AI and ML in Confluent Cloud

Confluent provides two sets of AI and ML capabilities. With Confluent Intelligence, you build AI workflows directly in Confluent Cloud using Flink SQL. With AI tools, you bring Confluent into the AI assistants and coding agents you already use.

Confluent Intelligence

Confluent Intelligence is a suite of capabilities for building agentic AI workflows with Flink SQL. You can create streaming agents, serve real-time context to AI agents, and run built-in ML functions.

Confluent Intelligence includes the following capabilities:

  • Streaming Agents: Create AI agents that run continuously in Flink SQL, connecting your streaming data to AI models. For more information, see Streaming Agents.

  • Real-Time Context Engine: Deliver real-time data from your Kafka topics to external AI agents through MCP. For more information, see Real-Time Context Engine.

  • Built-in ML functions: Run forecasting, anomaly detection, sentiment analysis, and PII detection directly in Flink SQL. For more information, see Built-In AI/ML Functions.

  • Model inference: Connect to remote or managed AI models from Flink SQL. For more information, see Run a Remote AI Model.

For more information, see Confluent Intelligence.

Use AI tools with Confluent

Confluent provides tools that integrate with AI assistants and coding agents. You can manage Confluent Cloud resources, inspect topics and schemas, debug connectors, and build streaming applications using natural language.

The following tools are available:

  • Managed MCP servers: Connect your AI assistant to Confluent Cloud to explore environments, inspect topics, debug connectors, and query metrics. For more information, see Managed MCP Servers.

  • Open-source MCP server: Run a self-hosted MCP server that supports both Confluent Cloud and local Kafka setups. For more information, see Open-Source MCP Server.

  • Agent skills: Use AI-powered guides with your coding agent to build production-ready streaming applications. For more information, see Agent Skills.

For more information, see Use AI Tools with Confluent Cloud.