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, Third Edition

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

When should a retailer hand a decision to software?

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 AmazonHardcover on Amazon Companion code

Paperback in other stores: US · CA · UK · DE · FR · IT · ES · JP

About the book

It follows the Retail Agent Operating Model through agent architectures, decision frameworks (probabilistic, sequential, learning and planning), perception, multi-agent coordination, end-to-end integration, production engineering, AgentOps and governance, and closes with playbooks, case studies and a maturity path.

Every runnable listing in the book comes from its companion repository, and each one has a regression test.

New in the third edition

  • Repaired code: the demos, agents and utilities were repaired for this edition, and the printed listings are drawn from that code.
  • Regression tests: each repair came with a test; the suite grew from 36 test files to 113, and all 1,029 tests pass.
  • Demos that say what they need: a demo that needs an API key or a running service names it and stops, instead of failing midway.
  • A current stack: Python 3.13 and the latest compatible release of every dependency, locked in uv.lock.

Contents

  1. 1 Introduction: The Age of Agency
  2. 2 Agent Architectures and Operating Models
  3. 3 Decision Frameworks I: Probabilistic Reasoning and Optimization
  4. 4 Decision Frameworks II: Sequential Decision-Making
  5. 5 Decision Frameworks III: Learning and Planning
  6. 6 Core Technologies Enabling Agentic Retail
  7. 7 Physical Perception and Sensor Intelligence
  8. 8 Multi-Agent Coordination and Interoperability
  9. 9 End-to-End Agent Integration
  10. 10 Building Production Agents
  11. 11 Operating Agents (AgentOps)
  12. 12 Governance and Responsible Autonomy
  13. 13 Playbooks and Case Studies
  14. 14 Strategy, Maturity, and Futures
Fatih Nayebi

About the author

Fatih Nayebi

Fatih Nayebi is Assistant Professor in Information Systems at McGill University, where since 2019 he has taught the five graduate courses these volumes hold: Enterprise Data Science, Machine Learning in Production, Introduction to AI and Deep Learning, Applications and Architectures of Deep Learning, and Designing and Building Agentic AI Systems. As founder and CEO of OODARIS AI, he builds real-world, production multi-agent systems that make autonomous decisions, combining machine learning, ML engineering, deep reinforcement learning, operations research and software engineering, and that act only within the authority they have earned.

More about Fatih OODARIS AI

Also in the series

All books

Autonomy should rise only as evidence rises. · Published by Gradient Divergence, Montréal.