Name: Prompt Engineering Pocket Guide. Techniques for Getting the Most from LLMs (en Inglés)
SKU: 67387605
Price: 31.72 USD
Availability: InStock
Author: Gabriel Anhaia

portada Prompt Engineering Pocket Guide. Techniques for Getting the Most from LLMs (en Inglés)

Prompt Engineering Pocket Guide. Techniques for Getting the Most from LLMs (en Inglés)

Formato

Libro Físico

Editorial

Independently published

Autor

Gabriel Anhaia

Año

2026

Idioma

Inglés

N° páginas

202

Encuadernación

Tapa Blanda

Dimensiones

22.9x15.2x1 cm

ISBN13

9798258893475

Prompt Engineering Pocket Guide. Techniques for Getting the Most from LLMs (en Inglés)

Gabriel Anhaia (Autor) · Independently published · Tapa Blanda

Libro Nuevo Importado

Envío: 19 a 26 días háb.

$ 63.45$ 31.72

-50%

Costos de importación incluídos en el precio ✅

Libro Nuevo

Quedan 100 unidades

$ 31.72

Llega entre el 14 Sep y el 25 Sep a Quito, Pichincha. Seleccionar ubicación

Agregar a lista de deseos

Reseña del libro "Prompt Engineering Pocket Guide. Techniques for Getting the Most from LLMs (en Inglés)"

Write prompts that get results - not hallucinations.

Most developers treat prompting as trial and error. Copy a template, tweak the wording, hope for the best. This book replaces guesswork with engineering. Whether you use ChatGPT, Claude, Gemini, or open-source models, the techniques behind reliable prompts are the same. Prompt Engineering Pocket Guide gives you repeatable patterns you can apply to any LLM.

Inside you will learn:

• System Prompts - Set the rules of the game. Control tone, format, and behavior before the user says a word.
• Few-Shot Prompting - Teach by example. Show the model what good output looks like and watch quality jump.
• Chain-of-Thought - Make the model reason step by step instead of guessing the final answer.
• Structured Output - Get JSON, YAML, or any format you need - reliably, every time.
• Prompt Chaining - Break complex tasks into stages where each prompt builds on the last.
• Temperature & Sampling - Understand what the knobs actually do and when to turn them.
• Prompt Optimization - Iterate systematically with evaluation metrics, not vibes.
• Common Pitfalls - Recognize and fix the patterns that cause hallucinations, refusals, and drift.

Every technique comes with clear Python code examples you can adapt to your stack. No filler, no hype - just the prompting patterns that separate unreliable demos from production-grade LLM applications.

Who this book is for: Software engineers, data scientists, and anyone building on top of LLMs who wants to stop guessing and start engineering their prompts.

Other books in Pocket Guides for Developers (standalone, no reading order):
• System Design Pocket Guide: Fundamentals
• System Design Pocket Guide: Interviews
• AI Agents Pocket Guide
• This book - Prompt Engineering Pocket Guide
• Database Playbook
• LLM Observability Pocket Guide
• Event-Driven Architecture Pocket Guide
• RAG Pocket Guide