Prompt Engineering for LLMs

The Art and Science of Building Large Language Model-Based Applications

Author: John Berryman and Albert Ziegler

Paperback

This book will teach you the art and science of prompt engineering-the key to unlocking the true potential of LLMs. Industry experts John Berryman and Albert Ziegler share how to communicate effectively with AI, transforming your ideas into a language model-friendly format.

New

$148.14

Or pay later with

Free 30 day returns Secure transaction

Check delivery options

Paperback

PRODUCT INFORMATION

Summary

Description

Large language models (LLMs) promise unprecedented benefits. Well versed in common topics of human discourse, LLMs can make useful contributions to a large variety of tasks, especially now that the barrier for interacting with them has been greatly reduced. Potentially, any developer can harness the power of LLMs to tackle large classes of problems previously beyond the reach of automation.

This book provides a solid foundation of LLM principles and explains how to apply them in practice. When first integrating LLMs into workflows, most developers struggle to coax useful insights from them. That's because communicating with AI is different from communicating with humans. This guide shows you how to present your problem in the model-friendly way called prompt engineering.

With this book, you'll:

Examine the user-program-AI-user model interaction loop
Understand the influence of LLM architecture and learn how to best interact with it
Design a complete prompt crafting strategy for an application that fits into the application context
Gather and triage context elements to make an efficient prompt
Formulate those elements so that the model processes them in the way that's desired
Master specific prompt crafting techniques including few-shot learning, and chain-of-thought prompting

About the Author

John Berryman started out in Aerospace Engineering but soon found that he was more interested in math and software than in satellites and aircraft. He soon switched to software development, specializing in search and recommendation technologies, and not too long afterward co-authored Relevant Search. At GitHub John played a prominent role in moving code search to a new scalable infrastructure. Subsequently John joined the Data Science team, and then Copilot where he currently provides technical leadership and direction in Prompt Crafting work. Albert Ziegler is a principal machine learning engineer with a PhD in Mathematics and a home at GitHub Next, GitHub's innovation and future group. His main interests are fusion of deductive and intuitive reasoning to improve the software development experience. At GitHub Next, he was part of the trio that conceived and implemented GitHub Copilot, the first large scale product delivering generative AI for software development. His most recent projects include Copilot Radar and AI for Pull Requests.