engineer@aine:~/book$ cat book.md
Learning AI-NativeSoftware Engineering
Building production software with AI agents and spec-driven development. Eleven chapters on how professional engineers work when AI is part of the stack — not a book about building AI applications.
- 11 chapters
- 392 sections
- 135k words
- ~10 hours
- O'Reilly Media · Early Release
- 01
Read it free for 30 days
Use the code ANSE2026 on the O'Reilly learning platform. That covers the whole platform, not just this book.
Redeem the code ↗ - 02
Already have O'Reilly access
The Early Release is live. New chapters appear on the same page as they are finished and copy-edited.
Open the book ↗ - 03
Wait for print, but stay current
The manuscript is due 25 November 2026. The newsletter tells you when each chapter drops and when the print edition is orderable.
Subscribe ↗
01 / the centre of gravity
Intent, constraints, verification. Everything else in the book hangs off these three.
- 01ch3
Context engineering
Assemble the right code, docs, rules and examples at the right time, so the agent produces consistent output instead of occasional lucky output.
- 02ch5
Spec-driven development
Write intent down before you prompt. The spec is the durable artifact that survives every tool change and model upgrade.
- 03ch10
Harness engineering
Build the environment around the agent: rules, skills, tests, feedback loops. Agent equals model plus harness, and the harness is yours.
- 04ch8
Verification and gates
Once code is cheap, trust is the bottleneck. Four layers of checks let AI-written code meet the same bar as anything else you ship.
- 05ch9
Agent orchestration
Know when one agent is enough and when to run a fleet, and stop hallucinations from propagating through a pipeline.
- 06ch10
Scaling in teams
Licences change nothing. Shared context, standard stacks and honest metrics are what move a team, not a purchase order.
02 / learning outcomes
What you can do after, that you could not do before.
- Adopt the AI-native mindset, from implementer to orchestrator
- Master context engineering for consistent, production-ready output
- Navigate the AI tool landscape with criteria instead of hype
- Apply spec-driven development as a practice that survives tool changes
- Orchestrate single and multi-agent systems without the usual anti-patterns
- Integrate verification and quality gates so AI code ships with confidence
- Collaborate across functions using specs, acceptance criteria and constraints
- Scale AI practices from IC to team to organisation
03 / who it is for
A short, honest fit check.
- You are a mid-level to staff engineer shipping and maintaining production systems.
- AI has made it into your editor but not into your workflow.
- You use a coding assistant daily and suspect you are using it badly.
- You lead a team and licences alone have not moved a single metric.
- You want practices that outlive the tool you happen to use this quarter.
- You want to build AI applications, models or RAG pipelines. That is a different book.
- You are looking for prompt templates to copy and paste.
- You have never shipped production code. The book assumes solid fundamentals.
- You want a tool tutorial tied to one vendor.
what it assumes you already have
- A few years of experience building and shipping production code
- Comfort with any mainstream language and a real codebase
- Familiarity with Agile-style delivery and working in a team
- No ML or AI research background at all
04 / the arc
Eleven chapters, in order.
- 01The AI-Native EngineerThe shift from implementer to orchestrator, the vibe-coding trap, and what makes an engineer irreplaceable.
- 02From LLMs to AgentsHow 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.
- 03Context Engineering FundamentalsMoving from prompt engineering to assembling the right context at the right time, so AI tools produce consistent outputs, not lucky ones.
- 04Model Context ProtocolWhat MCP is and why it matters, its client/server/transport architecture, and how to operate MCP servers safely.
- 05Spec-Driven DevelopmentWhy specs are the durable artifact that keeps AI-generated code aligned with intent, and how you already write them without realising it.
- 06The SDD WorkflowThe canonical loop — Specify, Plan, Execute, Verify, Integrate, Learn — and exactly where humans must stay in it.
- 07SDD Frameworks ComparedWhy frameworks exist and how to choose between them — or when no framework is the right answer.
- 08Verification and Quality GatesWhere the bottleneck moves once coding is cheap, and the four layers that let AI-generated code meet the same bar as human-written code.
- 09Agent Orchestration PatternsScaling one agent with compaction and scratchpads, then coordinating many agents while avoiding cascading failures.
- 10Scaling AI-Native Engineering in TeamsWhy buying licences changes nothing, what actually shifts when a team goes AI-native, and how to scale without burning out your best people.
- 11AI-Native in Practice at CogwheelNine weeks at Cogwheel: one team applies every practice in the book to ship the bet the company was too slow to ship.
05 / questions
The ones people actually ask.
01What will I learn from this book?
How to build production software with AI systems using the core pillars of AI-native engineering: avoiding the vibe-coding trap, context engineering, spec-driven development, MCP tooling, agent orchestration, and verification gates. Every chapter has concrete patterns, real code, and team playbooks.
02Who is this book for?
Software engineers, tech leads, and engineering managers who already use AI coding assistants but want to move past ad-hoc usage into repeatable, production-grade practice.
03Do I need prior AI or ML experience?
No. The book assumes solid software engineering fundamentals and treats AI-native engineering as a discipline of software delivery, not as an ML research topic.
04Which AI tools does the book cover?
The focus is on patterns that outlive any single tool. Claude Code, Cursor, Copilot, Codex, Windsurf, Aider and whatever ships next all fit the practice. Specific tools appear as examples, never as requirements.
05How is AI-native engineering different from vibe coding?
Vibe coding is ad-hoc AI usage that produces plausible code which fails in production. AI-native engineering is the disciplined alternative: explicit context, clear specs, verification gates, and team practices that ship reliable software.
Start with the free half of the ecosystem.
The canvas, the assessment, the 7-day roadmap and the foreword cost nothing and need no email. If they are useful, the book is the same thinking worked out in full.