AI
Evals aren't a step at the end. They run the whole way through
There’s a version of building an AI app that goes like this. You build the thing, you get it …
Four ways to run an eval, from a cheap unit test to a full-blown agent
Someone asked me last week how you actually run an eval on an AI app. I gave the honest answer, …
I built a little Claude that dances when it needs me
I’ve got into a bad habit lately. I set Claude Code off on some task - refactor this, write …
How to build an eval you can actually trust
Here’s how most people build an eval. They open a file, write an LLM judge prompt that says …
Twenty-seven years ago I nearly put six people out of work with an Excel spreadsheet
Twenty-seven years ago I nearly put six people out of work with an Excel spreadsheet.
Every AI …
Enhance GitHub Copilot CLI with skills
Coding agents like GitHub Copilot are pretty cool. You can ask them to do pretty much anything …
Build a Star Wars Copilot in C# - Lesson 8: Agents and Orchestration
Final lesson, and probably my favorite.
We move from a copilot with tools to a system that also uses …
Build a Star Wars Copilot in C# - Lesson 7: Multimodal Image Generation
Lesson 7 brings multimodal capabilities into the stack.
Instead of only generating text, the copilot …
Build a Star Wars Copilot in C# - Lesson 6: RAG from a Database
By lesson 6, we already have an MCP server and client working.
Now we add a classic enterprise use …
Build a Star Wars Copilot in C# - Lesson 5: MCP (Model Context Protocol)
Lesson 4 gave us tool calling inside the app.
Lesson 5 takes the next architectural step: move tools …
Build a Star Wars Copilot in C# - Lesson 4: Tool Calling
LLMs are smart, but they’re also confidently wrong sometimes.
Lesson 4 fixes that by giving …
Build a Star Wars Copilot in C# - Lesson 3: Model Choice and Local Models
One of the biggest advantages of the architecture so far is that we’re coding against …