Easier to read with cream paper, a tint, more contrast or larger text? Choose your colours and text, once, for every page.

Free module

Case study: shipping an AI feature

Learn shipping an AI feature hands on: write the brief, measure a first version, read evals, trace an incident, write a post-mortem and a decision log.

6 lessons360 min lessonSoftware engineering

The lessons

Each lesson is free to read in full. Create a free account to run its commands in a live lab and to sit its quizzes and tasks.

  1. 1 · Container lab

    What a brief for an AI feature contains

    I can turn a request into requirements and a way to know it works.

    Read the lesson

  2. 2 · Container lab

    Building the first version of an AI feature

    I can build the simplest version that can be measured.

    Read the lesson

  3. 3 · Container lab

    Reading eval results to choose a fix

    I can read eval results and decide what to change first.

    Read the lesson

  4. 4 · Container lab

    Finding the cause of an AI incident

    I can work out what went wrong from the trace and the logs.

    Read the lesson

  5. 5 · Container lab

    Writing a post-mortem you can check

    I can write what happened, why, and what changes.

    Read the lesson

  6. 6 · Container lab

    Keeping a decision log for an AI feature

    I can record the decisions behind a feature so others can follow them.

    Read the lesson

Worked in a real lab

Every lesson of this module is worked in a lab started for you alone. The labs it uses:

Teaching a class? Set this module for your students with a teacher guide, marked assignments and a lab for every student.