Learn AI
▣ AN INTERACTIVE COURSE FOR ENGINEERS

Learn AI the way
you'd build it

No ML background needed. One idea runs the whole field — predict the next chunk of text, then repeat — and everything else is a refinement of it. This course is T-shaped: skim the whole map shallow first, then drive each topic deep through Bloom's six levels, ending where you build something real.

▶ Start with the Visual LabSee the whole map →
TIER 0 · THE WIRE

Start here. Broad and shallow — build intuition and a map of the whole field.

The Visual Lab

Play with the one idea that explains all of AI: next-token prediction. Tokens, temperature, embeddings, attention, RAG — all interactive.

THE FOUNDATION
The Atlas

A map of the entire AI-engineer field: nine domains, where you're strong vs. where to focus, and the Bloom ladder for going deep.

THE MAP
TIER 1 · ORIENT

Get your bearings — the tools, the timeline, and the vocabulary drill.

The Stack Map

The mid-2026 AI stack, layer by layer, with a recommended pick at each level.

TOOLS
The 4-Week Plan

A week-by-week path from where you are to interview-ready.

TIMELINE
The Recall Deck

Flip-card drill for the core vocabulary. Run it daily until it's automatic.

DAILY REPS
Fine-tuning

When to reach for it — and when prompting, RAG, or structured outputs get you there cheaper.

ORIENT
TIER 2 · GO DEEP — CORE

Each topic driven through Bloom's 6 levels: Remember → Understand → Apply → Analyze → Evaluate → Create.

Foundations

What's under the hood — past 'I've seen it' to reasoning about cost, limits, and model choice.

L1→L6
Prompting

Steering models: anatomy of a strong prompt, the escalation ladder, reusable templates.

L1→L6
TIER 2 · GO DEEP — PRIORITY

The three that compound into a flagship: a RAG app, an eval suite on it, and an agent on top.

RAG

Retrieval you can defend: chunking, vector DBs, hybrid search, reranking.

L1→L6
Evals

The #1 differentiator: golden sets, LLM-as-judge, tracing, regression gates.

L1→L6
Agents

From chatbot to coworker: the agent loop, autonomy tradeoffs, trajectory evals.

L1→L6
TIER 2 · GO DEEP — PRODUCTION

Make it real: fast, cheap, remembering, and hard to attack.

Inference & Cost

Where time and money go; the levers that turn a demo into something shippable.

L1→L6
Agent Memory

Agents that don't forget — memory as RAG over their own past.

L1→L6
Guardrails & Security

Trust nothing the model reads: prompt injection, least privilege, red-teaming.

L1→L6
Model Routing

Cheapest model that works: gateways, fallbacks, cost-aware routing.

L1→L6

Built T-shaped: the wire first, then deeper over time. Concepts are durable; frameworks are swappable — so learn the ideas deeply and treat tools as interchangeable.

Open-source · deploy your own on Vercel.