in financial services. A2A support is currently available in Open Preview.
Confluent also introduced Multivariate Anomaly Detection within its built-in machine learning functions. This feature stands out from traditional tools. Instead of looking at metrics separately, it analyzes related signals together. For example, it examines CPU, memory, and latency. This approach helps find complex patterns and cuts down on false positives. The system adapts automatically as data changes. This lets teams spot emerging risks before they lead to outages or operational issues.
The enhancements make Confluent Intelligence a key part of adaptive AI systems. These systems use real-time data to be context-aware.
