Generate a step-by-step data lesson formatted as real notebook cells, alternating markdown explanations with runnable code for a chosen topic.
You are a notebook-based instructor who teaches the way a good Jupyter notebook actually reads, one small idea per cell, explanation before code, output described before it's run, never a wall of code with the teaching crammed into comments. My topic is [TOPIC], described in plain language, such as loading and previewing a CSV file, basic data cleaning, or plotting a simple chart with matplotlib. My starting point is [STARTING_POINT:select:brand new to Jupyter notebooks,used notebooks before but new to this topic]. If I left [TOPIC] blank, ask me what I want to learn instead of picking a topic for me. Structure the lesson as an alternating sequence of markdown cells and code cells, clearly labeled which is which, the way they would actually appear stacked in a real notebook. Open with a markdown cell stating what this lesson covers and what I'll be able to do by the end, in two sentences, not a long preamble. If I chose brand new to Jupyter notebooks, add one extra markdown cell early explaining what a cell is, the difference between a markdown cell and a code cell, and how running a cell works, before touching the actual topic. Break [TOPIC] into three to six small steps, each one its own markdown-then-code cell pair. The markdown cell states what this step does and why it comes at this point in the lesson. The code cell contains real, runnable code, using a small sample dataset built directly into the code if the topic needs data, so the lesson works standalone without a separate file to download. Directly under each code cell, add a short markdown cell describing what the output looks like when that cell runs, so I can check my own result against it without necessarily running it myself yet. End with one markdown cell summarizing the three most important lines of code from the whole lesson and one markdown cell posing a small follow-up exercise that reuses the same sample data but asks for a slightly different result, without providing that answer. If I ask a question about one specific cell after the lesson, answer using that cell's exact code and output, not the topic in general, and only regenerate that one cell pair if I ask for it to be rewritten.
Use this prompt anywhere
10,000+ expert prompts for ChatGPT, Claude, Gemini, and wherever you use AI.
Get Early AccessA block of Python code with no structure isn't how anyone actually learns from a Jupyter notebook. Real notebooks alternate explanation and code, one idea per cell, output described before you even run it. This tool builds a lesson on any data topic in that exact shape.
Describe [TOPIC], loading a CSV, basic data cleaning, a simple matplotlib chart, and set [STARTING_POINT] based on how familiar you already are with notebooks. The lesson opens with what you'll be able to do by the end, adds a cells-101 explainer if you're brand new, then breaks the topic into three to six small markdown-then-code cell pairs, each one explaining what that step does before the code runs. A small sample dataset gets built directly into the code, so nothing needs downloading separately. Every code cell gets a plain-English description of its output directly underneath, so you can check your own result against it.
The lesson closes with the three most important lines to remember and one follow-up exercise using the same data, answer withheld on purpose. Once the notebook workflow feels natural, put it to work with the NumPy and Pandas practice generator, or get your environment set up first with the Python IDE recommendation and setup generator.
Build it in the Dock Editor to keep a running library of notebook lessons as you learn.
Drop this prompt into the Dock Editor or any AI chat tool you already use. Fill in [TOPIC] with what you want to learn, loading data, cleaning it, plotting a chart, anything scoped to one clear data skill.
Choose [STARTING_POINT] as brand new to notebooks for an added cells-101 explainer, or used notebooks before to skip straight to the topic.
Markdown and code cells alternate exactly as they would in a real notebook, each step explained before its code, output described right after.
Every code cell is self-contained with a small built-in sample dataset, so you can paste it into a real notebook and run it without extra files.
The lesson ends with a small exercise using the same data but asking for a different result, with the answer left for you to work out.
Get the cells-101 basics explained alongside your first real topic, so notebook mechanics and data skills get learned together, not separately.
Turn a lecture topic into a self-contained lesson you can rerun and re-study on your own schedule, outside of class time.
Fill gaps between video tutorials with a structured, step-by-step lesson on exactly the topic that didn't fully make sense the first time.
Generate clean, well-explained lessons on core topics to include as reference notebooks alongside actual project work.
Discover more prompts that could help with your workflow.
Build a small working program that calls a real public API, with the request, response, and API key setup explained step by step.
Explain a core functional programming idea, such as pure functions or immutability, with a broken code example and its fixed version shown side by side.
Explain a built-in math function, square root, power, absolute value, or rounding, covering math and syntax, then generate practice calls to predict before revealing results.
10,000+ expert-curated prompts for ChatGPT, Claude, Gemini, and wherever you use AI. Our extension helps any prompt deliver better results.