Leanpub Header

Skip to main content
Go to Leanpub.com

Generative and Agentic AI for IT Managers

Hype meets reality in large companies

This book is 100% completeLast updated on 2026-06-17
Wolfgang Keller
LLMs and agentic AI are currently generating a great deal of hype. When applied correctly, they can deliver tremendous benefits. This book outlines the challenges involved in implementing these technologies within large enterprises—particularly in regulated environments. It serves as an accessible introduction for IT-focused executives and enterprise architects, while also proving useful for IT…
This book is a translation into English of Generative- und Agentic-AI für IT-Manager which was originally written in German

Minimum price

$16.80

$24.90

You pay

Author earns

$

Also available for 1 book credit with a Reader Membership

PDF
EPUB
WEB
APP
About

About

About the Book

Generative AI and AI agents are not the first hyped trend to sweep through the corporate world. However, this one is poised to unleash a transformative power unlike anything history has seen before.
Following the "ChatGPT moment" of 2022, everyone from CEOs and enterprise designers to line-of-business employees and programmers is asking—among other things—how their company can derive maximum benefit from AI.
Generative AI promises a massive corporate transformation. Yet, the "how" can often feel like navigating through a fog—a concept reflected in this book’s cover image, which shows someone standing atop a golden sphere, partially obscured by mist. New models, agent frameworks, and product announcements appear daily. CEOs ask when "this AI" will finally be deployed, development teams push for the latest tools, and consultants sell visions of autonomous systems capable of making decisions without human intervention.
This book is aimed at IT-focused leaders—such as project managers, enterprise architects, and solution architects—who want to turn the promises of generative AI and AI agents into reality.
Different industries and regulatory environments present unique challenges. You will find considerable discussion in this book regarding regulated sectors like banking and insurance; the healthcare industry faces similar, if not stricter, constraints. While these sectors offer promising approaches, one cannot simply unleash an AI agent naively and expect a windfall of riches to rain down on the company.
This book will help you identify challenges that the people trying to sell you products or projects often either fail to recognize or deliberately overlook.
Consequently, this book is not an introduction to the "engine room" of AI—such as the mechanics of machine learning or the deep technical intricacies of agent technologies. It goes as deep as necessary to explain key management issues. It is a guide for people who have already lived through more than one of the hypes that regularly sweep through the IT world.

Current state: The last one of 15 chapters (chapter 14) is waiting for confirmation by chapter authors - hence price is reduces compared to German version. If you buy now you will automatically get the full version the moment the chapter authors have given their OK

Share this book

Categories

Artificial IntelligenceVibe EngineeringLarge language modelsDigital TransformationBusiness ArchitectureBusiness AnalysisEnterprise Architecture

Feedback

Email the Author
This book is a translation into English of Generative- und Agentic-AI für IT-Manager which was originally written in German

Author

About the Author

Wolfgang Keller

Wolfgang Keller has more than 30 years of professional experience with large-scale software systems — as a developer, solution architect, enterprise architect, line manager, and interim manager — primarily in the insurance industry, a heavily regulated environment. Since the ChatGPT moment he has been exploring AI more deeply. He is, among other things, the author of several IT books.

Translations

Translations

Languages

Contents

Table of Contents

Before We Begin

  1. About the Author
  2. Acknowledgments to the Guest-Chapter Authors
  3. Preface to Version 1.0

Introduction and Overview

  1. The Fog of Hype
  2. Who This Book Is For
  3. Structure: Who Should Read What, and Why?
  4. What Happens Next?
  5. Why This Book Isn’t Free
  6. How AI Was Used for This Book
  7. Part A — Fundamentals

AI That Works - No New Directors

  1. AI and the Hype
  2. Agents Explained
  3. Directors Not Wanted
  4. How Claims Processes Already Work Today
  5. Director of Marketing
  6. Conclusion and Recommendation
  7. References

AI and EAM: The Wrong Questions

  1. The Seductive Illusion of Intelligent Agents
  2. The Limits of Today’s AI Agents
  3. What Actually Needs Cleaning Up?
  4. Experience Meets Hype: The Current Debate on AI in Companies
  5. Conclusion: Asking the Right Questions
  6. References

Agent Gateways: The Revenge of SOA in the Age of AI

  1. Where It Starts: AI Gateways
  2. What AI Gateways Do
  3. The Upshot: AI Gateways Are Necessary, but Not Sufficient
  4. Agent Gateways: The Great-Grandchildren of SOA
  5. Compliance and Governance
  6. How Mature Are Agent Gateways? — An Emerging Market
  7. Summary: Why There’s No Getting Around Agent Gateways
  8. References

In the Land of Lies: LLMs and Hallucinations

  1. Why hallucinations are a risk for you and your company
  2. Intro
  3. Hallucinations and bullshitting
  4. Business risks from hallucinations
  5. Detection and countermeasures
  6. Personal countermeasures
  7. Vendor countermeasures
  8. Conclusion and outlook: implications for using LLMs
  9. Epilogue
  10. References

How AI Accesses Enterprise Knowledge

  1. Mountains of Knowledge, Just Out of Reach for LLMs
  2. The Problem, Stated Precisely
  3. The Solution: RAG—From Simple to Complex
  4. How Do You Fill the Vector Database?
  5. Improvements and Variants
  6. The Consequences: Why RAG Changes the Rules of the Game
  7. Conclusion: RAG Makes AI-Powered Knowledge Management Accessible
  8. References

It’s a Model and It’s Looking Good

  1. How IT managers arrive at the right model for an AI project
  2. Why AI model selection isn’t a purely technical question
  3. Why benchmarks and marketing mislead
  4. Yet another selection process
  5. Why flexibility matters more than the perfect choice
  6. Epilogue
  7. References

Coding with LLMs and Agents

  1. Levels of Automated Coding with AI
  2. A New Software Development Process
  3. AI Environments That Protect Our Clients’ Data
  4. Further Security Aspects
  5. The Most Important Thing: The Quality of the Generated Code
  6. Consequences of Developing Software with AI
  7. About the Authors
  8. References
  9. Part B — Compliance and Security

AI-Relevant Regulation: The Financial Sector as an Example

  1. An Overview of the Rules
  2. Profiles of the Rules
  3. The EU AI Act
  4. ISO 42001 as an Aid for Implementing the EU AI Act
  5. References

The Inherent Risks of LLMs

  1. Why Large Language Models Need Safety Containment
  2. The Inherent Risks of LLMs
  3. The Safety Architecture of LLMs
  4. Conclusion
  5. References

Securing Applications Built on LLMs

  1. Risks You Want to Avoid When Deploying LLMs and AI Agents
  2. Possible Attack Vectors Specific to AI Applications
  3. How to Arrive at a Reasonably Secure AI Application
  4. Threat Catalogs
  5. Conclusion
  6. References

Why AI Forces Us to Rethink IT Security From Scratch

  1. From Easing the Work to Delegating the Action: When “Human in the Loop” Becomes a Fiction
  2. The Democratization of Criminal Capability
  3. Stealth Adoption: When AI Use Devalues the Rules
  4. The Devaluation of Knowledge Work
  5. Conclusion: How the Fault Lines Reinforce One Another–and Why Security Must Be Rethought
  6. About the Author
  7. References
  8. Part C — Practice, Not PowerPoint

Imagine It Is the Age of AI and Nobody Shows Up

  1. Two Stories: Morgan Stanley and Klarna
  2. Why Many Studies Are Already Out of Date a Year Later
  3. The Amplifier Effect: Why AI Makes the Strong Stronger and the Weak Weaker
  4. Why Top-Down Training Programs Almost Never Work
  5. What Works Instead: Inspire People, Don’t Just Train Them
  6. The Work-Intensification Trap
  7. What the Regulator Requires—and What That Really Means
  8. Conclusion: Something Has to Happen from the Bottom Up, Too
  9. References

AI That Works — Practice, Not PowerPoint

  1. Digitalization Is Nothing New — But AI Changes Everything
  2. From Theory to Practice: How This Chapter Fits the Book
  3. The Regulatory Foundation: Why Life and Health Are a Different League
  4. Use Case 1: msg.process:it — End-to-End Process Automation
  5. Use Case 2: AI-Assisted Product Development
  6. Use Case 3: Claims Handling in Property Insurance
  7. What Didn’t Work
  8. The Shared Story
  9. Conclusion and Recommendation
  10. About the Authors
  11. References

Not Every Project Is the Same

  1. The Problem with the One-Size-Fits-All Slide
  2. Four Types Worth Knowing
  3. These Four Types Exist in Every Regulated Industry
  4. Regulatory Complexity Determines Your Room to Maneuver
  5. A Different Project Type Means Different Costs and a Different Calculation
  6. Different Metrics, Different Truth
  7. Different Time Frames, Different Expectations
  8. Lessons from Practice
  9. Calculate ROI Honestly — By Type
  10. Why a Domain-Agnostic Project Lead Has No Chance
  11. What This Means for Your Next AI Project
  12. References

Get the free sample chapters

Click the buttons to get the free sample in PDF or EPUB, or read the sample online here

Download Sample PDFDownload Sample EPUB

The Leanpub 60 Day 100% Happiness Guarantee

Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

See full terms...

Earn $8 on a $10 Purchase, and $16 on a $20 Purchase

We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.

(Yes, some authors have already earned much more than that on Leanpub.)

In fact, authors have earned over $15 million writing, publishing and selling on Leanpub.

Learn more about writing on Leanpub

Free Updates. DRM Free.

If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).

Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.

Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.

Learn more about Leanpub's ebook formats and where to read them

Write and Publish on Leanpub

You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!

Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.

Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.

Learn more about writing on Leanpub