In partnership with
It took me years to get confident with Python. Today I think you can do it in a couple of months — not because Python got easier (it did not), but because AI changed how we learn.
The problem is most people use AI to skip the learning. And then wonder why they still can not write a line of code without it.
This week's YouTube video walks through how I would actually approach it. But here is the short version.
Before we proceed - a small ad. Your clicks on the ads help to cover newsletter hosting fees and make me $1. Thank you!
100+ Claude Code hacks to ship code 10X faster
Top engineers at Anthropic and OpenAI say AI now writes 100% of their code.
If you're not using AI, you're spending 40 hours doing what they do in 4.
These 100+ Claude Code hacks fix that and help you ship 10x faster.
Sign up for The Code and get:
100+ Claude Code hacks used by top engineers — free
The Code newsletter — learn the latest AI tools, tips, and skills to code faster with AI in 5 minutes a day
The rule
Never ask AI to do the thinking you are trying to learn.
If you are learning loops, do not ask AI to write the loop. If you are learning pandas, do not ask AI to solve the pandas problem.
It is like going to the gym and asking someone else to lift the weights for you. You do not get any stronger. Learning things works exactly the same way.
If AI writes the code, you did not learn Python. You learned how to copy and paste. And I can’t stress enough how important to learn foundations. Because AI still makes mistakes and overcomplicates things. That’s why you can use AI to help you doing your work, but you still need to be able to tell when it produces nonsense.
1. Set AI up as your tutor.
Before you ask AI anything, set the context. Type something like this:
"Act as a Python tutor for a complete beginner. When you introduce something new, explain it and show a small example. But once I am trying to use something I have already learned, do not give me the answer straight away. Ask me what I would try first, give me a hint if I am stuck, and only show the full solution if I have made a real attempt and I am still lost."
Also with AI it is important to assign a role ‘act as a python tutor/ marketing manager / film editor’ in your prompt - this improves the results you get from AI.
Use AI to explain new concepts, create small exercises, and review your code when you are stuck. But do not ask it to solve the problem before you have genuinely tried.
2. Get a tailored study plan
Generic roadmaps fail because they are built for someone with eight free hours a day — not someone squeezing in forty minutes after work. You have your own life commitments and circumstances, so do not ask AI for a roadmap. Ask it for your roadmap that fits your busy schedule.
"Act as an experienced Python instructor. Help me learn Python for data analysis. I can study for 45 minutes on weekday evenings and two hours on Sundays. I already know Excel and SQL but have never written Python before. Build me an 8-week plan that fits this schedule. Focus on the 20% of Python I will actually use as a data analyst, tell me what I can safely skip for now, include one small project each week, and suggest a quick way to check I have understood each topic before moving on."
Adjust the time and your background to match your situation.
3. Work on a project you actually care about
I learnt coding by working on real projects, and I believe this is the most efficient way - learning by doing.
You can watch tutorials for months and still freeze when you open a blank notebook. That is because tutorials create the illusion of understanding. You follow every step and it all makes sense — but the moment you have to decide what to do next by yourself, you realise how much you were borrowing from the instructor.
Projects expose those gaps. That is exactly why they work.
Start with something small and connected to something you actually care about. Football, personal finance, books, social media — it does not matter. Do not force yourself to analyse the Titanic dataset if you do not care about it.
"I am interested in [topic]. Suggest three beginner Python projects I can complete in a few hours that will help me practise pandas and data visualisation. For each one, tell me what the final output should be and which Python skills I will use."
4. Debug without just asking for the answer
Here is the part most people miss.
AI does not know when it is wrong. It can explain something completely confidently, invent a function that does not exist, use an outdated library, or write code that almost works but quietly gives you the wrong answer. That’s why learning fundamentals is essential.
Treat AI like a colleague who can make mistakes. When a colleague sends you code, you do not assume it is perfect. You read it, you run it, you test it. Do exactly the same with AI.
When something fails, do not immediately paste the error back and say "fix it." Read the error first and try to fix it yourself. Then ask:
"I am getting this error. Explain what it means, why it happened, and what I should check before changing the code."
You will learn far more than if you just ask for another solution.
The full video is out this week
I walk through all four steps in today’s video.
Watch it here → link
Keep pushing 💪,
Karina
Just starting with Python? Wondering if programming is for you?
Master key data analysis tasks like cleaning, filtering, pivot and grouping data using Pandas, and learn how to present your insights visually with Matplotlib with ‘Data Analysis with Python’ masterclass.
Already know the basics and want something more hands-on?
Take the Python Challenge.
You'll work through a real business problem, complete a portfolio-ready project, and practise the kind of analysis employers expect from junior analysts.
👉 Start with the Masterclass if you're a complete beginner.
👉 Choose the Python Challenge if you're comfortable with the fundamentals and want to apply them to a real project.
Data Analyst & Data Scientist
