30 AI Engineering Terms Explained in Plain English

Learn 30 essential AI engineering terms explained in plain English through this comprehensive 24-minute video tutorial. Master fundamental concepts including Large Language Models (LLMs), prompts, and prompt engineering, then progress to advanced topics like context windows, tokens, and inference processes. Explore critical AI safety concepts such as prompt injection, guardrails, and hallucinations, while understanding evaluation methods (evals) and Retrieval-Augmented Generation (RAG) systems. Dive into technical components including semantic search, embeddings, chunks, and vector databases, followed by cutting-edge developments in AI agents, agentic AI, and multi-agent systems. Discover the Model Context Protocol (MCP), Agent2Agent (A2A) communication, and multimodal AI capabilities. Conclude with advanced training concepts including reasoning models, fine-tuning, distillation, foundation models, and train-time compute optimization. Each term receives clear, jargon-free explanations with timestamps for easy navigation, making complex AI engineering concepts accessible to learners at all levels.

Syllabus

Intro - 0:00
1 Large Language Model LLM - 0:08
2 Prompt - 0:42
3 Prompt Engineering- 1:13
4 Context Window - 2:04
5 Context Engineering - 3:25
6 Token - 3:59
7 Inference - 5:30
8 Parameter - 6:00
9 Prompt Injection - 6:52
10 Guardrails - 8:00
11 Hallucination - 8:45
12 Evals - 9:10
13 RAG - 10:11
14 Semantic Search - 10:42
15 Embedding - 12:03
16 Chunk - 13:10
17 Vector Database - 14:33
18 AI Agent - 15:01
19 Agentic AI - 15:18
20 Agentic RAG - 16:13
21 Model Context Protocol MCP - 16:47
22 Agent2Agent A2A - 18:11
23 Multi-agent System - 18:47
24 Multimodal AI - 19:36
25 Reasoning Models - 20:10
26 Fine-tuning - 20:43
27 Distillation - 21:45
28 Foundation Model - 22:04
29 Train-time Compute - 22:33
30 Train-time Compute - 22:58