Safer Agentic AI

“Nell Watson and Ali Hessami’s new book is just in time, offering the actionable guidance we must have to ensure AI truly aligns with human values.” * David D Luxton, Affiliate Professor, University of Washington School of Medicine *“This book is an essential read for those seeking to safeguard humanity’s future in the age of AI, serving as a reminder that we all are stewards and have a significant role to play. The book provides practical action items for agentic AI safety, combining ethical insight with governance strategies to help organizations harness agentic AI responsibly and effectively.” * Keeley A Crockett, Professor in Computational Intelligence, Manchester Metropolitan University *“With clarity and courage, Nell Watson and Ali Hessami expose how AI shapes our minds, organizations and planet and how we must build the guardrails to keep it serving life, not running it.” * Thijs Pepping, philosopher of technology, SogetiLabs and co-author of Real Fake *“Safer Agentic AI advances a pragmatic control architecture by regulating agents by what they can actually do. Imposing measurable safety gates on plans, tools, and autonomy, Nell Watson and Ali Hessami turn alignment from aspiration into auditable engineering.” * Roman Yampolskiy, author of AI: Unexplainable, Unpredictable, Uncontrollable *“Agentic AI can bring humanity into a better future - if it is governed responsibly. I can think of no one better than Nell Watson and Ali Hessami to guide us all on that crucial journey.” * Kris Østergaard, author of Transforming Legacy Organizations *“Nell Watson and Ali Hessami have produced a guide for safely and ethically engaging with agentic AI. This work presents clear descriptions of many of the ways in which human and computational intelligences interact. The authors’ approach performs a vital service for both information professionals and concerned citizens alike when they discuss these once-obscure and subtle aspects of intelligence and interactions. In doing so, they reveal points of intervention to help humans and organizations to more successfully, safely and ethically engage with computationally intelligent systems.” * Scott L David, Executive Director, Information Risk and Synthetic Intelligence Research Initiative, University of Washington *“Nell Watson and Ali Hessami address the potential risks of agentic AI. The authors provide an overview of the concepts and principles of this fast-moving technology and consider the key issues, such as how to align the behaviour of agents with human goals and values. They specifically address the topics of safety, security and ethics in the context of AI and other important aspects of controlling and governing agentic AI. The work is timely and thought provoking; without the approaches they advocate there is a risk that the development of agentic AI will outpace the community’s ability to ensure positive outcomes from its use.” * John A McDermid, Lloyd’s Register Foundation Chair in Safety, University of York *“Safer Agentic AI charts the many failure modes of current agentic AI technology, as well as potential future developments that will have to be taken into account, if we want to keep AI agents safe. This book does not limit itself to technical problems alone: it also identifies the ethical questions and coordination challenges we will need to urgently resolve, if we want to build a future where powerful AI agents create societally beneficial outcomes. It provides actionable recommendations for AI researchers, AI agent designers and policy makers alike.” * Koen Holtman, co-founder, AI Standards Lab *

Nell Watson is a researcher and applied tech ethicist. She advises organizations on their machine learning strategies, specializing in AI research and ethical advocacy. She is President of the European Responsible AI Office and the author of Taming the Machine published by Kogan Page. She lives in Belfast, UK.

Ali Hessami is a systems engineer specializing in risk analysis, assessment and safety. He is Vice Chair of the IEEE AI Ethics Certification Programme and Chair of the IEEE 7000 AI Ethics Standard. He lives in London, UK.