What do you think?
Rate this book
Graph Engineering for Agentic AI Systems
Design the topology. Don't inherit it.Most agent systems get their shape by accident — a prompt, then a tool, then a retry, then a second agent because the first one got long. Nobody writes the topology down.
Graph engineering is the discipline of declaring it on the nodes that must exist, the edges that are legal, the state that travels with the run, and the gates that sit on every irreversible step.
Ken Huang writes for engineers who have to ship these systems and then operate them. Fourteen chapters
Execution graphs and memory graphs — and what conflating them costs youWhat actually runs under LangGraph, AutoGen GraphFlow, and ADK's Workflow RuntimeWhen a loop is the right answer and a graph is over-engineeringKnowledge graphs as durable agent memorySecurity, identity, and governance for agent graphsTesting, evaluation, and verification that survive productionThe computer science underneath — and what stays true after the name fadesEvery chapter ends in work you can run. Companion code and homework ports live on GitHub with links in the book.
About the author. Ken Huang is CEO and Chief AI Officer at DistributedApps.ai, Co-Chair of AI Safety groups at the Cloud Security Alliance and the OWASP AIVSS project, and Adjunct Professor at the University of San Francisco. He coauthored OWASP's Top 10 for LLM Applications, contributes to the NIST Generative AI Public Working Group, and has published with Springer, Cambridge University Press, IEEE, ACM, China Machine Press, Packt, and Wiley.
Graph engineering is the discipline of declaring it on the nodes that must exist, the edges that are legal, the state that travels with the run, and the gates that sit on every irreversible step.
Ken Huang writes for engineers who have to ship these systems and then operate them. Fourteen chapters
Execution graphs and memory graphs — and what conflating them costs youWhat actually runs under LangGraph, AutoGen GraphFlow, and ADK's Workflow RuntimeWhen a loop is the right answer and a graph is over-engineeringKnowledge graphs as durable agent memorySecurity, identity, and governance for agent graphsTesting, evaluation, and verification that survive productionThe computer science underneath — and what stays true after the name fadesEvery chapter ends in work you can run. Companion code and homework ports live on GitHub with links in the book.
About the author. Ken Huang is CEO and Chief AI Officer at DistributedApps.ai, Co-Chair of AI Safety groups at the Cloud Security Alliance and the OWASP AIVSS project, and Adjunct Professor at the University of San Francisco. He coauthored OWASP's Top 10 for LLM Applications, contributes to the NIST Generative AI Public Working Group, and has published with Springer, Cambridge University Press, IEEE, ACM, China Machine Press, Packt, and Wiley.
Audible Audio
Published September 13, 2026
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
No one has reviewed this book yet.