Big-data streaming company Confluent Inc. is upgrading its Confluent Intelligence platform with Streaming Agents. These agents utilize the Agent2Agent protocol to connect with specialized external AI agents, enabling collaborative automation.
This new capability addresses the isolation of most current AI agents, allowing them to share business context. Streaming Agents analyze data from sources like BigQuery and Databricks, feeding insights to enterprise platforms such as Salesforce and ServiceNow for immediate action. Confluent acts as the orchestrator, providing governance, security, and observability for these interactions.
Confluent Head of AI, Sean Falconer, stated, "AI can automatically react to live data, take action, coordinate systems and escalate issues when needed." The platform connects AI investments and systems regardless of their origin.
Additionally, Confluent is rolling out Multivariate Anomaly Detection in early access. This tool enhances system monitoring by analyzing multiple related metrics simultaneously. Unlike traditional tools that often work in isolation or with batch data, this feature provides real-time context, helping prevent outages and reduce false positives by identifying complex patterns across system signals.
These updates aim to provide enterprises with a foundation for more proactive and capable AI agents that can instantly react to business changes.