29 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.
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.
11 April 2026
From sandbox success to a full CI/CD pipeline in a day: Terraform for AKS, Spot nodepools, a clean LLM-adapter pattern, Traefik on ARM64, ConfigMap-driven prompts, and a cross-subscription, bootstrap-plus-main-stage pipeline — all on €45 of remaining credits.
10 April 2026
The first working milestone: a self-hosted sentiment-analysis service running in the Whizlabs AKS sandbox — Terraform + PowerShell automation, a multi-container Ollama/LLM-adapter/Flask architecture, and ConfigMap-driven prompts with proper health probes.
5 April 2026
Kicking off a self-hosted LLM sentiment-analysis platform on AKS: a Flask API, an LLM adapter layer, Ollama (phi3:mini) in-cluster, Terraform for IaC, and Traefik ingress via Helm — the plan before any of it exists yet.
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.
18 January 2026
Migrating the Hangman game from classic Semantic Kernel to Microsoft's new Agent Framework in ~3 hours: why AutoGen is being phased out, and the honest recommendation for where to invest depending on where you're starting from (AutoGen, older SK, or fresh).
17 January 2026
The full write-up (and code) for the Semantic Kernel multi-agent Hangman game, promised as a follow-up to the earlier 'finally got it working' milestone post.
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.
9 January 2026
Three small local models (llama3.2:3b, phi4-mini, qwen2.5:7b) and a host agent structure for the Hangman game — writing the game logic was easy, getting agents to reliably call functions and use tool output instead of hallucinating turned out to be the real challenge.