Skip to content

engineer@aine:~/book$ ls -l chapters/

Eleven chapters.One arc.

Chapters 1 to 4 build the mental model. Chapters 5 to 7 turn it into a workflow. Chapters 8 and 9 make the output trustworthy and scale it. Chapters 10 and 11 take it to a team, then show the whole thing running for nine weeks at a company that was losing.

  • 11 chapters
  • 135k words
  • 37 figures
chapters/total 135k
  1. 01

    The AI-Native Engineer

    The shift from implementer to orchestrator, the vibe-coding trap, and what makes an engineer irreplaceable.

    • 19 sections
    • 11k words
    • 2 figures
    • ~48 min
  2. 02

    From LLMs to Agents

    How LLMs work from an engineer's-eye view, why they are good at code, and how tools, context, and a loop turn a model into an agent.

    • 52 sections
    • 15k words
    • 3 figures
    • ~67 min
  3. 03

    Context Engineering Fundamentals

    Moving from prompt engineering to assembling the right context at the right time, so AI tools produce consistent outputs, not lucky ones.

    • 38 sections
    • 10k words
    • 2 figures
    • ~46 min
  4. 04

    Model Context Protocol

    What MCP is and why it matters, its client/server/transport architecture, and how to operate MCP servers safely.

    • 51 sections
    • 11k words
    • 2 figures
    • ~51 min
  5. 05

    Spec-Driven Development

    Why specs are the durable artifact that keeps AI-generated code aligned with intent, and how you already write them without realising it.

    • 24 sections
    • 9k words
    • 4 figures
    • ~43 min
  6. 06

    The SDD Workflow

    The canonical loop — Specify, Plan, Execute, Verify, Integrate, Learn — and exactly where humans must stay in it.

    • 41 sections
    • 15k words
    • 4 figures
    • ~67 min
  7. 07

    SDD Frameworks Compared

    Why frameworks exist and how to choose between them — or when no framework is the right answer.

    • 18 sections
    • 9k words
    • 2 figures
    • ~43 min
  8. 08

    Verification and Quality Gates

    Where the bottleneck moves once coding is cheap, and the four layers that let AI-generated code meet the same bar as human-written code.

    • 66 sections
    • 21k words
    • 7 figures
    • ~93 min
  9. 09

    Agent Orchestration Patterns

    Scaling one agent with compaction and scratchpads, then coordinating many agents while avoiding cascading failures.

    • 33 sections
    • 12k words
    • 6 figures
    • ~55 min
  10. 10

    Scaling AI-Native Engineering in Teams

    Why buying licences changes nothing, what actually shifts when a team goes AI-native, and how to scale without burning out your best people.

    • 34 sections
    • 11k words
    • 4 figures
    • ~48 min
  11. 11

    AI-Native in Practice at Cogwheel

    Nine weeks at Cogwheel: one team applies every practice in the book to ship the bet the company was too slow to ship.

    • 16 sections
    • 11k words
    • 1 figure
    • ~51 min

tree chapters/

Every section, listed

The full table of contents as a directory tree.

open figures/

All 37 diagrams

The visual argument of the book in one page.