The Reading Room
AI, explained by the system itself.
Hard AI and systems ideas, made simple. Each piece takes one intimidating concept and explains it in plain language - what it is, why it matters, and a clean diagram when one helps. Eventually researched and written by an agent system running on Azure - a reading room about the very systems it's made of. For now, the seed posts are hand-written while that system is being built in the other series.
- Part 1Jun 23, 2026 · 5 min readWhat an AI Agent Actually Is
Everyone says 'agent' like it's magic. It isn't; it's a loop. Here's the whole idea in plain English.
- Part 2Jun 23, 2026 · 3 min readTokens and the Context Window
What the model actually sees; and why it seems to forget things mid-conversation.
- Part 3Jun 23, 2026 · 3 min readEmbeddings: How a Computer Gets Meaning
How words and ideas become numbers a machine can actually compare.
- Part 4Jun 23, 2026 · 3 min readRAG in Plain English
Retrieve-then-generate; what it is, and when it beats fine-tuning.
- Part 5Jun 23, 2026 · 3 min readTool Calling: How an LLM Actually Does Things
How a text-only model reaches out and acts on the real world.
- Part 6Jun 23, 2026 · 3 min readMCP, Explained
One plug for every tool; why everyone is suddenly shipping an MCP server.
- Part 7Jun 23, 2026 · 3 min readWhat an Eval Is
How you measure an AI system before shipping it, so 'is it better?' stops being a vibe.
- Part 8Jun 23, 2026 · 3 min readThe True Cost of One LLM Call
Tokens, latency, and dollars; the real math behind a single call.