Sources

<!-- registry: A11 -->

S1 — Anthropic Interactive Prompt Engineering Tutorial

URL: https://github.com/anthropics/prompt-eng-interactive-tutorial

  • authority: official-docs
  • supports: Prompt 基本结构、Few-shot learning、Chain-of-thought 等核心概念和最佳实践。
  • key-fact: "Chain-of-thought (CoT) prompting enables complex reasoning capabilities through intermediate reasoning steps."

S2 — OpenAI Prompt Engineering Best Practices

URL: https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-the-openai-api

  • authority: official-docs
  • supports: Prompt 工程的六大策略：写清晰的指令、提供参考文本、拆分复杂任务、给模型思考时间、使用外部工具、系统化测试。
  • key-fact: "For best results, we generally recommend using the latest, most capable models. Newer models tend to be easier to prompt engineer."

S3 — Anthropic Prompt Engineering Overview

URL: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview

  • authority: official-docs
  • supports: Claude 特定的 prompt 技术，包括 XML 标签、角色设定、长上下文处理。
  • key-fact: "An example-filled tutorial that covers the prompt engineering concepts found in the docs."

S4 — Prompt Engineering Guide - Few-Shot Prompting

URL: https://www.promptingguide.ai/techniques/fewshot

  • authority: authoritative-guide
  • supports: Few-shot prompting 的定义、使用方法和最佳实践。
  • key-fact: "Following the findings from Min et al. (2022), here are a few more tips about demonstrations/exemplars when doing few-shot: the label space and the distribution of the input text specified by the demonstrations are both important."

S5 — Prompt Engineering Guide - Chain-of-Thought

URL: https://www.promptingguide.ai/techniques/cot

  • authority: authoritative-guide
  • supports: Chain-of-thought prompting 技术的原理、实现方法和应用场景。
  • key-fact: "Introduced in Wei et al. (2022), chain-of-thought (CoT) prompting enables complex reasoning capabilities through intermediate reasoning steps."

S6 — IBM Prompt Engineering Guide 2026

URL: https://www.ibm.com/think/prompt-engineering

  • authority: authoritative-guide
  • supports: 2026 年 prompt 工程的最新趋势和综合指南。
  • key-fact: "Prompt engineering is the new coding. In a world increasingly driven by machine learning, the ability to communicate with AI-generated systems by using natural language is essential."

S7 — Prompt Engineering Best Practices 2026

URL: https://thomas-wiegold.com/blog/prompt-engineering-best-practices-2026/

  • authority: blog
  • supports: 2026 年 prompt 工程最新实践和模型差异。
  • key-fact: "The discipline has split cleanly in two: casual prompting (which anyone can do — the models got better at reading intent) and production context engineering (which is a genuine engineering skill)."

S8 — AI Prompt Debugging: Fixing Issues Through Iteration

URL: https://whitebeardstrategies.com/blog/ai-prompt-debugging-fixing-issues-through-iteration/

  • authority: blog
  • supports: Prompt 调试和迭代优化的系统化方法。
  • key-fact: "Debugging AI prompts isn't a one-time task; it's an iterative process where each cycle reveals new insights."

S9 — 提示工程指南（中文）

URL: https://www.promptingguide.ai/zh

  • authority: authoritative-guide
  • supports: 中文 prompt 工程学习资源和最佳实践。
  • key-fact: "提示工程不仅仅是关于设计和研发提示词。它包含了与大语言模型交互和研发的各种技能和技术。"

S10 — Chain of Thought Prompting Guide

URL: https://www.prompthub.us/blog/chain-of-thought-prompting-guide

  • authority: authoritative-guide
  • supports: Chain-of-thought prompting 的详细实现和示例。
  • key-fact: "At its core, Chain of Thought prompting encourages the model to think through the problem in a step-by-step manner, which is supposed to mimic how humans break down complex problems."

S11 — Few-Shot Prompting Guide

URL: https://www.prompthub.us/blog/the-few-shot-prompting-guide

  • authority: authoritative-guide
  • supports: Few-shot prompting 的设计原则和实战应用。
  • key-fact: "Few shot prompting is a prompt engineering technique where you insert examples in your prompt, training the model on what you want the output to look and sound like."

S12 — Prompt Engineering for Code Generation

URL: https://graphite.com/guides/better-prompts-ai-code

  • authority: blog
  • supports: 代码生成场景的 prompt 最佳实践。
  • key-fact: "By spelling out these details, you greatly reduce ambiguity. Microsoft's Developer Tools research group observed that prompts with explicit specifications reduced the need for back-and-forth refinements by 68%."

S13 — Prompt - Wikipedia

URL: https://en.wikipedia.org/wiki/Prompt_engineering

  • authority: encyclopedia
  • supports: Prompt 和 prompt engineering 的标准定义。
  • key-fact: "Prompt engineering is the process of structuring text that can be interpreted and understood by a generative AI model."

S14 — Large Language Model - Wikipedia

URL: https://en.wikipedia.org/wiki/Large_language_model

  • authority: encyclopedia
  • supports: 大语言模型的基本概念和工作原理。
  • key-fact: "A large language model (LLM) is a type of language model notable for its ability to achieve general-purpose language understanding and generation."

S15 — Zero-shot Learning - Wikipedia

URL: https://en.wikipedia.org/wiki/Zero-shot_learning

  • authority: encyclopedia
  • supports: Zero-shot learning 的定义和应用。
  • key-fact: "Zero-shot learning is a problem setup in machine learning where, at test time, a learner observes samples from classes which were not observed during training."