- About the Author
- Introduction
- Chapter 1 When AI Starts Taking Action
- Chapter 2 The Secure Agent Blueprint
- Chapter 3 Connecting Agents Safely
- Chapter 4 Identity Permissions and Human Control
- Chapter 5 Protecting What Agents Know
- Chapter 6 How Agents Get Manipulated
- Chapter 7 Testing Before Trusting
- Chapter 8 Monitoring and Responding
- Chapter 9 Going Live and Staying in Control
- Putting the Book to Work
- Use Case Gallery
- Appendix A Review Worksheets
- Appendix B Ten Security Test Cards
- Appendix C A 30 60 90 Day Improvement Plan
- Appendix D Glossary
- References and Source Notes
When AI Takes Action
A Practical Guide to Securing and Governing AI Agents
What changes when an AI assistant can take action? Follow a fictional enterprise team as it works through permissions, prompt injection, testing, monitoring, and governance, using practical diagrams, published cases, and exercises to design and operate agents with clear boundaries
Minimum price
$19.00
$29.00
You pay
Author earns
PDF
EPUB
About
About the Book
Key benefits
• Map the data flows, identities, tools, and trust boundaries around an AI agent.
• Constrain tool permissions and bind human approval to the action being authorized.
• Protect retrieved knowledge and persistent memory with appropriate access controls.
• Recognize prompt injection and examine risks in connectors and software dependencies.
• Test important failure modes and preserve evidence for investigation and review.
• Plan monitoring, containment, recovery, and accountable governance for production agents.
Description
An AI agent can read a service ticket, retrieve internal knowledge, and prepare an account change. Once it can act through connected tools, a useful answer becomes a decision with consequences. The organization needs to know who authorized the work, which information the agent may use, and what it is permitted to change.
When AI Takes Action explains how to secure and govern those connections. This accessible guide follows the fictional Northbridge Services team as it develops an internal assistant and considers more capable workflows. Their decisions give architects, developers, security professionals, and service owners a practical way to examine the systems around an agent.
The nine chapters cover secure architecture, Model Context Protocol connections, identity and permissions, human approval, retrieval and memory, prompt injection, testing, operations, and governance. Published vulnerability research and incident reports illustrate concrete failures and their limits. The book distinguishes research demonstrations from reported attacks and keeps its fictional teaching scenarios clearly identified.
Fourteen technical diagrams and five conceptual illustrations help explain where authority and information cross boundaries. Each chapter closes with takeaways, leadership questions, practical actions, and a decision exercise. Eight fictional use cases explore settings such as the service desk, software delivery, finance, healthcare administration, and public services.
Seven review worksheets, ten security test cards, a 30/60/90-day improvement plan, a glossary, and 38 references help readers apply the material to their own services. You can follow the book without experience training a large language model. Familiarity with applications, identities, and business processes is enough to begin.
Who this book is for
Written for solution architects, security professionals, developers, platform teams, service owners, and technical leaders who need to design, review, or operate AI agents in organizations.
Author
About the Author
Igor van der Burgh
Igor van der Burgh is a Lead Solution Architect at Citrix with almost 25 years of experience in
information technology. His career has centered on end user computing, progressing from consultant to
field architect and then to his current role.
In recent years, Igor has increasingly focused on cybersecurity and artificial intelligence. That interest
has led him to explore how AI systems can be manipulated, how their data and connections create
exposure, and how technical choices affect organizations and the people who depend on them.
This book grew out of his own learning journey. As Igor deepened his understanding of AI security, he
wanted to turn what he learned into an accessible resource for others. His aim is to connect explanations
with practical examples and questions that readers can apply in their own work.
Drawing on his background in consulting and architecture, Igor writes for people who need to translate
technical subjects into organizational decisions. He hopes readers will use the book to examine
assumptions, start useful conversations, and identify practical improvements, whether advising
customers or strengthening security within their own organizations.
For Igor, writing is also a way to keep learning. This book reflects his belief that knowledge becomes
more valuable when it is shared and put into practice.
Connect with Igor
linkedin.com/in/igor-van-der-burgh-5284947
Contents
Table of Contents
The Leanpub 60 Day 100% Happiness Guarantee
Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
See full terms...
Earn $8 on a $10 Purchase, and $16 on a $20 Purchase
We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.
(Yes, some authors have already earned much more than that on Leanpub.)
Learn more about writing on Leanpub
Free Updates. DRM Free.
If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).
Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.
Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.
Learn more about Leanpub's ebook formats and where to read them
Write and Publish on Leanpub
You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!
Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.
Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.