In my previous post, I was pointing out how an LLM context should be handled with care, and how there’s a better and worse way to basically interface with it. It’s not enough to “prompt in a clear way” or pack tons of customizations inside a CLAUDE.md file. In part 1, which you can read…
Read MoreAgentic coding tools promise to move beyond code completion. Instead of asking an AI assistant to generate a function or explain an error, we give an agentic coder a goal and let it inspect a repository, plan a change, edit several files, run tests, and iterate. That shift is powerful, but it also changes the…
Read MoreHmmm, that question sounds familiar… maybe I wrote about something similar in the past, for instance Would You Use an AI Chatbot to Write Your Blog Post? That time I was saying that a lot of people were beginning to write their blog posts with the help of AI. And that the result was wonderful…
Read MoreIf you’ve spent any real time with an AI coding agent, you know the feeling. The first twenty minutes are great – the agent finds the right file, makes the right edit, and explains itself clearly – this is amazing, what a time to be alive! Just like when you’re stuck in a 3 hour…
Read MoreMore tools don’t mean more intelligence. Especially when the model runs on your own hardware. Let’s be honest: Ever since the Model Context Protocol became the de facto standard for connecting an LLM to the outside world, a sort of hoarding race has begun. One MCP server for the filesystem, one for Git, one for…
Read MoreTekton has been at the core of our CI/CD infrastructure for several years. On OpenShift, however, we’ve never interacted with Tekton only through its APIs or command-line tools: The OpenShift web console provides a convenient graphical interface to inspect pipelines, understand their structure, start them with custom parameters and workspaces, and follow their execution. As…
Read MoreIf I start with a generic opening like “In the AI age” or “AI is changing software development,” I’d have lost your interest already. You’ve likely read phrases like those a bazillion times in the last month alone. You probably also already have a strong opinion, either in favor of or against AI-generated code. And…
Read MoreThe first half of 2026 has witnessed the transition of artificial intelligence from an experimental playground into a cyber warfare domain. In fact, threat actors have shifted from basic prompting toward highly automated, multi-stage operations. This shift is characterized by a bifurcation of threats. On one side, attacks exploiting inherent AI vulnerabilities and architectural boundaries,…
Read MoreFor a long time, software development has had a fairly comforting structure: You had a problem, you wrote some code, you shipped it, and then you moved on to the next problem while quietly pretending the previous one wouldn’t come back to haunt you at all. Mission accomplished. That model is starting to break, not…
Read MoreWhen our work on the NetEye 4.47 upgrade started, one technical dependency quickly became impossible to ignore: Grafana dashboards that still relied on the legacy IDO MySQL database had to be moved to IcingaDB first. That wasn’t the interesting part, though. The interesting part was how to do it safely. These dashboards are part of…
Read MoreOne practical approach to how the IT function of a global enterprise can govern strategy, manage digital products and services, and deliver work continuously, using a coherent three-layer model based on a hybrid operating model. Building on What We Already Know Running IT in a global enterprise is not a single problem. It is at…
Read MoreHi everyone 😃 Today I’d like to walk you through some experiments we ran about load-balancing requests to LLMs in Kubernetes. Let’s dive deep into it! Why Deploy LLMs in Kubernetes? Well, Kubernetes has now established itself as a leading technology when it comes to workloads orchestration. And with time the increasing support for accelerators…
Read MoreThe code is the structure, the LLM is the glue at the joints. There’s a widespread misconception about automations “powered by artificial intelligence”: People picture a model you give an order to, which then carries out a complex operation from start to finish all on its own. It’s a seductive image, and almost always wrong….
Read MoreDuring our consulting activities we frequently find ourselves having to collect data from SNMP devices that do not support SNMPv3 for data encryption. This type of traffic is readable on the network and can create security problems and noncompliance with company certifications, for example ISO27K. For this reason, you might have devices segregated on a…
Read MoreRunning Ollama locally or on dedicated hardware is straightforward until you need to know whether a model is actually loaded in RAM, how fast it generates tokens under load, or when memory consumption reaches a threshold that affects other workloads. A simple TCP port check confirms the process is alive, nothing more. This tutorial shows…
Read More