💻 Build

— API・SDK4 articles ▸

How to Choose and Use AI APIs: A Practical Comparison of OpenAI / Anthropic / Google

— セルフホスト2 articles ▸

Introduction to Local LLMs: Where to Use Ollama / vLLM

Ollama Complete Guide: The Standard Tool for Local LLMs

AI Coding Tools▸

Boost developer productivity with coding AIs like Claude Code, Codex, Cursor, and GitHub Copilot

12 articles · 4 groups

— 全体像2 articles ▸

Intro to AI Coding Tools: The Entry to 2x Dev Productivity

AI × Coding: A Practical Guide to Ultra-Fast Development by Strategically Using Cursor, Claude Code, and GitHub Copilot

— 主要ツール5 articles ▸

Getting Started with Claude Code: An AI Coding Assistant from Your Terminal

Cursor Complete Guide

GitHub Copilot Complete Guide

OpenAI Codex Complete Guide

Skills

— 実用ノウハウ3 articles ▸

viii

AI Pair-Programming Mindset: Avoid Dumping and Swallowing

Introducing AI to an Existing Codebase: Guardrails and Review

How to Write Prompts (Coding Edition)

— 深掘り2 articles ▸

Developing a Mobile App with Claude Code

xii

Claude Code Agent Features: Using Sub-agents

— PracticeRead in parallel

Prompt Engineering▸

Structured prompting, few-shot, chain-of-thought, and evaluation

6 articles · 3 groups

— 基本2 articles ▸

Prompt Design for LLM Developers: Basic Principles

Structured Prompts: System Prompts and Role Design

— 技法2 articles ▸

Few-shot and Chain-of-Thought: Raising Reasoning Accuracy

Structured Output: JSON / Function Calling

— 品質管理2 articles ▸

Prompt Evaluation Basics: Reproducibility and Accuracy

Prompt Management: Promptfoo / LangSmith / Helicone

App Development▸

Claude/GPT APIs, AI SDK, and Next.js integration

7 articles · 3 groups

— 全体像1 articles ▸

Intro to LLM App Development: Chat, Assistants, Automation

— API・SDK4 articles ▸

Building a Chat App with APIs: Intro to the Claude / GPT API

Streaming, Tool Use, and Structured Output

Next.js × LLM with the Vercel AI SDK

When to Use LangChain vs LlamaIndex

— クラウド・運用2 articles ▸

Using via Cloud: Bedrock / Vertex

Authentication, Billing, and API Key Management

— Advanced

RAG & Retrieval▸

Embeddings, vector DBs, and search quality improvement

6 articles · 4 groups

— 全体像1 articles ▸

What Is RAG: The Big Picture of Making LLMs Smarter with Your Own Data

— 基礎2 articles ▸

Basics of Embeddings and Vector Search (Developer Edition)

RAG Building Guide: A Practical Roadmap to Make AI Smarter with Your Own Data

— ベクトル DB1 articles ▸

Vector DB Comparison: Pinecone / Weaviate / pgvector / Qdrant

— 品質改善2 articles ▸

Raising Retrieval Quality: Rerankers and Hybrid Search

Fine-Tuning in Practice: LoRA / QLoRA

AI Agents▸

Tool use, autonomous tasks, multi-agent systems, and MCP

7 articles · 3 groups

— 全体像1 articles ▸

Introduction to AI Agent Development: Grasp MCP, Tool Integration, and Multi-Agent Systems

— 設計と実装3 articles ▸

Agent Design Recipes: Tool Use, Sub-agent, Control Flow

Introduction to MCP: Connecting External Tools to Claude

Intro to MCP Server Development: Protocol Spec and Implementation Examples

— 上級・自律3 articles ▸

Multi-Agent Design: LangGraph / Swarm / Sub-agents

Browser-Use / Computer-Use: Screen-Operating Agents

Rules for Operating Agents Internally

Eval & Operations▸

Evaluation, cost optimization, security, and observability

5 articles · 3 groups

— 評価1 articles ▸

Evaluating and Testing LLM Apps: eval / regression / Golden Set

— 運用基盤3 articles ▸

Cost Optimization: Caching, Model Selection, Quantization

Implementing Observability (Logging / Tracing / Metrics)

Rate Limiting, Failover, and Redundancy

— セキュリティ1 articles ▸

Prompt-Injection Defense: Security Implementation from a Developer's View