The staticwebapp.config.json file
Second article in the series. We explore the staticwebapp.config.json file in depth: the fallback for Blazor, routes, redirects, headers and page protection.
[Read More]
What is an Azure Static Web App?
First article in a series on Azure Static Web Apps with Blazor. We create a Blazor WASM project and deploy it to Azure in minutes.
[Read More]
dotnet watch: you use it for hot reload. You should do more with it.
Every time I changed code, I’d Alt-Tab to the terminal, arrow up, Enter. dotnet test. Wait. Check. Back to the editor. Repeat.
It’s not the end of the world. But over a full day, it adds up, mostly in lost focus. The annoying part is that I already had dotnet watch in my workflow for hot-reloading a web app. I just never thought to ask what else it could do.
Microsoft Agent Framework: First Agent, MCP, and Multi-Agent Workflows
Microsoft Agent Framework replaces Semantic Kernel and AutoGen. Here’s how to create a local agent with Ollama, connect an MCP server, and orchestrate two agents in sequence.
[Read More]
MCP in C#: Exposing Your Own Tools to Any AI Client
MCP standardises how AI clients call external tools. Here’s how to build a working MCP server in C#: with a complete weather example, ready to connect to Claude Desktop or VS Code Copilot.
[Read More]
A Tour of My Public GitHub Repositories
A themed tour of my public GitHub repos, with a short description of each one.
[Read More]
Rebuilding My 15-Year Blog Archive Without Losing Its Memory
I rebuilt my 15-year blog archive using Hugo and Azure Static Web Apps. Here’s what mattered: don’t break old links, keep EN/FR working, and make deploys boring.
[Read More]
15 Years of Blogging: Lessons Learned
Looking back at 15 years of blogging: why consistency matters less than quality, how bilingual content builds community, and what actually drives value for your readers.
[Read More]
Building AI Agents with Ollama and .NET
Learn how to create AI agents that think, plan, and act autonomously using Ollama and .NET. Explore the ReAct pattern, tool calling, and practical agent architectures.
[Read More]
Local RAG with Ollama, LiteLLM, and Qdrant
Wire up Ollama to LiteLLM and Qdrant for local RAG: ingestion, chunking, embeddings, retrieval, and basic evaluation.
[Read More]