Assurance of AI and Autonomous Systems: a Dstl biscuit book

A simple guide to understanding and describing the trustworthiness of autonomous systems and associated artificial intelligence (AI) algorithms.


Assurance of Artificial Intelligence and Autonomous Systems: a Dstl biscuit book

This file may not be suitable for users of assistive technology.

Request an accessible format.
If you use assistive technology (such as a screen reader) and need a version of this document in a more accessible format, please email Please tell us what format you need. It will help us if you say what assistive technology you use.


This guide has been written by the Defence Science and Technology Laboratory (Dstl) to help the people we work with think about how we assure AI and autonomous systems. We work with our partners and suppliers to deliver research on AI and autonomy, and aim to understand how we can responsibly and safely apply these techniques to a wide range of defence and security challenges.

This guide explains how we work out how confident we are about the safety and trustworthiness of a system or algorithm, and how we describe and communicate our findings.

It is one of a series of biscuit books, designed to be dipped into and easily digested - just like a biscuit with tea.

Published 12 October 2021
Last updated 1 December 2021 + show all updates
  1. Added PDF version.

  2. First published.