Skip to main content
BookintermediatePaidJapanese

LLMの原理、RAG・エージェント開発から読み解く コンテキストエンジニアリング

by 蒲生弘郷 · 技術評論社

Japanese practitioner guide to building LLM application context: how LLMs generate tokens, structured output and function calling, a full chapter on instruction-prompt design with few-shot and chain-of-thought, then RAG evaluation and agent workflows. Scope broader than pure prompting.

Buy on Amazon.co.jp

This Japanese edition is sold on Amazon.co.jp.

This link may earn us a small commission at no extra cost to you. Affiliate disclosure

More resources on Prompt Engineering

CourseFree

Anthropic Learn

Anthropic's free learning hub, now Claude Academy, with self-paced courses and tutorials on AI fluency, model capabilities and limits, prompt writing, and building applications with the Claude API. Learners can write clearer prompts, judge model output critically, and start developing with Claude.

PaperFree

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Generalizes chain-of-thought prompting into a search over a tree of intermediate reasoning steps, letting a model consider several branches, self-evaluate them, and backtrack. Demonstrated on Game of 24, creative writing, and mini crosswords.

PaperFree

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Shows that prompting a large model with a few worked examples containing intermediate reasoning steps substantially improves arithmetic, commonsense, and symbolic reasoning, and that the effect emerges only at sufficient model scale. The origin of chain-of-thought prompting.

WebsiteFree

Prompt Engineering Guide

Reference covering prompting techniques with worked examples: zero-shot and few-shot, chain-of-thought, self-consistency, ReAct, and tree of thoughts, plus model-specific notes and adversarial prompting risks. Readers finish able to choose techniques deliberately.

BookPaid

Prompt Engineering for LLMs: The Art and Science of Building Large Language Model-Based Applications

Two engineers who built GitHub Copilot explain why prompts work in terms of how models complete text, then build up few-shot patterns, chain-of-thought, retrieval-assembled context and evaluation for production applications rather than one-off chat sessions.

WebsiteFree

Effective Context Engineering for AI Agents

Anthropic's applied AI team reframes prompting as one part of curating the whole context window. Covers context rot, calibrating system prompt specificity, minimal non-overlapping tool sets, just-in-time retrieval, and compaction, note-taking and sub-agents for long-horizon tasks. This is the resource that answers the topic's hardest question - where prompting stops and retrieval, memory or architecture must take over. It gives concrete mechanisms (compaction, structured note-taking, sub-agent isolation) rather than the vague 'context is the new prompt' takes that flooded blogs afterwards.

See all Prompt Engineering resources →