🌍 Real-World Projects
Everything in the course so far ran in a sandboxed, in-browser playground — so you could start writing Python on day one with zero setup. These projects are the graduation step: install Python for real on your own machine, then build something the playground could never run.
They're optional and ungraded. Browse them any time — each project's intro says what background it expects (usually Python 101, sometimes Data Analysis too), so you don't need to have finished the whole course first. New projects are added whenever a trending tool or framework is worth a real, hands-on write-up — not on a fixed schedule.
Fine-tune a Small Language Model
July 2027
Fine-tune a small open-source language model with LoRA using Unsloth, on a free Colab/Kaggle GPU.
Scrape and Analyze a Live Website
October 2026
Scrape a real, scraping-friendly website with requests and BeautifulSoup, then clean and chart the results with pandas and matplotlib — no API key needed.
Train Your First Machine Learning Model
September 2026
Go from describing data to predicting from it: train and compare binary classifiers with scikit-learn on the Titanic dataset from Data Analysis Week 10.
Build an MCP Server
August 2026
Build a Model Context Protocol server exposing your own tools, and connect it to a real AI client like Claude Desktop.
Build a RAG App Over Your Own Notes
July 2026
Chat with your own notes: local embeddings with sentence-transformers, NumPy similarity search, and a free-tier LLM for the final answer.
Build an AI Agent
June 2026
Install Python for real and build your first AI agent with LangChain's deepagents, using a free-tier API key.