COMPLETE LEARNING PATH

397 concepts.
Nothing important skipped.

Browse the full map, or start at concept one and simply keep moving down.

Start at AI →Practical guides
PHASE 1

FOUNDATIONS

Start before LLMs. Understand where AI, ML and neural networks fit.

PHASE 2

TRANSFORMERS & LLMs

Follow text from characters to tokens, attention, transformers and generation.

PHASE 3

PROMPTS & APIs

Understand how applications send instructions to models and handle production API behavior.

PHASE 4

KNOWLEDGE, EMBEDDINGS & RAG

Teach models to look up relevant information before answering.

PHASE 5

TOOLS, AGENTS & ORCHESTRATION

Move from a model that talks to a system that can inspect and act.

PHASE 6

FRAMEWORKS & MCP

Understand the names you will hear when teams build agentic systems.

PHASE 7

MODEL ADAPTATION

Know when to prompt, retrieve, fine-tune or compress a model.

PHASE 8

EVALS & OBSERVABILITY

Measure whether the AI is good and trace where it fails.

PHASE 9

LLMOPS & AI INFRASTRUCTURE

Operate AI like production: serving, GPUs, latency, capacity, routing and reliability.

PHASE 10

RELIABILITY & SRE

Apply familiar SRE thinking to AI dependencies and workflows.

PHASE 11

AI SECURITY

Understand how untrusted text, tools and autonomy create new attack paths.

PHASE 12

AI INCIDENTS & COST

Recognize the failure modes an AI SRE will actually troubleshoot.

PHASE 13

PRODUCTION ARCHITECTURE

Connect every term into systems you can design and operate.