AI Fundamentals

beginner 5 hours

The concepts every AI developer needs

Build a solid foundation in AI/LLM concepts. Understand how language models work, what embeddings are, how tools extend capabilities, and why type safety matters for AI applications.

For: Developers

What You’ll Learn

• Understand what happens when you call an LLM API
• Explain tokens, attention, and context windows
• Implement semantic search using embeddings
• Build a tool that an LLM can call
• Design type-safe schemas for AI outputs

Modules

1

How LLMs Work

Demystify language models by understanding tokens, prediction, attention, and context windows. No PhD required.

30 min

2

Vectors & Embeddings

Learn how text becomes numbers that capture meaning. Understand embeddings, vector databases, and how they power semantic search and RAG.

35 min

3

Tools & MCP

Extend LLM capabilities beyond text generation. Learn how tool calling works, build your own tools, and understand the Model Context Protocol.

35 min

4

Type Safety for AI

Learn to constrain AI outputs with schemas. Master JSON Schema, Zod, and Pydantic to build reliable, type-safe AI applications.

40 min

Concepts Covered

Fundamentals

Tokens & Tokenization beginner

LLMs process text as tokens — chunks of characters that form the atomic units of input and output, directly affecting pricing and context limits.

10 min

Context Windows beginner

The context window is the maximum amount of text (in tokens) an LLM can 'see' at once, including prompts, history, injected documents, and responses.

12 min

Attention Mechanism intermediate

The core mechanism that allows language models to understand how words relate to each other by dynamically focusing on relevant parts of the input.

15 min

Embeddings & Vector Representations beginner

Embeddings convert text into numerical vectors that capture semantic meaning, enabling similarity search, clustering, and the foundation for RAG systems.

15 min

Retrieval-Augmented Generation (RAG) intermediate

RAG combines document retrieval with LLM generation, allowing AI to answer questions grounded in your specific data without fine-tuning.

20 min

Structured Outputs & JSON Schema beginner

Constrain AI responses to follow a specific format using JSON Schema, enabling reliable data extraction and type-safe integrations.

15 min

Protocols

Tool Use & Function Calling intermediate

Tool use enables LLMs to interact with external systems by generating structured function calls that applications execute and return results for.

15 min

Model Context Protocol (MCP) intermediate

MCP is an open protocol by Anthropic that standardizes how AI applications connect to data sources and tools through a unified server architecture.

12 min

Type Systems

JSON Schema for Structured Outputs beginner

JSON Schema defines the exact structure and constraints for LLM outputs, ensuring type-safe, validated responses without post-processing guesswork.

15 min

Decision Guides

Chat vs RAG vs Agent beginner

When should I use a simple chatbot vs RAG vs an autonomous agent?

20 min

Fine-Tuning vs RAG intermediate

Should I fine-tune a model or use RAG for domain-specific knowledge?

20 min

LangChain vs Custom Implementation intermediate

Should I use LangChain (or similar frameworks) or build custom?

15 min