- ホーム
- > 洋書
- > 英文書
- > Computer / General
Full Description
Lead AI adoption across engineering with practical pilots, measurable outcomes, scalable frameworks, and governance that earns developer trust - no ML expertise required.
Key Features
Build an AI code reviewer on your own repos and scale it across the organization
Turn successful AI pilots into repeatable systems for adoption across teams
Apply AI across the SDLC, from planning and testing to incidents and releases
Measure AI adoption with meaningful metrics and communicate impact to leadership
Book DescriptionMost AI initiatives stall not because the technology falls short, but because they never get past isolated experiments. Engineers adopt tools on their own, yet the way teams work doesn't change. This book is for the leaders who close that gap.
You'll start with the foundations a leader actually needs: how models learn and the vocabulary (RAG, context, agents, MCP) to assess an architecture. You'll then build your own AI practice, from prompts to small agents, and turn what works into team standards through pilots, prompt libraries, and metrics. Then you'll build an agent, a codebase Q&A bot, and an AI code reviewer on real pull requests, taking it to production, refining context engineering and addressing noise, cost, and trust.
The authors bring experience. One has led engineering across enterprises including Oracle and Manhattan Associates and companies including Cohesity and Variant. The other helped scale two unicorns, Cohesity and Eightfold, and builds GenAI infrastructure at Palo Alto Networks today. This book is for the people leading AI adoption, not building models. Whether you lead a team or an organization, you'll come away with the playbooks, metrics, and confidence to drive AI adoption that lasts.What you will learn
Decide where AI should - and should not - fit engineering work
Turn AI capabilities into measurable engineering outcomes
Run high-trust AI pilots with low-code tools and existing systems
Build an AI code reviewer from prototype to production
Apply AI to planning, testing, incidents, and releases
Measure adoption with quality, usage, cost, and trust metrics
Build executive-ready business cases for AI investments
Govern AI with auditability and human-in-the-loop controls
Who this book is forEngineering managers, staff engineers, tech leads, directors, and VPs responsible for AI adoption across software teams. Product leaders and executives who work closely with engineering will also benefit. No AI or ML background is required; readers should have experience leading or influencing modern engineering teams.
No AI background required, just experience leading modern development teams.
Contents
Table of Contents
The AI Landscape and its Business Context
Key AI Concepts Without the Math
Why Language Models are Different
Upskilling Yourself as a Leader
Introducing AI for Team Efficiency
Building with No/Low-Code Agents
The Problem Statement - AI Code Reviewer
From Pieces to Prototype
Context Engineering- Feed the AI Reviewer
Monitoring and Responsible AI in Practice



