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

Free module

Operating AI features

Learn to operate AI features hands on: context budgets, caching and cost, limits and retries, graceful failure, latency and a runbook.

7 lessons475 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

    Context budgets for a prompt

    I can decide what fits in a window and what goes first.

    Read the lesson

  2. 2 · Container lab

    Caching and the cost of an AI feature

    I can predict what a feature will cost and how much a cache saves.

    Read the lesson

  3. 3 · Container lab

    Rate limits and safe retries

    I can retry a call without causing a storm.

    Read the lesson

  4. 4 · Container lab

    Circuit breakers and graceful fallbacks

    I can keep a feature useful while its model is failing.

    Read the lesson

  5. 5 · Container lab

    Latency budgets and streaming

    I can set a latency budget and say what streaming changes.

    Read the lesson

  6. 6 · Container lab

    A weekly service level review

    I can check a feature against a service level over a week.

    Read the lesson

  7. 7 · Container lab

    Tracing AI calls with spans

    I can trace a request through an AI feature and read the trace to find what was slow, costly or failing.

    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.