Introduction to Building AI Applications with Foundation Models

How the scaling of foundation models reshaped AI, lowered the barrier to building applications, and turned AI engineering into one of the fastest-growing disciplines in software.

The Age of Scale

If I could use only one word to describe AI post-2020, it'd be scale. The models behind ChatGPT, Gemini, and Midjourney are at such a scale that they're consuming a nontrivial portion of the world's electricity — and we're at risk of running out of publicly available internet data to train them.

AI's Energy Consumption

Two Consequences of Scaling

The scaling up of AI models has two major consequences that, together, are reshaping who gets to build with AI.

More Powerful Models

AI models are becoming more capable of more tasks, enabling more applications. More people and teams leverage AI to increase productivity, create economic value, and improve quality of life.

Model as a Service

Training large language models (LLMs) requires data, compute, and specialized talent that only a few organizations can afford. Those organizations now make their models available for others to use as a service.

Anyone who wishes to leverage AI to build applications can now use these models without having to invest up front in building one.

The Rise of AI Engineering

The demand for AI applications has increased while the barrier to entry for building them has decreased. This has turned AI engineering — the process of building applications on top of readily available models — into one of the fastest-growing engineering disciplines.

What's New, What's Not

Building applications on top of machine learning (ML) models isn't new. Long before LLMs became prominent, AI was already powering many applications.

Product Recommendations

Fraud Detection

Churn Prediction

While many principles of productionizing AI applications remain the same, the new generation of large-scale, readily available models brings about new possibilities and new challenges — the focus of this book.

What This Chapter Covers

Foundation Models

An overview of foundation models — the key catalyst behind the explosion of AI engineering.

Successful AI Use Cases

A range of real-world applications, each illustrating what AI is good and not yet good at. As AI's capabilities expand daily, predicting its future possibilities becomes increasingly challenging — but existing application patterns can help uncover opportunities today and offer clues about how AI may continue to be used in the future.

The New AI Stack

What has changed with foundation models, what remains the same, and how the role of an AI engineer today differs from that of a traditional ML engineer.

Throughout this book, traditional ML refers to all ML before foundation models.

Edit this pageorReport an issue

The Rise of AI Engineering

Trace how decades of advances in language models, self-supervision, and multimodality produced foundation models — and turned AI engineering into a discipline of its own.