AI Developer Tools

5/19/2026

Introduces the generally available Confluent AI Developer Tools, comprising an open-source local MCP server for read/write access to Confluent environments, a managed MCP server in Confluent Cloud for read-only access and diagnostics, and Agent Skills that provide domain expertise for AI assistants. The MCP server implements an open standard for AI tool integration, enabling discovery, building, management, and debugging of Confluent resources. Agent Skills offer specialized workflows for Schema Registry, Kafka Streams, Python Kafka Client, and CDC to Tableflow pipelines, enhancing AI assistant capabilities with Confluent-specific knowledge and best practices.

10/16/2025

This post details the integration of Confluent's data streaming platform with Google Cloud to power real-time backbone for agentic AI systems. It explains how Confluent facilitates real-time data flow for Generative AI, enabling LLMs and other AI services with up-to-date information. The post elaborates on the Model Context Protocol (MCP) for agent-to-resource interaction and Agent-to-Agent (A2A) protocol for inter-agent communication, highlighting how Confluent acts as a proxy to standardize and manage these interactions. Key technical aspects include using Kafka topics for decoupled, event-driven communication, ensuring message durability and asynchronous processing, and exposing existing microservices and Flink jobs as MCP tools or A2A agents via a unified registry and protocol transformation. The post also emphasizes the role of Confluent in providing real-time context and stability for complex agent systems.

7/1/2025

This post details the technical implementation of integrating a GitHub Copilot chat participant with Confluent's AI Developer Tools. It explains the VS Code tool-calling flow, including the roles of Copilot, LLMs, and the LanguageModelTool API. The post outlines the file structure of the chat participant, focusing on the 'tools' and 'summarizers' subfolders, and provides code examples for tool registration, invocation, and summarization of Kafka topics. It highlights the use of `LanguageModelChatMessage` and `LanguageModelToolResultPart` for communication between the VS Code extension and LLMs, and emphasizes the importance of explicit formatting in messages sent to the AI model.

4/28/2025

This post extends the AI Developer Tools feature thread by proposing how Apache Kafka and event streaming can serve as a scalable communication backbone for agent-to-agent protocols like Google's Agent2Agent (A2A). It details the limitations of point-to-point communication for A2A and MCP in enterprise AI ecosystems and advocates for an event-driven architecture approach using Kafka. It outlines three potential implementation patterns: Kafka as a transport layer, Kafka for task routing and fan-out, and a hybrid orchestration pattern, emphasizing how Kafka can enable loose coupling, multiple consumers, durable communication, and real-time orchestration for agent interactions.

3/25/2025

This post details the implementation of a Confluent MCP server that allows AI agents to interact with Confluent resources using natural language. It explains the Model Context Protocol (MCP) and its client-server architecture, highlighting how Confluent's MCP server exposes tools, resources, and prompts to AI clients. The post showcases practical examples of AI agents managing Kafka topics, producing/consuming messages, executing Flink SQL, and tagging topics via natural language commands. It also provides a step-by-step guide on how to add new tools to the MCP server, demonstrating the extensibility of the system.

9/17/2024

Introduces Confluent for VS Code, an IDE extension that provides local Kafka process support, integration with stream processing tools like Apache Flink, and enhanced visibility into data streams. Features include project templates, Kafka topic management (list, create, edit, delete), message browsing and searching, and Schema Registry integration for schema management. It enables live debugging of data streams within the IDE.

9/10/2024

This post details how generative AI can be leveraged to improve data quality by automating the creation of metadata (schemas, descriptions, provenance) which is essential for trustworthy AI applications. It explains the process of using generative AI models with examples to induce schemas and generate metadata, emphasizing the need for human review to correct AI errors and ensure accuracy. The post advocates for a data streaming platform as an optimal pattern for applying metadata at the time of data production and creating reusable data products. It also touches upon the broader concept of AI governance and its dependence on robust data governance.

5/23/2023

This post details the development and deployment of a PII Detection stream processing application, PII UDFs/UDTs for ksqlDB, and a PII SMT for Kafka Connect. These components leverage machine learning and NLP to identify and redact Personally Identifiable Information (PII) from data streams in real-time, enhancing data governance and security for SIEM/SOAR solutions. It also introduces the concept of entity-level control for unstructured data and provides configuration examples for custom entity detection.