About this ebook
- Design a security control plane for long running agents and delegated multi-agent work
- Contain prompt injection and memory poisoning through enforceable trust boundaries
- Use HarnessLab scenarios to connect design patterns with observable control decisions
- Set autonomy budgets and risk based human approval gates
- Scope agent identities, credentials, and delegation chains
- Bind tool authority to intent and detect goal drift
- Contain prompt injection and govern persistent memory
- Use decision traces and evals to govern agent improvement
- Steer live runs and enforce fleet and data boundaries
For AI engineers, security architects, platform teams, and technical leaders designing or governing long running agentic AI systems. Researchers and graduate students will also benefit from its pattern based treatment of agent security and control. Familiarity with LLM applications, tool calling, access control, and distributed systems is recommended. The book supports readers moving from agent prototypes to accountable enterprise operations.
Discover more
About the author
Ken Huang is an author and researcher in AI applications and agentic AI security, serving as CEO and Chief AI Officer at DistributedApps. He is Co-Chair of AI safety groups at the Cloud Security Alliance and the OWASP AIVSS Project, and Co-Chair of the AI STR Working Group at the World Digital Technology Academy. He is an EC-Council instructor and Adjunct Professor at the University of San Francisco, teaching GenAI and agentic AI security to data scientists. He co-authored OWASP's Top 10 for LLM Applications and contributes to the NIST Generative AI Public Working Group. His books are published by Springer, Cambridge, Wiley, Packt, and China Machine Press. A frequent global speaker, he participates in major technology and policy forums.
