Book Series  ·  2024–2026

The Agentic AI Series

Four books on designing, building, and governing agentic AI products, and on keeping the human judgment they route through.

These books were written from a practitioner’s seat, not an analyst’s. Each one is a field guide to a specific problem: what the PM job actually requires, what the team has to hold, and what happens when the agent runs without a design behind it.

They were written in order, but each stands alone. If you are new to agentic product management, start with Book 1. If you are building something specific, start where the problem is. If you have been operating agents long enough to feel the supervision skill quietly erode, start with Book 4.

Book 1  ·  The PM
Agentic AI for Busy Product Managers
A Practitioner’s Guide to the New PM Job

The full PM lifecycle for agentic products: deciding whether to build, designing behavior and evals, measuring drift, and managing the human system around the agent. Fifteen chapters. Second edition.

Free online Amazon Read
Book 2  ·  The Failures
Why Agentic AI Products Fail
Building the Supervisory Layer That Governs It

Every agentic product is two products. Most teams build the first and assume the second takes care of itself. It does not. Twenty-two chapters on the supervisory layer’s four dimensions, failure modes, and how to build it deliberately.

Free online Amazon Read
Book 3  ·  The Team
The Agentic AI Team
How Agentic AI Reshapes the Roles That Build It

The prior books were written from the PM’s seat. This one zooms out. The unit of failure is the seam between roles, not the capability of any one of them. Twenty-six chapters.

Free online Amazon Read
Book 4  ·  The Practitioner  ·  Draft
The Agentic AI Practitioner
Keeping the Judgment the Machine Cannot Hold

The first three books rest on one assumption nobody audited: that the practitioner in the seat still has the judgment the structure routes through them. This book is the deliberate-practice curriculum that keeps that assumption true. Fifteen chapters and a full appendix set.

Free online Amazon Read
Companion  ·  Whitepapers
Eight Papers, One Question Each
Short, self-contained, and drawn from the four books.

Cost, readiness, supervision, prototyping, procurement, and the roles that arrive with the agent. Eight to fifteen pages each, written to hand to a room that has not read the books. Free to read and download.

Browse the papers
Companion  ·  Skill Package for Claude Cowork
Agentic AI PM Skill Package
The lifecycle, as working aids the PM can invoke at the moment of need.

Seven skills covering the agentic PM lifecycle, distilled from the four books. Install in Claude Cowork and invoke at the moment of need. Stage 1 of three.

Install & learn more
Companion  ·  Interview Reference
AI PM Interview Questions, Answered
Fifty-five questions, answered from the product seat rather than the engineering seat.

The questions circulating in 2026, answered against the lifecycle and linked to the chapter each answer comes from. Plus the eleven questions nobody asks, including who owns a wrong outcome.

Read the answers

About the author

Yoram Friedman, MD, is a physician and enterprise product leader. He has shipped enterprise software across SAP, Walmart, Microsoft, and regulated health technology, working on semantic data architecture, AI-ready data products, and systems that operate under real regulatory constraint. He trained in anesthesiology and radiology, and writes on agentic AI, clinical workflow, and the product discipline that emerges when software starts making decisions on its own.

The regulatory and design default for AI is “keep a human in the loop.” Sustained AI use erodes the human’s ability to perform that loop’s function. This series is for the people who have to design supervision that does not assume the supervisor is the unimpaired version of themselves they were on day one.