How to Read This Book
The Encyclopedia is not a tutorial. You don’t read it front to back unless you want to. You pick an entry that matches where you are, follow the links it offers, and build your understanding in whatever order fits the work in front of you.
If you’d rather start from a guided path, the Learning Tracks page lays out five curated reading orders by situation. This page covers the rest of the map: how each entry is built, and how this book’s sections fit together.
Choose by Situation
- First time directing an AI coding agent? Start with Track 1: Your First Day with an AI Agent.
- Need the software foundations first? Start with Track 2: Building Things That Work.
- Focused on correctness, testing, or security? Start with Track 3: Keeping Software Honest.
- Already building with agents? Start with Track 4: Mastering the Agentic Workflow.
- Turning an idea into a shipped product? Start with Track 5: From Idea to Product.
The Structure of Each Entry
Most entries in the Encyclopedia follow the same template:
- Context describes the situation where this concept shows up, so you can recognize whether it applies to you.
- Problem names the specific tension or challenge you’re facing.
- Solution explains the concept: what it is and what it does.
- How It Plays Out shows the concept in action through concrete scenarios.
- Consequences covers the tradeoffs: what the pattern costs you and what you give up to get its benefit.
- Related Articles links to concepts that work alongside this one, refine it, or push back on it.
Some pages, including introductory and methodology articles, don’t follow this structure. They use narrative prose instead.
This Book’s Sections
The sections run roughly from strategic to tactical, then turn to the people and agents who do the work. The sidebar lists them in this order.
Product Judgment and What to Create starts before any code exists. What should you build? For whom? Why would it matter? Skip these questions and you risk building the wrong thing well.
Intent, Scope, and Decision-Making turns a goal into a workable task. Vague ideas become the requirements and constraints that guide an agent or a developer.
Structure and Decomposition is about organizing software into parts: which pieces belong together, which belong apart, and how to break a large problem into smaller ones you can solve on their own.
Data, State, and Truth covers how information is represented, stored, and kept consistent. Most bugs live here.
Computation and Interaction gets into how software does things: algorithms, side effects, concurrency, and the interfaces through which components talk to each other.
Correctness, Testing, and Evolution is about building confidence that software works, and keeping that confidence as the software changes.
Security and Trust covers protecting systems and users from things going wrong, whether by accident or by malice.
Human-Facing Software is what it takes to build something people can actually use: interaction design, accessibility, internationalization.
Operations and Change Management picks up after the code is written. How does software get deployed, updated, rolled back, and kept running?
Socio-Technical Systems is about the people. Software is built by teams, and the shape of an organization shows up in the shape of its code. These entries cover ownership, team structure, and the human layer of the system.
Design Heuristics and Smells collects rules of thumb for the decisions where the right answer depends on context, plus the warning signs that tell you something has gone wrong.
Agentic Software Construction covers the concepts specific to directing AI agents: models, prompts, context, tools, and the workflows that tie them together. It’s the largest section in this book.
Agent Governance and Feedback is about trusting an agent over time. Once an agent takes actions on its own, you need approval policies, evaluations, and the feedback loops that tell you when to extend its leash and when to pull it back.