Skip to content
calwm

Red pen: Fundamentals of AI and ML

Exam answers on Fundamentals of AI and ML are often almost right. Each round hands you a short document with a few mistakes hidden in it. Mark the faulty lines, say why each one is wrong, and see what a good version would say.

Find the mistake before the auditor does.

Grab the red pen2 documents, about 4 min

What you will practise

You will practise Fundamentals of AI and ML, with questions touching AI use cases and ML lifecycle.

  • AI use cases
  • ML lifecycle

It is part of the AWS Certified AI Practitioner track (AIF-C01), where Fundamentals of AI and ML is about 20% of the exam.

A taste of what you will get

  • Priya's team phones every customer the model flags. Only 5% of customers cancel each quarter.

    Sample document 1: Raj's report on the churn model. Which lines are wrong, and why?

    • Goal: flag customers likely to cancel next quarter
    • Data: two years of customer history, each labelled cancelled or stayed
    • Testing: scored on the same customers it was trained on, 99% accurate
    • Headline metric: accuracy
    • Next step: check performance monthly and retrain when it drops

    Answer: Line 3 (Testing: scored on the same customers it was trained on, 99% accurate): It only shows how it does on customers it has already seen. Better: Hold back a test set the model never sees in training, and report that score. Line 4 (Headline metric: accuracy): With 5% leaving, flagging nobody is already 95% accurate. Better: Lead with recall: of the customers who really left, how many it caught.

  • Marco wants AI wherever it saves time. Dana wants it only where it earns its keep.

    Sample document 2: Marco's AI wish list for operations. Which lines are wrong, and why?

    • Forecast next month's demand for each product from three years of sales
    • Train a model to work out payroll tax from the published tax tables
    • Use clustering to predict next month's total sales in dollars
    • Group customers by buying pattern, with no labels, for targeted offers
    • Flag invoices likely to be paid late, based on past labelled invoices

    Answer: Line 2 (Train a model to work out payroll tax from the published tax tables): Known, exact rules: a calculation is cheaper and auditable. Better: Calculate tax with rules from the published tables, and keep ML for predictions. Line 3 (Use clustering to predict next month's total sales in dollars): Predicting a number is regression; clustering finds groups. Better: Use a regression model to predict the dollar total.

Advertise here

How scoring works

  • Every correct answer pays 10 XP for each difficulty level, so an easy item is worth 10, a medium one 20 and a hard one 30.
  • Answer with time to spare and you can earn up to 5 bonus XP on top.
  • A wrong answer pays nothing. It does not cost you anything either.
  • Flashcards pay 2 XP each time you grade yourself 3 or higher.
  • Using a hint costs 2 XP, so use it when it helps, not when it is comfortable.
  • Finish a session on consecutive days to build a streak. Your progress lives in your browser, and signing in syncs it.

Quick answers

How long does the red pen on Fundamentals of AI and ML take?
About 4 minutes for 2 documents. Pause whenever you like.
Do I need an account to play the red pen?
No. Progress is saved in your browser, and signing in syncs it across devices.