In this section: Chapters
- Part 0: Monday Morning
- Introduction
- Part I: The Problem
- Ch.1: The Day After
- Ch.2: Tribal Knowledge Is the Bottleneck
- Part II: The Architecture
- Ch.3: Contracts Are the Answer
- Ch.4: Capability Graphs, the New Atomic Unit
- Ch.5: Extraction Over Refactoring
- Ch.6: Making Your System Legible to AI Agents
- Part III: The Transformation
- Ch.7: The Architect
- Ch.8: The Developer
- Ch.9: The PM / PO
- Ch.10: The Designer
- Ch.11: Leadership
- Ch.12: The Company That Gets There First
- Appendices
- Appendix A: The C-DAD Specification
- Appendix B: MCP Documentation and Implementation Resources
- Appendix C: The Agent Onboarding Test
- Appendix D: The Interaction Contract Template
Making Your System Legible to AI Agents
The technical model for agent-navigable architecture
Chapter 6 is the technical model for a system an agent can navigate. It covers what agents actually need. It covers contract completeness: the minimum viable contract, the extended contract, and anti-patterns. It covers MCP as the runtime bridge, the agent onboarding test, and governing the graph under agent-assisted evolution.
The agent onboarding test checks whether a capability's contract is enough, on its own, for an agent to navigate the capability safely. It evaluates the contract, not the agent. The book's write-up of that test, including scoring bands and a legibility index, isAppendix C.
Forthcoming from Apress. ISBN 9798868834516.