Hands-on builds

Projects

Projects

About These Projects

The best way to make the modules stick is to build something. These five projects take you from a custom chatbot through structured data extraction, a RAG chatbot for your own documents, an AI agent with tools, and finally a hands-on prompt injection challenge.

Each one is a code-along or hands-on video, so you can pause, try it yourself and adapt it to your own ideas. Pick the project that matches the module you've just finished and come back for the rest.

Projects

5 builds
01

Build a Custom Chatbot with the OpenAI API

Wire up the OpenAI API and build your own chatbot, using a system prompt to shape how it behaves, from the first call to a working product.

02

Extract Structured Data from Text with an LLM

Turn unstructured text into structured data with Python, Pydantic, and a language model, a hands-on drill for structured outputs.

03

Build a RAG Chatbot for Your PDFs

Build a retrieval-augmented generation app in Python that lets you query and chat with your own PDF documents.

04

Build an AI Agent with Tools in Python

Build an AI agent from scratch with structured output, prompt templates, prebuilt tools, and custom tool calling.

05

Test Prompt Injection with the Gandalf Challenge

Try to trick an AI into revealing a secret password in a safe, legal challenge, and see how prompt injection works in practice.