Systems | Development | Analytics | API | Testing

Today, I'm excited to announce one of our largest Kong AI Gateway releases (3.11), which ships with several new features critical in building modern and reliable AI agents in production. We strongly recommend updating to this version to get access to the latest and greatest that AI infrastructure has to offer.

We’re excited to bring you Kong Gateway Enterprise 3.11 with compelling new features to make your APIs and event streams even more powerful, including: We’ll also touch on what’s new with Konnect networking and Active Tracing. There’s a lot to unpack, so keep on reading for the full story!

RAG (Retrieval-Augmented Generation) is not a new concept in AI, and unsurprisingly, when talking to companies, everyone seems to have their own interpretation of how to implement it. So, let’s start with a refresher. RAG (short for Retrieval-Augmented Generation) is a technique that injects relevant data from an external knowledge source directly into a prompt before sending it to a Large Language Model (LLM). “But wait, my model is already fine-tuned on my domain-specific data.

APIs have long been the backbone of modern software systems, architectures, and businesses. They now dominate the web, accounting for 71% of all internet traffic. Generative AI is accelerating this trend especially as we pivot our interaction with common web-based capabilities, like “search” in favour of AI-enriched variants. More AI leads to more APIs, and with that, APIs act as an important mechanism to move data into and out of AI applications, AI agents, and Large Language Models (LLMs).

This article originally appeared on Software Testing News. We’re sharing it here for our audience who may have missed it. An overlooked API can expose customer data, trigger multi-million-dollar fines, and sink a FinTech product launch. And now, the FinTech industry is at a crossroads, driven by innovation yet bounded by intensifying regulatory demands.

AI systems need both structured data (like spreadsheets) and unstructured data (like images or text). SQL databases excel at structured data, while vector databases handle unstructured data for tasks like similarity searches. The solution? Hybrid AI stacks that combine both through unified Data AI Gateways.

In today’s data-driven world, collecting data is easy, but making sense of it is what truly matters. That’s where Pandas pivot tables come into play. With just a few lines of Python, you can quickly turn disorganized data into meaningful, well-structured summaries. Imagine Excel pivot tables, but faster, more flexible, and fully powered by code.

Quality assurance (QA) is no longer an optional luxury in today’s software development, it is a necessity. As applications become more complex, executing or managing hundreds or thousands of tests by hand is increasingly impractical. Testing suites in software testing provides a way to manage a formal collection of test cases to test various aspects of a software application systematically.