Yesterday I created a build and push artifact CI/CD pipeline for AZ-400 practise in Azure DevOps!16 May 2026
Building a reusable Azure DevOps YAML pipeline for a small .NET helper library: AI-assisted (Aider + Qwen2.5) unit tests, automated SemVer NuGet packaging to GitHub Packages, restore caching, a dotnet format style gate, and the Cache@2 quirk that needed a manual mkdir to fix.
Checkout my new website and live text analysis demo!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.
Disappointing first test with Foundry Local on Intel GPU29 April 2026
Foundry Local reaching GA raised hopes for a real Ollama replacement on Intel GPU — but both tested OpenVINO models hard-capped responses at 199 tokens regardless of the configured max_tokens, a blocker for agentic coding workflows like Aider.
Another update about my AZ-400 practice project!25 April 2026
Adding a detect-language endpoint to the sentiment API, backed by AI-assisted unit tests (Aider + Qwen) that also run on main, a feature-branch flow set up for blue-green then canary, and a Flask route-ordering gotcha (routes must be defined before the blocking app.run() call).
AI Unit Tests: Hype vs My 4-Hour Night21 March 2026
A 4-hour night fighting a local LLM through Aider on unit-test generation — a hallucinated table name, the wrong test framework, and empty files marked 'Done!' — versus the hour it would have taken by hand, and why local AI's ceiling is still worth exploring anyway.
Local LLM Coding Agent: Aider + Ollama on Windows (No Cloud, No Token Limit, Full Privacy)21 March 2026
A streamlined Windows setup for running Aider + Ollama fully locally on an Intel GPU: zero cloud dependency, unlimited context, and a qwen2.5-coder:14b model that handles .NET refactors, new endpoints, and unit tests as a genuine local pair programmer.