Confluent connects AI agents using MCP and A2A

Confluent has revealed its Confluent Intelligence offering designed to connect AI agents and uncover more accurate, intelligent data analysis.

The company’s streaming agents use the Agent2Agent protocol to trigger and coordinate external AI agents using real-time data streams. Confluent said this makes it easier to connect AI systems across an enterprise.

Confluent Intelligence also uses Multivariate Anomaly Detection to automatically spot unusual patterns in data streams. This is intended to help teams prevent issues with greater accuracy, before they cause outages or downstream impacts.

The organisation’s Streaming Agents connects AI agents to real-time data using Model Context Protocol, and to other agents using A2A.

Confluent said the product can continuously analyse information from agent frameworks such as LangChain, as well as data platforms like BigQuery, Snowflake, and Databricks to generate insights, then trigger enterprise AI platforms like ServiceNow and Salesforce workflows to take immediate action, which closes the gap between insight and execution.

"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, act, coordinate systems, and escalate to team members as needed.”