Python Coding With AI
Learning Path ⋅ Skills: AI, LLM Integration, Prompting, RAG, Embeddings, LangChain, LangGraph, ChromaDB, Agents, Orchestration, Chatbot, MCP
Follow this learning path to go from “I’ve tried ChatGPT in the browser” to building real LLM‑powered features, agents, and tools in Python. You’ll start by using AI as a coding partner, then move on to prompt engineering, RAG and vector databases, LangChain and LangGraph, and finally MCP‑based integrations that connect models to your own data and systems.
Along the way, you’ll keep things practical. Every step centers on concrete AI coding tools and workflows like documentation, testing, chatbots, data extraction, and automation.
This path is for you if you:
- Are an intermediate Python developer or above
- Already write Python and want to add AI features to real projects
- Want to make AI coding tools part of your daily workflow
- Need to evaluate how LLMs, agents, and MCP fit into your team’s existing Python stack
You should be comfortable with virtual environments, installing packages, and reading Python code.
By working through this Learning Path, you’ll know how to:
- Use AI coding tools (such as Claude Code, Gemini CLI, GitHub Copilot) as pair programmers inside your editor and terminal
- Offload documentation and test writing to ChatGPT while staying in control of quality
- Call LLMs from Python, use prompt engineering techniques, and tap into open‑source models with Hugging Face
- Build RAG systems using embeddings, ChromaDB, and LangChain, and deploy a full chatbot with FastAPI and Streamlit
- Design stateful AI agents with LangGraph and orchestrate multi‑step workflows
- Connect LLMs to your own data and tools using the Model Context Protocol (MCP) and MarkItDown
You can follow the sections in order or dip into individual chunks as needed.
Note: If you’re brand new to programming and Python, then start with the Python Basics Learning Path alongside the optional On‑Ramp section below, then come back and follow the rest of this Learning Path in order.
Python Coding With AI
Learning Path ⋅ 21 Resources
Optional On‑Ramp: Learn Python With AI
Use ChatGPT as a study partner while you learn Python basics. You’ll practice asking good questions, iterating on explanations, and using the model to clarify error messages and improve small code snippets without skipping the fundamentals.
Tutorial
Use ChatGPT to Learn Python Programming
Learn Python with ChatGPT! Get instant help, pair program, fix errors, and explore alternate solutions to grow your Python coding skills.
Podcast
Advice on Beginning to Learn Python
What's changed about learning Python over the last few years? What new techniques and updated advice should beginners have as they start their journey? This week on the show, Stephen Gruppetta and Martin Breuss return to discuss beginning to learn Python.
Make AI a Daily Coding Partner
Start by integrating AI into the tools you already use: your editor and terminal. Browse available tooling in the tutorials below and pick one that fits your workflow best. Capabilities are similar, focus on getting familiar with one AI-assisted tool.
Podcast
Simon Willison: Using LLMs for Python Development
What are the current large language model (LLM) tools you can use to develop Python? What prompting techniques and strategies produce better results? This week on the show, we speak with Simon Willison about his LLM research and his exploration of writing Python code with these rapidly evolving tools.
Course
Getting Started With Claude Code
Learn to set up and use Claude Code for Python projects: install, run commands, and integrate with Git.
Tutorial
GitHub Copilot: Fly With Python at the Speed of Thought
In this tutorial, you'll get your hands dirty with GitHub Copilot, a virtual pair programmer powered by artificial intelligence trained on billions of lines of code. You'll explore several practical use cases in Python for this amazing productivity tool.
Tutorial
How to Use Google's Gemini CLI for AI Code Assistance
Learn how to use Gemini CLI to bring Google's AI-powered coding assistance directly into your terminal to help you analyze and fix code.
Let AI Handle Documentation and Tests
Next, practice using LLMs to take on some of the work that developers often procrastinate: documentation and testing.
Tutorial
Document Your Python Code and Projects With ChatGPT
Good documentation is a critical feature of any successful Python project. In practice, writing documentation is hard and can take a lot of time and effort. Nowadays, with tools like ChatGPT, you can quickly document your Python code and projects.
Tutorial
Write Unit Tests for Your Python Code With ChatGPT
Learn how to use ChatGPT to generate tests for your Python code. You'll use the chat to create doctest, unittest, and pytest tests for your code.
Build Intuition for AI Models in Python
Now that AI is helping you write code, step back and learn what’s happening under the hood.
Course
Building a Neural Network & Making Predictions With Python AI
In this step-by-step course, you'll build a neural network from scratch as an introduction to the world of artificial intelligence (AI) in Python. You'll learn how to train your neural network and make accurate predictions based on a given dataset.
Tutorial
Hugging Face Transformers: Leverage Open-Source AI in Python
As the AI boom continues, the Hugging Face platform stands out as the leading open-source model hub. In this tutorial, you'll get hands-on experience with Hugging Face and the Transformers library in Python.
Prompt Engineering and LLM APIs
With model basics in place, shift back to application development and learn how to talk to LLMs effectively from Python.
Tutorial
Prompt Engineering: A Practical Example
Learn prompt engineering techniques with a practical, real-world project to get better results from large language models. This tutorial covers zero-shot and few-shot prompting, delimiters, numbered steps, role prompts, chain-of-thought prompting, and more. Improve your LLM-assisted projects today.
Retrieval‑Augmented Generation & Vector Databases
Next, extend your apps with RAG so models can answer questions using your data, not just their pretraining.
Tutorial
Embeddings and Vector Databases With ChromaDB
Vector databases are a crucial component of many NLP applications. This tutorial will give you hands-on experience with ChromaDB, an open-source vector database that's quickly gaining traction. Along the way, you'll learn what's needed to understand vector databases with practical examples.
Course
First Steps With LangChain
Large language models (LLMs) have taken the world by storm. In this step-by-step video course, you'll learn to use the LangChain library to build LLM-assisted applications.
Podcast
Leveraging Documents and Data to Create a Custom LLM Chatbot
How do you customize a LLM chatbot to address a collection of documents and data? What tools and techniques can you use to build embeddings into a vector database? This week on the show, Calvin Hendryx-Parker is back to discuss developing an AI-powered, Large Language Model-driven chat interface.
Podcast
Measuring Bias, Toxicity, and Truthfulness in LLMs With Python
How can you measure the quality of a large language model? What tools can measure bias, toxicity, and truthfulness levels in a model using Python? This week on the show, Jodie Burchell, developer advocate for data science at JetBrains, returns to discuss techniques and tools for evaluating LLMs With Python.
Agents, Tools, And Your Own Data
Once you’re comfortable with RAG, you’re ready for more complex multi‑step workflows and tool integrations.
Tutorial
LangGraph: Build Stateful AI Agents in Python
LangGraph is a versatile Python library designed for stateful, cyclic, and multi-actor Large Language Model (LLM) applications. This tutorial will give you an overview of LangGraph fundamentals through hands-on examples, and the tools needed to build your own LLM workflows and agents in LangGraph.
Tutorial
Python MarkItDown: Convert Documents Into LLM-Ready Markdown
Get started with Python MarkItDown to turn PDFs, Office files, images, and URLs into clean, LLM-ready Markdown in seconds.
Tutorial
Python MCP Server: Connect LLMs to Your Data
Learn how to build a Model Context Protocol (MCP) server in Python. Connect tools, prompts, and data to AI agents like Cursor for smarter assistants.
Tutorial
Build a Python MCP Client to Test Servers From Your Terminal
Follow this Python project to build an MCP client that discovers MCP server capabilities and feeds an AI-powered chat with tool calls.
Podcast
Dangers of Automatically Converting a REST API to MCP
When converting an existing REST API to the Model Context Protocol, what should you consider? What anti-patterns should you avoid to keep an AI agent’s context clean? This week on the show, Kyle Stratis returns to discuss his upcoming book, "AI Agents with MCP".
Podcast
Large Language Models on the Edge of the Scaling Laws
What's happening with the latest releases of large language models? Is the industry hitting the edge of the scaling laws, and do the current benchmarks provide reliable performance assessments? This week on the show, Jodie Burchell returns to discuss the current state of LLM releases.
Congratulations on getting up to speed with modern, practical AI-assisted workflows, tools, and libraries. To synthesize what you learned, set the guardrails, stay in control, and experiment with vibe coding your own Python project that leverages LLM interactions.
Got feedback on this learning path?
Looking for real-time conversation? Visit the Real Python Community Chat or join the next “Office Hours” Live Q&A Session. Happy Pythoning!
