Books

Books on agents that act, and what they must show first

Three books in the Gradient Divergence series Foundations of Agentic AI, each with a companion repository that runs every listing it prints. The series line is the argument of all three: Autonomy should rise only as evidence rises.

Cover of Foundations of Agentic AI Systems, Volume I: Models, Learning, and Decisions, from First Principles, by Fatih Nayebi, on a navy ground Cover of Foundations of Agentic AI Systems, Volume II: Agents, Operations, and Governance, in Production, by Fatih Nayebi, on a wine-red ground

Two volumes · October 2026

Foundations of Agentic AI Systems

A book in two volumes about agents that act, and about what an agent must show before it is allowed to. One running example, a refund agent, goes from drafting decisions for a person to its launch gate. Every program the book prints, and every output it quotes, comes from the companion repository.

Volume I

Models, Learning, and Decisions, from First Principles. 455 pages.

About Volume I

Volume II

Agents, Operations, and Governance, in Production. 419 pages.

About Volume II
Volume I on Amazon Volume II on Amazon Companion code

Hardcover now. Paperback and Kindle to follow.

Cover of Foundations of Agentic AI for Retail, Third Edition, by Fatih Nayebi: white price tags hanging from a marigold rail on a lagoon-teal ground

Third Edition · October 2026

Foundations of Agentic AI for Retail

Designing, Building, and Operating Retail AI Agents, from First Principles to Production

A pricing agent marks down a winter coat in one region, exactly as its rules allow, and by morning the brand owns the outcome. The book asks when a retailer should hand a decision to software, and what evidence and controls make the handover worthwhile, from first principles to production.

Paperback on Amazon Hardcover About the book

Published by Gradient Divergence, Montréal. Earlier editions of the retail book: second edition (2026), first edition (2025).