27 July 2026
The origin story for the Capacity Advisor: born from real throttling alerts, first shipped as a live ACA demo, now extended to evaluate node fit and cluster headroom on AKS too.
27 July 2026
The origin story for the Capacity Advisor: born from real throttling alerts, first shipped as a live ACA demo, now extended to evaluate node fit and cluster headroom on AKS too.
1 June 2026
The original Hangman demo launch: two Cloudflare Qwen2.5 LLM agents playing against each other, containerized on Azure Container Apps, served by a Cloudflare Worker, with real-time output over SignalR — evolved from an earlier AI-102 console practice project.
20 May 2026
How blue/green deployment in Azure Container Apps and feature-flag-driven canary rollout in Azure App Configuration work together on a real demo: stable blue serving production traffic, green tested separately, with per-user feature flags controlling which AI features (sentiment, language detection, summarization) are live.
7 May 2026
The build log for koorevaar.com itself: three evenings from buying the domain to a portfolio built with Aider+Qwen2.5, GitHub Actions pipelines, and a Terraform-deployed Azure Container Apps text-analysis demo behind a Cloudflare Worker + phi3:mini.
2 May 2026
A 60-second canary deployment demo: traffic split at the ingress controller between blue and green environments, plus a sticky-session example, all served over a real HTTPS production URL.
26 April 2026
The first working blue-green deployment on AKS for AZ-400 practice: three pipelines split across infrastructure provisioning, deployment, and Traefik IngressRoute-based promotion between two Git-branch environments.
19 April 2026
The sentiment API goes live via a real two-pipeline, cross-subscription Azure DevOps setup: Terraform cluster creation feeding a second deploy pipeline through cross-pipeline artifact passing, arm64/amd64 cost-split nodepools, end-to-end deploy in 2 minutes.
15 January 2026
The first real working milestone for the Semantic Kernel Hangman game: switching to a bigger qwen2.5:32b-instruct model via IPEX-LLM Ollama and simplifying down to 2 agents (no host agent) finally got a full game to completion.