Getting started
Ollama, setup, first run. Instant gratification with Llama 3.2.
Explore→APIs & Ollama
OpenAI, Anthropic, Gemini, OpenRouter. Free options with Ollama.
Explore→Prompt engineering
System prompts, few-shot, structure. Make models do what you want.
Explore→RAG
Retrieve, augment, generate. Ground LLMs with your data.
Explore→Fine-tuning
QLoRA, adapt models to your domain. From data to custom model.
Explore→Agentic AI
Tools, reasoning, autonomy. Build systems that think and act.
Explore→Tools & Ecosystem
LangChain, vLLM, Unsloth, and more.
Explore→Resources
Handbook, agent guides, courses, books, newsletters. All-stop reference.
Explore→Revision Quiz
52 questions: transformers, inference, quantization, fine-tuning, sampling.
Explore→Your learning path
Each section has lessons, code examples, and quizzes. Progress is saved locally.
What you'll build
By the end you'll understand how to call LLMs, craft prompts, ground them in your data with RAG, fine-tune for custom behaviour, and orchestrate autonomous agents. The Week 8 capstone ties it all together — a system that reasons, uses tools, and acts.
LLM vs Inference Engineering
LLM Engineering — Building with LLMs: prompts, RAG, fine-tuning, agents. How to make models work for you.
Inference Engineering — Serving at scale: prefill, decode, vLLM, production. How to deploy fast and cheap.