explaingit

xindoo/agentic-design-patterns

4,766HTMLAudience · developerComplexity · 2/5Setup · easy

TLDR

A complete Chinese translation of Google's book on building AI agents, covering 21 core patterns for making AI systems that can plan, use tools, reflect on their work, and coordinate with each other. All 32 chapters are available as a browsable website.

Mindmap

mindmap
  root((Agentic Patterns))
  Foundational Patterns
    Prompt chaining
    Routing requests
    Parallelization
  Advanced Patterns
    Self-reflection
    Tool use
    Multi-agent coordination
  Memory and Knowledge
    Session memory
    RAG retrieval
    Knowledge bases
  Practical Topics
    Error handling
    Human in the loop
    Goal monitoring
  Appendices
    Agent frameworks
    Coding agents
    Prompting techniques
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Learn the 21 core patterns used to build reliable AI agent systems before writing any code

USE CASE 2

Understand how to chain AI prompts together so complex tasks are broken into manageable steps

USE CASE 3

Study how multi-agent systems coordinate so you can design your own AI workflows

USE CASE 4

Read in Chinese the standard reference for AI agent architecture originally published by Google

Tech stack

MarkdownAI agentsLLMRAG

Getting it running

Difficulty · easy Time to first run · 5min

Pure reading resource, no code to run. Browse online at adp.xindoo.xyz or clone the repo to read locally. Original English files are included alongside Chinese translations.

No license specified in the explanation, this is a translation project of a Google-published book.

In plain English

This repository is a Chinese translation of a book called "Agentic Design Patterns," originally published by Google. The book explains how to build AI agent systems, and this project makes that material available to Chinese-speaking readers. All 32 chapters and appendices have been translated and are hosted as a browsable website at adp.xindoo.xyz. An AI agent, in the context of this book, is a program that uses a language model to take actions, make decisions, and complete tasks with some level of independence. The book walks through 21 core patterns that developers use when building these systems. Early chapters cover foundational approaches such as prompt chaining (breaking a task into a sequence of steps), routing (directing requests to different handlers based on their type), and parallelization (running multiple model calls at the same time). Later chapters address more advanced concepts including how agents reflect on and revise their own outputs, how they use external tools, how multiple agents can coordinate with each other, and how they manage memory across a session. The final chapters cover practical concerns: how to retrieve information from a knowledge base (a technique often called RAG), how agents communicate with each other using a protocol called A2A, how to set goals and monitor progress, how to handle errors, and how to keep a human in the loop when needed. There are also appendices covering advanced prompting techniques, a survey of agent frameworks, agents on the command line, and coding-specific agents. The repository stores the translated Markdown files alongside the original English versions for reference. Readers can browse the content online or clone the repository to read locally. The project is open to contributions, primarily focused on reviewing and improving the quality of the existing translations rather than adding new content.

Copy-paste prompts

Prompt 1
Based on the agentic design patterns book, explain the difference between prompt chaining and parallelization, and give me a concrete example of when to use each one.
Prompt 2
I'm building an AI agent that needs to use external tools and reflect on its results. Which patterns from the Agentic Design Patterns book apply, and how do I implement them?
Prompt 3
Explain the RAG pattern from Agentic Design Patterns: what problem it solves, how it works, and a simple code sketch of how to implement it.
Prompt 4
I want my AI agent to know when to ask a human for help instead of guessing. Which chapter in Agentic Design Patterns covers human-in-the-loop design and what does it recommend?
Open on GitHub → Explain another repo

← xindoo on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.