AI AGENTS THAT WORKBuy the eBook

Inside the book

Eight parts, fourteen chapters

Plain-English explanations and an everyday analogy for every core idea, two in-depth case studies, twelve worked examples, a design workbook and a technical field guide.

  1. Part 1

    Understanding Agents

    What an agent is, and the spectrum from assistant to autonomous system.

  2. Part 2

    Designing the Work

    Human Twin Design and the OPT model.

  3. Part 3

    Choosing and Decomposing

    The five-gate test, the opportunity matrix, and why bounded agents beat one giant agent.

  4. Part 4

    Building and Governing

    Architecture patterns, controls, human-in-the-loop and governance.

  5. Part 5

    Evaluation

    What to measure, and how to run evals at scale.

  6. Part 6

    Running Agents in the Organisation

    Ownership, decision rights, cost and proving value.

  7. Part 7

    Worked Examples

    Two deep cases and twelve patterns.

  8. Part 8

    Build Your Own

    Eight design canvases, the one-page Agent PRD and a first hands-on build.

Get the book

The best agent is not the most autonomous one.

It is the one whose value, boundary, controls and evidence are clear.

Available now

Kindle eBook

Read tonight on any device. Searchable, with every canvas and checklist one tap away.

Buy on Amazon

Out 20 November 2026

Paperback

The desk copy for design reviews, with the workbook canvases ready to mark up.

Paperback out 20 November 2026

For organisations

Team copies and talks

Bulk copies for your team, or a talk or workshop on applying the method to your own agents.

Message Anuj on LinkedIn