AI & LLM Terminology & Architecture
Master 60+ essential AI, LLM, RAG, agentic, fine-tuning, safety, and LLMOps terms with architectural diagrams, code examples, self-checks, and exercises.
This free, self-paced course is designed for beginner learners in ai & machine learning. Work through the lessons in order, use the objectives below as a checklist, and practice against real systems rather than memorizing slide labels. Estimated time: ~2.5 hours across 6 lessons.
Prerequisites
- Interest in AI engineering, LLM application architecture, or system design
- Basic understanding of JSON, REST APIs, or Python/TypeScript code snippets
Course Curriculum
Each lesson is a focused read. Open one, complete any self-checks or exercises, then mark progress in this browser before moving on.
AI & LLM Fundamentals: Models, Tokens & Context Windows
22 min
RAG & Knowledge AI: Embeddings, Vector DBs & Reranking
24 min
Agents, Tools & Model Context Protocol (MCP)
25 min
Training, Fine-Tuning, LoRA & Quantization
24 min
Alignment, Safety & Security: RLHF, DPO & Guardrails
22 min
Vision, Audio & LLMOps: Evals, Observability & Scaling
20 min
Related articles
Pair this course with deeper guides on the same topic. Articles include diagrams, failure modes, and decision rules.
- Documentation MCP Servers: How Context7 Eliminates AI API Drift
- Gastown Architecture: Multi-Agent Factory vs Normal Sessions
- LLM Internals: Pretraining, Tokenization, SFT, and RLHF
- AI Agents for Coding: Tools, Swarms, Protocols, and Workflows
See the full AI, LLM & Agentic Systems topic hub.