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

Free module

Securing LLM applications

Learn LLM security hands on: prompt injection, risk mapping, tool allow-lists, redacting personal data and audit logs for AI applications.

6 lessons390 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 is prompt injection

    I can add a check to my program that catches a reply taken over by prompt injection.

    Read the lesson

  2. 2 · Container lab

    Main risks of LLM applications

    I can name the main risks of a model-backed application and say where each one lives in my design.

    Read the lesson

  3. 3 · Container lab

    How to limit an LLM tool

    I can check each tool request against an allow-list policy before anything runs.

    Read the lesson

  4. 4 · Container lab

    Keeping personal data out of prompts

    I can replace personal data with placeholders before a model call and restore them afterwards.

    Read the lesson

  5. 5 · Container lab

    Audit logs and data retention for AI

    I can write audit records with no private content and delete them when their retention time ends.

    Read the lesson

  6. 6 · Container lab

    A hardened AI assistant with tools

    I can put limits, checks and an audit log round an assistant that uses tools.

    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.