🤖 AI Explained
🤖

How AI Agents Work

The foundational model — what LLMs actually are, how tools extend them, and how the request/execute/return loop powers every AI agent you'll ever build or use.

18 lessons · ~177 min total

Lessons

1

Architecture Overview — For New Developers

The big picture of how AI agents work — three simple building blocks that turn a text predictor into something that can actually do things.

8 min
2

Architecture Overview — For SRE / DevOps

The runtime architecture of an AI agent — process model, trust boundaries, transport layers, and where each component fits in your infra.

8 min
3

Architecture Overview — For Tech Leaders

The three-layer model that powers every AI agent — and the architectural decisions each layer puts on your plate.

6 min
4

Architecture Overview — For Experienced Developers

How tools, skills, and MCP stack together — the three extensibility primitives, the host routing layer, and the mental model that ties them all.

8 min
5

What is an LLM — For Experienced Developers

The transformer architecture, tokenization mechanics, and inference pipeline — everything you need to understand how LLMs actually work under the hood.

12 min
6

What is an LLM — For New Developers

A plain-language introduction to Large Language Models — what they are, how they work at a high level, and why they matter for the code you'll write.

10 min
7

What is an LLM — For SRE / DevOps

LLMs from an infrastructure perspective — resource requirements, inference costs, latency characteristics, and what you need to know to run them reliably.

10 min
8

What is an LLM — For Tech Leaders

The accurate mental model for Large Language Models — what they actually are, what they can and can't do, and what that means for your technical strategy.

8 min
9

Tools — For New Developers

How AI models interact with the real world — the request/execute/return loop explained from scratch with simple examples.

12 min
10

Tools — For Tech Leaders

What tools mean for AI architecture — the trust model, the control boundary, and what it means that the model never executes anything directly.

8 min
11

Tools: A Deep Dive

What tools actually are, how the request/execute/return loop works, parallel calls, error handling, and how to write tool definitions that the model uses correctly.

15 min
12

MCP — For New Developers

How AI agents connect to the outside world — MCP explained from scratch with plain-language examples and diagrams.

12 min
13

MCP — For Tech Leaders

Why MCP matters for your AI strategy — the standard protocol that eliminates vendor lock-in and turns N×M integration problems into N+M.

8 min
14

MCP: Model Context Protocol

The open protocol that standardizes how AI agents connect to external systems. JSON-RPC internals, transports, the three primitives, and how to build a custom server.

20 min
15

Skills — For Experienced Developers

Just-in-time retrieval-augmented prompting — how skill files work, how to structure them, and how they compare to RAG and fine-tuning.

10 min
16

Skills — For New Developers

What skill files are, why they exist, and how to create your own — giving AI agents expert knowledge exactly when they need it.

8 min
17

Skills — For SRE / DevOps

Skills from an infrastructure perspective — file layout, context budget, performance implications, and managing skill files across teams.

8 min
18

Skills — For Tech Leaders

How skills keep AI agents lean and expert at the same time — just-in-time knowledge loading as a context management strategy.

6 min
Start module →