Introduction to Building AI Applications with Foundation Models

Summary

A recap of how foundation models gave rise to AI engineering, the application patterns enabled, and the framework this book provides.

Chapter Summary

This chapter had two purposes: explain the emergence of AI engineering as a discipline thanks to the availability of foundation models, and give an overview of the process needed to build applications on top of these models.

As an overview chapter, it only lightly touched on many concepts. These will be explored further in the rest of the book.

What This Chapter Covered

The Rapid Evolution of AI

The transition from language models to large language models, thanks to a training approach called self-supervision. Then how language models incorporated other data modalities to become foundation models, and how foundation models gave rise to AI engineering.

Application Patterns

The rapid growth of AI engineering is motivated by the many applications enabled by emerging capabilities. The chapter discussed some of the most successful application patterns, both for consumers and enterprises.

Should You Build It?

Before building an application, an important yet often overlooked question is whether you should build it. The chapter discussed this question alongside major considerations for building AI applications.

The AI Engineering Stack

AI engineering evolved out of ML engineering. Many ML principles still apply, but AI engineering brings new challenges and solutions. The last section discussed how the stack has changed.

Despite the incredible number of AI applications already in production, we're still in the early stages of AI engineering, with countless more innovations yet to be built.

Navigating the Overwhelm

One aspect of AI engineering that is especially challenging to capture in writing is the incredible amount of collective energy, creativity, and engineering talent that the community brings. This collective enthusiasm can often be overwhelming, as it's impossible to keep up-to-date with new techniques, discoveries, and engineering feats that seem to happen constantly.

One consolation is that since AI is great at information aggregation, it can help us aggregate and summarize all these new updates. But tools can help only to a certain extent. The more overwhelming a space is, the more important it is to have a framework to help us navigate it. This book aims to provide such a framework.

The rest of the book will explore this framework step-by-step, starting with the fundamental building block of AI engineering: the foundation models that make so many amazing applications possible.

Edit this pageorReport an issue

The AI Engineering Stack

The three layers of the AI stack, how AI engineering differs from ML engineering and full-stack development, and how foundation models reshape model and application development.