Guided Courses

Tracks

Learn it in order

buildarchitecturecode
0/23

Building RAG Systems

Ground language models in your own knowledge — retrieval, reranking, evaluation, and production, end to end.

23 lessonsStart →
understandtheory
0/14

Tokenization, Inside and Out

BPE, WordPiece, Unigram, SentencePiece, tiktoken — every algorithm, every tradeoff, every production implication.

14 lessonsStart →
understandtheorycode
0/16

Attention Mechanisms, from First Principles

Self-attention, multi-head, KV cache, MQA, GQA, MLA, FlashAttention — the complete mechanism that makes transformers work.

16 lessonsStart →
understandtheoryarchitecture
0/16

The Transformer Architecture

From 'Attention Is All You Need' to GPT-4 and Llama 3 — every layer, every design choice, every scaling decision.

16 lessonsStart →
buildcodearchitecture
0/12

Prompt Engineering and Context Design

System prompts, structured outputs, chain-of-thought, and the context engineering patterns that make LLMs reliable in production.

12 lessonsStart →
buildarchitecturetheory
0/17

Vector Databases, Inside and Out

Algorithms, architecture, and operations — from HNSW internals to production at scale.

17 lessonsStart →
buildcodearchitecture
0/16

AI Agents in Production

From the agent loop to multi-agent systems — LangGraph, MCP, tool calling, memory, and the guardrails that make agents safe to ship.

16 lessonsStart →
shipcodearchitecture
0/14

LLM Evaluation and Testing

Golden datasets, LLM-as-a-judge, regression testing, and CI/CD gates — the engineering discipline that separates demos from products.

14 lessonsStart →
shipcodeops
0/14

LLM Fine-Tuning for Production

LoRA, QLoRA, dataset engineering, and the decision framework for when fine-tuning is the right answer — and when it isn't.

14 lessonsStart →
shipopsarchitecture
0/15

LLMOps: Serving and Operating LLMs

Model serving, inference optimization, guardrails, observability, and cost control — the engineering that keeps LLM systems running.

15 lessonsStart →
evolvearchitecturecode
0/14

Loop Engineering and Agent Harnesses

Harness design, context management, subagent orchestration, evaluation-as-steering, and the Claude Agent SDK — the infrastructure layer that makes agents reliable.

14 lessonsStart →
evolveopsarchitecture
0/14

Autonomous and Headless Agents

Durable execution with Temporal, event-driven triggers, sandbox isolation, crash recovery, and the governance framework for agents that run without human oversight.

14 lessonsStart →
evolvearchitecturecode
0/13

Self-Improving AI Systems

Automated prompt optimization, log-driven harness patching, principle extraction, memory-driven evolution, and the governance framework for systems that modify themselves.

13 lessonsStart →
evolvearchitectureops
0/13

Compound AI Systems

Multi-model routing, cascading, the classifier-generator-verifier triad, AI gateways, protocol composition, and the systems engineering that turns models into products.

13 lessonsStart →