Why This Matters

Natural language to SQL (NL2SQL) works well for ad-hoc questions and app backends — until the model returns the wrong rows or a query that fails or runs too slowly in production. To ship with confidence you need three guarantees: the result set is correct (same logical result as the intended query), the SQL executes on your database without syntax or runtime errors, and it’s efficient enough (reasonable latency and plan quality, e.g. Oracle EXPLAIN PLAN). The only reliable way to get those guarantees is to compare LLM output to a gold standard on a real database, in a repeatable pipeline — so you can improve prompts, compare models, and catch dialect gotchas (Oracle vs MySQL, EXTRACT vs LIMIT, and the like). This framework gives you that pipeline.

For example, the internal AI assistant looks great at demo time. Vector database ingesting overnight, GPT-4-class model, clean stakeholder presentation. The team ships.

Just like POST requests, the content-type header is important because it tells the server how to interpret the data we’re sending.

This is what I mean when I call uncontrolled retries a self-inflicted Denial-of-Wallet attack. Not metaphorically. Mechanically.

At first, everything looks fine:

It isn't. And the gap between those two things has eaten more than a few production environments.

Building a CI/CD pipeline for LLM-based applications on Google Cloud Platform (GCP) presents unique challenges. Unlike traditional software, LLM outputs are non-deterministic, making testing complex. Unlike traditional ML, the "model" is often a managed service (like Gemini) or a fine-tuned version of an open-source giant, shifting the focus from training to orchestration, prompt management, and RAG (Retrieval-Augmented Generation) infrastructure.

Nowadays, there are quite a lot of AI coding assistants. In this blog, you will take a closer look at Claude Code, a terminal-based AI coding assistant. Since mid January 2026, Claude Code can also be used in combination with Ollama, a local inference engine. Enjoy!

Introduction

There are many AI models and also many AI coding assistants. Which one to choose is a hard question. It also depends on whether you run the models locally or in the cloud. When running locally, Qwen3-Coder is a very good AI model to be used for programming tasks. In previous posts, DevoxxGenie, a JetBrains IDE plugin, was often used as an AI coding assistant. DevoxxGenie is nicely integrated within the JetBrains IDEs. But it is also a good thing to take a look at other AI coding assistants. In a previous blog, Qwen Code was used; now it is time to take a look at Claude Code.

Modernization used to mean something simpler: Move the workloads, update the tooling, declare the project done. In practice, that approach meant engineers manually migrating hundreds of DataStage jobs one at a time, a process that was slow, error-prone, and impossible to scale as platforms grew. The traditional model worked when volumes were low. It broke entirely when weekly release windows started carrying 500 jobs, and the only way through was brute-force manual effort.

What changed the equation was not just cloud infrastructure but also a fundamentally different operating model. When a CI/CD-based promotion mechanism replaced manual steps, reducing what once required hours of coordinated effort down to a single parameterized execution, hundreds of jobs could migrate consistently, with less human involvement and a verifiable audit trail. That shift exposed a harder truth: the technology was never the bottleneck. The operating model was.

In reality, Kubernetes is a layered ecosystem where storage, compute, networking, security, and developer workflows interlock like gears in a precision machine. If one gear slips, everything grinds. If all align, you unlock a platform that scales, heals, and evolves with your applications.

Challenges in Kafka Consumer Fault Tolerance

Kafka consumers usually operate in an at least once delivery mode, which means a message might be delivered multiple times if not acknowledged properly. Transient errors can cause message processing failures. Without proper handling, such failures might lead to data loss or duplicate processing. If a consumer fails after processing a message but before committing the offset, Kafka will resend that message to another consumer, leading to a duplicate delivery. A fault tolerant consumer design addresses these scenarios by:

The Goal

User asks in natural language → chatbot reads/searches PDFs → returns an answer.

In this article, you'll see how to configure request logging in Spring Boot and inspect request payloads and parameters.

This shift creates a real opportunity. With the right tools, organizations can move beyond basic reporting and start making informed decisions around efficiency, cost optimization, and sustainability.

In my experience, these failures are rarely caused by tools. They come from how integration patterns are applied without considering real-world conditions like latency, retries, partial failures, and security boundaries.

In this guide, we'll walk through how to create an anonymous PL/pgSQL block that generates random data and inserts it into a PostgreSQL table. The data will include various types such as integers, strings, dates, booleans, and UUIDs.

Architecture Overview

The pipeline involves multiple components working together in sequence. Below is the event flow:

Azure AI Search (formerly known as Azure Cognitive Search) has emerged as a powerhouse in this space. By moving beyond simple vector databases and offering a comprehensive information retrieval platform, it addresses the unique challenges of the enterprise: scale, security, and precision. In this article, we will deep-dive into the five key ways Azure AI Search is improving enterprise RAG, backed by technical architecture, code examples, and performance insights.

It is surprisingly common and often misunderstood, even by teams that have encountered it in production. Understanding the dual write problem starts with seeing why the obvious solution fails, and ends with four patterns that address it correctly.

Enter AWS Kiro. AWS Kiro (Kernel-Integrated Runtime Orchestrator) is a specialized, high-performance infrastructure layer designed specifically for the orchestration of multi-agent systems. It moves beyond the limitations of standard container orchestration to provide a low-latency, state-aware environment where agents can thrive. This article provides a deep dive into what AWS Kiro is, how it works, and why it is the missing piece for the next generation of AI development.