Learn AI: The Modern AI Application Stack
Modern AI application engineering combines models with retrieval, tools, data and workflows. Here is every building block explained simply.
- 01 LLMs
- 02 Prompting
- 03 Embeddings
- 04 Vector Search
- 05 Vector Database
- 06 RAG
- 07 Tool Calling
- 08 AI Agents
- 09 Agentic Workflows
- 10 MCP
LLM
What is an LLM (Large Language Model)?
A model trained to understand and generate language.
ReadEmbeddings
What are Embeddings?
Meaning converted into numbers.
ReadVector Database
What is a Vector Database?
Search by meaning, not just exact words.
ReadRAG
What is RAG (Retrieval-Augmented Generation)?
Ground AI answers in retrieved information.
ReadAI Agent
What is an AI Agent?
AI that plans, uses tools and acts toward a goal.
ReadMCP
What is MCP (Model Context Protocol)?
A standard way to connect AI to tools and data.
ReadDon't Confuse Them: RAG vs Agents vs MCP
| Concept | What it does |
|---|---|
| LLM | Understands & generates |
| Embeddings | Represent meaning |
| Vector DB | Stores / searches vectors |
| RAG | Retrieves relevant knowledge |
| Tool Calling | Interacts with tools |
| AI Agent | Uses tools toward a goal |
| Agentic AI | Multi-step AI workflow |
| MCP | Standardized connection |