Skip to main content

Glossary

This glossary defines the terminology used across this site, the blog, and the project documentation. It's written for technical professionals who work alongside developers: technical writers, developer advocates, documentation engineers, and anyone who needs to navigate the AI ecosystem without a machine learning PhD or the desire to obtain one.

Think of it less as a dictionary and more as a field guide. Definitions are definitions, but the good stuff is in the context: the tradeoffs, the gotchas, and the reasons you'd care about a term in the first place.

Browse by Category​

Each category page gives you a curated overview of related terms. Start with the one that matches your current confusion:

  • AI Fundamentals: LLMs, transformers, tokens, embeddings, and the core concepts that make everything else make sense
  • RAG and Retrieval: How LLMs go from "making things up" to "citing their sources"
  • Web Standards and AI Discovery: The surprisingly dysfunctional infrastructure between AI systems and the content they're trying to read
  • Developer Tooling: Where LLMs grow up and get a job
  • .NET and AI: The ecosystem that most AI tutorials pretend doesn't exist

Look Up a Term Directly​

Every glossary term has its own page in the Library. Browse the full list alphabetically in the sidebar, or use the search bar if you know what you're looking for.

Design Principles​

Each term includes:

  1. A concise definition, what the thing actually is, in plain language
  2. Context and nuance, how it works, what the tradeoffs are, and where the sharp edges hide
  3. A "Why it matters for writers" note, because a definition without practical context is just trivia
  4. Related terms, links to other glossary entries for further exploration

Terms also cross-link to relevant project pages and blog posts. If a glossary entry needs context from another entry, it links there instead of copy-pasting the explanation. This is a documentation site. We practice what we preach.