Applied AI Engineering · Volume I

Foundations

How Modern AI Systems Actually Work

In production Manuscript complete and validated. Release pending final production checks.

Not yet on saleGet release updates

About this volume

Volume I builds the conceptual and economic foundation the rest of the series stands on. It moves from what artificial intelligence is, through machine learning, neural networks, and deep learning, into the transformer architecture and the large language models built on it.

It ends where practical work begins: a full chapter on prompt engineering foundations that explains why prompting works in terms of the underlying mechanism, not as a list of tricks.

Mission

Understand how modern AI systems actually work, what they cost, where they fail, and why engineering discipline is required to use them well.

Prerequisites. Basic computer literacy. Programming experience is helpful but not required — every laboratory provides a complete starting point.

Details

SeriesApplied AI Engineering, Volume I
AuthorDr. Ahmed AlSalih
PublisherNexoma Labs LLC
EditionFirst Edition
Chapters10
Laboratories10
DifficultyBeginner to Intermediate
FormatsPaperback, Hardcover, Kindle, EPUB, PDF
StatusIn production

What you will be able to do

  • Explain the evolution from symbolic AI to foundation models.
  • Distinguish AI, machine learning, deep learning, and generative AI precisely.
  • Explain the transformer architecture and why it displaced recurrent models.
  • Describe how an LLM turns text into tokens, and tokens into a next-token distribution.
  • Explain how reasoning models differ from standard LLMs, and when the extra cost is justified.
  • Identify the characteristic failure modes of LLMs and explain their mechanical causes.
  • Explain why prompt engineering works, in terms of the underlying mechanism.

Contents

10 chapters. Chapter numbering restarts at 1 in every volume; cross-volume references are written as Volume III, Chapter 4.

  1. Introduction to Artificial Intelligence
  2. History and Evolution of Artificial Intelligence
  3. Machine Learning Fundamentals
  4. Neural Networks
  5. Deep Learning
  6. Transformer Architecture
  7. Large Language Models
  8. Generative AI
  9. Reasoning Models
  10. Prompt Engineering Foundations

Errata

No errata reported.

Volume I errata

Companion code

Every laboratory runs from a clean checkout and is tested in CI.

Companion code

Teaching this volume?

Slides, syllabi, teaching notes, and assessment keys are free to verified instructors.

Instructor resources