What's New

Track meaningful updates to the book. This page is refreshed once a day from the latest changes to the book's content.

---

Latest Updates

Updates are grouped by day and written automatically from the day's content changes, each linking to the lesson that changed.

2026-07-15

• Clarified the Loop Engineering crash course with plainer guidance on background sessions, timers, scheduling, retries, and stopping loops, plus a cleaner orientation for the event-driven section. (Loop Engineering: A Crash Course)

2026-07-14

• Added a new hero image to the About page to anchor the book and ecosystem overview. (The AI Agent Factory — A Definitive Book and Ecosystem for the Agent Era)
• Clarified the geography note in Why AI Is Non-Negotiable so Shenzhen reads as China's hardware capital and Beijing as its AI capital. (Why AI Is Non-Negotiable)
• Expanded The Forward Deployed Engineer Agent Factory Model with a plain-language explanation of how domain knowledge lives as corpus, map, and reflexes. (The Forward Deployed Engineer Agent Factory Model)

2026-07-13

• Refreshed the Loop Engineering crash course with a plainer, clearer rewrite that keeps the loop shape and stopping rules easy to follow. (Loop Engineering: A Crash Course)
• Added a NemoClaw cage simulation to Scenario 8 so readers can practice the sandboxed OpenClaw setup before they ship it publicly. (OpenClaw with General Agents: A 90-Minute Crash Course)
• Clarified the FDE AF Model page with a plainer explanation and a new forecast section about AI infrastructure spending. (The Forward Deployed Engineer Agent Factory Model)

2026-07-12

• Introduced a new five-layer model page that links the foundation, vertical ecosystems, and customer work into one business blueprint. (The Forward Deployed Engineer Agent Factory Model)
• Rewrote the OpenClaw general-agents course so Scenario 8 explains NemoClaw and OpenShell as a caged setup for sharing with other people, with a clearer agent-led install flow. (OpenClaw with General Agents: A 90-Minute Crash Course)
• Added a checker-ladder visual and a clearer rule for when a writing loop can trust a rubric versus a human review. (Loop Engineering: A Crash Course)
• Added a new section showing how AI infrastructure spending is shifting cash from hyperscalers to chipmakers. (The Agent Factory Thesis)
• Expanded the roles map with a new Skill Author example and a tighter link back to the FDE AF Model. (The Roles This Book Trains)

2026-07-11

• Added a new Ecosystem section with a hub and three product pages for the System of Record, Zia Tutor AI, and Zia Developer AI. (The Agent Factory Ecosystem)
• Refreshed the About page to use the new ecosystem names and point readers to the System of Record, Zia Tutor AI, and Zia Developer AI. (The AI Agent Factory — A Definitive Book and Ecosystem for the Agent Era)
• Added a practical tip to Loop Engineering that helps readers choose the lightest loop that fits the task. (Loop Engineering: A Crash Course)
• Expanded The Roles This Book Trains with a Harari-framed opening about why judgment, specification, and deployment matter more than syntax. (The Roles This Book Trains)
• Expanded Why AI Is Non-Negotiable with a Harari-based framing that turns the objections into hazards on the road to adoption. (Why AI Is Non-Negotiable)

2026-07-10

• Corrected the Agentic Coding crash course so the saved-plan step now happens after plan mode, where writing is allowed. (Claude Code and OpenCode: A Crash Course)
• Expanded Loop Engineering with a new dogfooding section, an interactive loop-shift simulator, and fuller guidance on schedules, channels, and Routines. (Loop Engineering: A Crash Course)
• Expanded The Agent Factory Thesis with a new section on foreign investments in data centers. (The Agent Factory Thesis)

2026-07-09

• Expanded Loop Engineering with clearer guidance on stopping /loop jobs, a fuller explanation of conditional loops, and a more complete walkthrough of scheduled Routines and cron. (Loop Engineering: A Crash Course)
• Added a new Four Survival Skills section on the About page that names direction, orchestration, judgment, and human connection as the skills that matter in the agent era. (The AI Agent Factory — A Definitive Book and Ecosystem for the Agent Era)

2026-07-08

• Expanded Loop Engineering with a clearer four-layer mental model, four more practice projects, and three routine drills in the appendix. (Loop Engineering: A Crash Course)

2026-07-07

• Reframed the Agentic Coding crash course around trust-by-checking, added a verification loop section and a new maturity ladder, and expanded the quiz. (Claude Code and OpenCode: A Crash Course)
• Clarified Loop Engineering by separating the inner loop from the outer loop and spelling out how the layers fit together. (Loop Engineering: A Crash Course)
• Tightened The Agent Factory Thesis with first-party Claude Code evidence and a clearer line between invariants and implementation. (The Agent Factory Thesis)

2026-07-06

• Reworded the Spec-Driven Development crash course in plainer, more accessible language. (Spec-Driven Development: A Crash Course)
• Added Scenario 8 to the OpenClaw crash course, where readers sandbox an AI Employee with NemoClaw, plus new flashcards for that lesson. (OpenClaw with General Agents: A 90-Minute Crash Course)
• Expanded Loop Engineering with a new routines appendix and clearer beginner-friendly explanations of how loops start, run, and recover. (Loop Engineering: A Crash Course)

2026-07-05

• Reworked the preface to frame the book around the line between people who build AI workers and people who get displaced by them. (Preface: The Right Side of the Line)
• Expanded the loop engineering crash course with a clearer outer-loop vs inner-loop model and new diagrams for the six-part loop shape. (Loop Engineering: A Crash Course)

2026-07-04

• Expanded The Roles This Book Trains into a full map of the FDE market, including salary ranges, freelance work, interview prep, and a five-archetype view of the job. (The Roles This Book Trains)
• Tied The Agent Factory Thesis more directly to the Forward Deployed Engineer path and the AI-Native Company Architect. (The Agent Factory Thesis)

2026-07-03

• Refined the Getting Started map and the Mode 2 landing page so the phase labels and course blurbs line up with the sidebar. (Getting Started: Crash Courses)
• Added AI gravity as the named pull toward outsourcing your thinking, with matching glossary wording and a loop-engineering callback. (How to Think in the AI Era: Crash Course)
• Expanded Human-Agent Teams with a Claude Tag example and an extra check question. (Human-Agent Teams: The Operating Model for Your Workforce)
• Refreshed the roles map with a new Forward Deployed Engineer infographic and current Microsoft context. (The Roles This Book Trains)

2026-07-02

• Added a hands-on MCP Apps lab and a refund-approval widget walkthrough to the Designing Agent Experiences crash course. (Designing Agent Experiences: Where Humans Learn to Trust Machines That Act)

2026-07-01

• Shipped a new crash course on designing agent experiences, with a reader track, an Agent Experience Brief, and fresh flashcards, quiz, and teaching aid. (Designing Agent Experiences: Where Humans Learn to Trust Machines That Act)
• Expanded AI Identity with a clearer agent-identity arc, plus flashcards, a 50-question quiz, and a teaching aid. (AI Identity: Human Sign-In and Agent Access)
• Added a new loop-engineering section that frames one fast coding loop inside slower feedback and outside loops. (Loop Engineering: A Crash Course)
• Tightened the roles map's pod-of-one story and linked it back to Human-Agent Teams. (The Roles This Book Trains)

2026-06-30

• Expanded AI Identity into a clearer agent-identity arc with step-by-step build prompts and a more explicit frontier for agent credentials. (AI Identity: Human Sign-In and Agent Access)
• Refined Connector-Native Apps around the new release starter and a cleaner handoff from the old monorepo base. (Connector-Native Apps: A Remote MCP Server Whose Customer Is an AI)
• Reworked Plugins for AI Agents into a more judgment-first course with a clearer opening and a fresh release starter. (Plugins for AI Agents: One Bundle, Your Whole Team)

2026-06-29

• Reworked Connector-Native Apps around a clearer mental model and a cleaner build path for the Reading Room connector. (Connector-Native Apps: A Remote MCP Server Whose Customer Is an AI)
• Added a preview AI Identity course about owning sign-in and giving agents their own bounded credentials. (AI Identity: Human Sign-In and Agent Access)
• Expanded Human-Agent Teams with a teaching aid, flashcards, and a 50-question quiz. (Human-Agent Teams: The Operating Model for Your Workforce)
• Tightened Plugins for AI Agents so the starter path is clearer for both marketplace installs and local development. (Plugins for AI Agents: One Bundle, Your Whole Team)
• Expanded the role map to sharpen the Outcome Architect and add the Connector and Plugin Engineer. (The Roles This Book Trains)
• Added a clearer end-to-end RAG pipeline map to Give Your AI Searchable Context. (Give Your AI Searchable Context: RAG on Postgres with pgvector — A Crash Course)
• Added a new boom-vs-bust section to the thesis so the market-cycle risk is easier to separate from the technology itself. (The Agent Factory Thesis)

2026-06-28

• Added the new Mode 2 plugin crash course, so readers can now extend Claude Code and OpenCode right after Connector-Native Apps. (Plugins for AI Agents: One Bundle, Your Whole Team)
• Clarified Connector-Native Apps with gentler first-contact explanations and more consistent build instructions. (Connector-Native Apps: A Remote MCP Server Whose Customer Is an AI)
• Refreshed the About page to better explain the book, its ecosystem, and the channels it ships through. (The AI Agent Factory — A Definitive Book and Ecosystem for the Agent Era)

2026-06-26

• Fixed the Getting Started course map so the engineer path now points to Course 17 for Build AI Agents and keeps the Digital FTE sequence aligned. (Getting Started: Crash Courses)

2026-06-25

• Reframed Personal Agent Harnesses as the shared step where readers build an owned persistent agent, with clearer OpenClaw and Hermes choices. (Personal Agent Harnesses)
• Added a new Mode 1 path with a task-diagnosis lesson and a bridge from one-off solves to workers. (Mode 1 — Problem-Solving)
• Added section overview pages for the General Agents and Mode 2 Manufacturing tracks, so each track now opens with a guided map. (General Agents, Mode 2 — Manufacturing)

---

About This Page

This book is continuously updated. Instead of version numbers, we track changes here so you can see what's new since your last visit.

• Each entry links to the specific lesson that changed
• A short digest is written once a day from the latest content changes on main
• Only changes to book content (not infrastructure) appear here

Tip: Bookmark this page to quickly check for updates.