BLOG
Notes from practice.
What we learn while we build — AI patterns, migrations, a few market observations. Writing helps us sort what we have learned.
More articles
-
Methodology AI in the office: 6 quick wins you can implement today
If you think of "artificial intelligence" as ChatGPT helping you draft emails, you've only seen the tip of the iceberg. The real strength of AI sits where day-to-day office work actually hurts: with the repetitive, time-consuming tasks no one likes doing but everyone has to do.
-
AI patterns Pragmatic Claude Code Usage for C# Developers on Mac
Claude Code works excellently for C/.NET development on Mac – despite the Python/TypeScript focus of coding LLMs. The key lies in targeted context engineering: skills for C code standards, a PRD-based workflow (Plan → Generate → Code), Git worktrees
-
AI patterns Markdown for Agents
AI agents are increasingly the primary "reader" of web content — and they prefer Markdown to HTML. This article is for web developers and DevOps engineers who want to optimise their websites for AI agents without depending on a specific host.
-
AI patterns C#/.NET MCP server demo
Anthropic's Model Context Protocol (MCP) is reshaping the integration of AI models with external tools and data sources. While most available demo implementations are based on Python or TypeScript, this C#/.NET project shows how MCP integrates cleanly into the Microsoft ecosystem.
-
Methodology From prompt engineering to context engineering
Prompt engineering describes the craft of shaping a single text input ("prompt") so that a large language model (LLM) responds as well as possible. Since the arrival of GPT-3.5, developers have spent countless hours fine-tuning wording, optimising the order of prompt elements, or refining system instructions.
NEWSLETTER
Four to six times a year, no marketing noise.
One pattern, one case, one recommendation. Signup with double opt-in, unsubscribe at any time.