Part 12: AI Gateway Reloaded

This blog explores how Kong AI Gateway has been reloaded between versions 3.10 and 3.14, evolving from a secure AI integration layer into a powerful foundation for managing agentic AI workloads. Building on its enterprise-grade capabilities, Kong has significantly expanded its AI feature set with enhanced multi-provider support, improved resilience and fine-grained Model Context Protocol (MCP) access controls. The result is a more mature AI Gateway designed to support modern AI systems.

22.06.2026

Alexander Suchier

Part 11: RAG team play with Spring AI

This blog talks about Kong’s potential for Retrieval-Augmented Generation (RAG) implementations. RAG is a technique that improves large language models by adding real-time, enterprise-specific data retrieval, improving response accuracy and relevance. The team play between Kong AI Gateway and Spring AI enables seamless integration and optimization of generative AI RAG workflows within enterprise environments.

17.07.2025

Alexander Suchier

Part 10: AI Gateway

This blog details how Kong API Gateway functions as an AI Gateway, providing the necessary features to manage AI integrations securely and efficiently. Kong offers a complete, high-quality middleware solution that makes AI development easier by removing the need for many special tools and frameworks. It also supports language independence to avoid any limits. Additionally, the new AI plugins empower organizations to mitigate AI risks and uphold ethical AI practices.

14.06.2025

Alexander Suchier

Part 9: Serverless functions - Who responded?

In our previous blog posts in the Kong Gateway series, we explored various security aspects, particularly focusing on token-related issues and their solutions involving both Kong and custom-built plugins. Today, we dive deeper into another coding variant within the gateway: Kong serverless functions. We will use a real-world “Who Responded?” example to demonstrate how effectively a root cause analysis approach can be supported with minimal effort.

19.03.2025

Alexander Suchier

Reproducible and consistent development environments with DevContainers

As a developer in an agile world it becomes quite normal to be involved in more than one activity (projects, trainings and some research) at a time. Each of these activities may require a specific setup of development environments in terms of programming languages, compiler and library versions. Installing and maintaining all this with a classical approach is error-prone and requires a lot of effort. Using task-specific virtual machines would solve the problem, but it consumes a lot of resources and causes a lot of maintenance as well, because one also needs to keep VM’s operating system up to date. This article shows, how DevContainers can help you create and maintain reproducible development environments leveraging the benefits of modern container technology.

14.03.2025

Stefan Kühnel