Use Jupyter AI to generate code, debug errors, and get explanations—all without leaving your notebook environment.
Beginner1h14m
Jupyter AI: AI Coding in Notebooks
Instructors: Andrew Ng, Brian Granger
Earn an accomplishment with PRO · Updated Nov 3, 2025
- Beginner
- 1h14m
- 5 Video Lessons
- 3 Code Examples
- 1 Graded Assignment PRO
- Earn an accomplishment with PRO
- Updated Nov 3, 2025
- Instructors: Andrew Ng, Brian Granger
Project Jupyter- Learn more aboutMembership PRO Plan
What you'll learn
Build AI applications from scratch, including a book research assistant and a stock data analysis workflow, using Jupyter AI.
Apply AI coding best practices to guide Jupyter AI with the right context to successfully build your projects.
Course recap
PROThis course introduces Jupyter AI, an open-source framework purpose-built to integrate AI coding assistance into Jupyter notebooks and JupyterLab. Taught by Brian Granger, co-founder of Project Jupyter, alongside Andrew Ng, it demonstrates how to use the Jupyternaut chatbot for code generation, code explanation, and data analysis workflows.
Concept map
Key concepts
- Prompt EngineeringWriting detailed specifications in markdown cells to guide AI code generation, especially for complex multi-step workflows
- Tool CallingGiving LLMs access to external functions (like book search APIs) through frameworks like aisuite
- Retrieval-Augmented GenerationProviding API documentation as context files to the LLM so it can generate correct code for unfamiliar APIs
Lesson highlights
- 1.Introduction — Overview of Jupyter AI and its mission to evolve notebooks for the AI coding era
- 2.Coding with Jupyter AI — Basics of chat-driven code generation, code explanation, and providing context through cell dragging and markdown files
- 3.Building an AI Book Research Assistant — Advanced usage with Open Library API documentation, function wrapping, and tool calling with aisuite
- 4.Exploring Stock Market Data — Data analysis workflow with yfinance, matplotlib visualization, and LLM-powered insight summarization
- 5.Conclusion — Future directions including custom agents, tool calling, and agent-to-agent collaboration
About this course
Learn to use Jupyter AI as your notebook coding partner in this short course, taught by Andrew Ng and Brian Granger, co-founder of Project Jupyter.
Coding practices are shifting from manual coding to AI-assisted development, and Jupyter AI allows you to integrate AI coding into all your notebook development workflows. Many AI coding assistants struggle to function well within the notebook environment, the Project Jupyter team has introduced Jupyter AI, which is an open-source framework that deeply integrates AI coding and collaboration into Jupyter notebooks and JupyterLab.
Jupyter AI provides a chat interface that you can use to generate new cells in your notebook. You can also drag existing cells into the chat for debugging, attach files for context, and save chat histories to reuse later as additional context for your work.
In this course, you’ll build a book research assistant using the Open Library API, and create a stock market data analysis workflow, all with the help of Jupyter AI. You’ll learn how to provide API documentation as context so the LLM generates accurate syntax for code that wasn’t part of its pretraining.
In detail, you’ll use Jupyter AI to:
- Generate, refactor and explain code, including making API calls to services like OpenAI and performing statistical data analysis.
- Build a book research assistant using the Open Library API by providing Jupyter AI with the API documentation as context.
- Create a stock market data analysis workflow that you can use to perform analysis and visualization of financial data.
This course offers an early look at how Jupyter AI is reshaping coding in notebooks—and how you can start using it today!
Whether you’re a data scientist, AI developer, educator, or new to coding and you want to leverage AI coding assistance, this course gives you hands-on experience with a framework designed specifically for working with Jupyter notebooks.
Who should join?
Any AI builder who wants to learn AI-assisted coding in Jupyter notebooks. No prior experience with AI coding tools required. Basic familiarity with Python is helpful.
Course Outline
5 Lessons・3 Code Examples
Elevate your learning experience with Pro
Upgrade to Pro and gain unlimited accomplishments on your resume
Instructors
Course access is free for a limited time during the DeepLearning.AI learning platform beta!
Want to learn more about Generative AI?
Keep learning with updates on curated AI news, courses, and events, as well as Andrew’s thoughts from DeepLearning.AI!