So, not much work done because of picking up a kid, but I got some AI work done. Right now, it handles loading typesafe settings from the project YAML file and running plugins against files as they are loaded.

I find it interesting trying to get a typesafe collection of objects. For AI, I wanted to have each plugin be able to define its own properties.

I got that working this evening, which means I'm closer to producing something usable.

It also can pull out YAML metadata from the Markdown files, which is something I use rather heavily in my own writing.

And the final bit of coding today. I started working on the XPath-based splitter. This is what is going to break apart a chapter into paragraphs, lines, and tokens/words.

That way, an echo plugin can search for `//token[length() > 3]` to get all tokens over three characters long.

`//para//token[index() = 1]` for the first word of every paragraph. I want to use that to make sure no paragraph starts with the same word.

I figured I'm 2-4 days from seeing if this POC works.