精选资料索引

更新时间：2026-03-03。 说明：以官方文档、权威机构与高质量论文为主，不追求“链接数量”，追求可执行价值。

一、平台官方最佳实践

• OpenAI Prompt Engineering
  • https://developers.openai.com/api/docs/guides/prompt-engineering
• OpenAI Reasoning Best Practices
  • https://developers.openai.com/api/docs/guides/reasoning-best-practices
• OpenAI Structured Outputs
  • https://developers.openai.com/api/docs/guides/structured-outputs
• OpenAI Safety Best Practices
  • https://developers.openai.com/api/docs/guides/safety-best-practices
• OpenAI Production Best Practices
  • https://developers.openai.com/api/docs/guides/production-best-practices
• OpenAI Evals Guide
  • https://developers.openai.com/api/docs/guides/evals
• OpenAI Evals Cookbook Example
  • https://developers.openai.com/cookbook/examples/evaluation/getting_started_with_openai_evals
• Anthropic Prompt Engineering Overview
  • https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview
• Anthropic Prompting Best Practices
  • https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices
• Anthropic Engineering: Building agents with the Claude Agent SDK
  • https://claude.com/blog/building-agents-with-the-claude-agent-sdk
• Google Gemini Prompt Design Strategies
  • https://ai.google.dev/gemini-api/docs/prompting-strategies
• Google Gemini Function Calling
  • https://ai.google.dev/gemini-api/docs/function-calling
• Google Gemini Long Context
  • https://ai.google.dev/gemini-api/docs/long-context

二、安全与治理

• OWASP Top 10 for LLM Applications v1.1
  • https://owasp.org/www-project-top-10-for-large-language-model-applications/
• NIST AI Risk Management Framework
  • https://www.nist.gov/itl/ai-risk-management-framework
• EU AI Act Regulatory Framework（官方时间线）
  • https://digital-strategy.ec.europa.eu/en/policies/regulatory-framework-ai

三、学习与教育（AI + Learning Science）

• ChatGPT Study Mode FAQ
  • https://help.openai.com/en/articles/11780217-chatgpt-study-mode-faq
• ChatGPT Release Notes（含 Study Mode 时间点）
  • https://help.openai.com/en/articles/6825453-chatgpt-release-notes
• Google LearnLM
  • https://ai.google.dev/gemini-api/docs/learnlm
• UNESCO: Guidance for generative AI in education and research
  • https://www.unesco.org/en/articles/guidance-generative-ai-education-and-research
• Dunlosky et al. (2013) 学习技术综述（APS 页面）
  • https://www.psychologicalscience.org/publications/journals/pspi/learning-techniques.html
• Scientific Reports (2025): AI tutoring RCT
  • https://www.nature.com/articles/s41598-025-97652-6

四、关键研究论文（方法论底座）

• RAG: Retrieval-Augmented Generation (NeurIPS 2020)
  • https://arxiv.org/abs/2005.11401
• Chain-of-Thought Prompting
  • https://arxiv.org/abs/2201.11903
• ReAct: Synergizing Reasoning and Acting
  • https://arxiv.org/abs/2210.03629

五、怎么用这份索引

1. 先从“平台官方最佳实践”建立工程底座。
2. 再把“安全与治理”映射成你的发布门禁。
3. 最后将“学习与教育”方法迁移到个人或团队学习流程。
4. 每周按 每周更新清单 维护文档新鲜度。

六、按角色快速查阅

开发者优先读

• Prompt Engineering
• Structured Outputs
• Evals Guide
• Production Best Practices
• RAG / ReAct 论文

产品经理优先读

• Evals Guide 与评测案例
• Safety Best Practices
• OWASP LLM Top 10
• NIST AI RMF
• EU AI Act 时间线

七、Agent 工程专题资料

• Agent 基础设施资料索引

八、OpenClaw 专题资料

• OpenClaw 资料索引