This Part is reference material. You do not need to understand it before beginning the book.
First time here? Read the Preface and continue into Part I. You may skip the rest of Part 0 for now; it is designed to become more useful as the terminology and argument become familiar.
Returning to the book? Use What This Book Argues for the six central claims, MAGE on One Page for the relationship among the major concepts, and the Glossary for definitions.
The Preface asks one question: How do we safely grant autonomy to commodity intelligence? The book builds toward the answer provided by MAGE. The Conclusion returns to the question and asks its converse: What cannot be delegated?Figure 0.1-1 traces that argument.
Figure 0.1-1.The book's argument, from the Preface's opening question through the seven Parts to the Conclusion's answer and its converse.
Three shorter routes serve different purposes:
Do it Monday. Part I → Part IV → Appendix Part I: Practice. Start with the premise, move directly to the working method, then use the practice appendices as a reference while applying it.
Show me the data. Part I → Part V → Appendix Part II: Evidence. Read the framing, examine the empirical argument, then inspect its evidentiary basis.
I want the theory. Part I → Part II → Part III → Interlude: One Problem, Many Models → Part VI → Part VII → the Conclusion. Start with the changed engineering substrate, learn Modeling and Alignment, then follow one problem as successive models expose its constraints and design choices. The closing Parts develop the resulting theory and its implications for software engineering.
Adopt it in an organization. Part I → Section 5.5 → Appendix G. Start with the changed engineering problem, see how several organizations are already restructuring agentic work, then use the adoption guide to decide where context, models, evidence, and enforcement are worth organizational investment. Parts II–IV provide the engineering practices; Part VI provides the underlying theory.