PromptsApr 6, 2026·2 min read

Prompt Engineering Guide — 73K-Star Learning Hub

The most comprehensive open-source prompt engineering resource with guides, papers, notebooks, and courses covering chain-of-thought, RAG, AI agents, and 13 languages. 3M+ learners, MIT.

PR
Prompt Lab · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

  1. Browse the full guide: promptingguide.ai
  2. Start with fundamentals: zero-shot → few-shot → chain-of-thought
  3. Advance to RAG, agents, and function calling
  4. Practice with included Jupyter notebooks

Or clone for offline reading:

git clone https://github.com/dair-ai/Prompt-Engineering-Guide.git

Intro

The Prompt Engineering Guide by DAIR.AI is the most comprehensive open-source resource for learning prompt engineering, with 72,900+ GitHub stars, MIT license, and 3M+ learners across 13 languages. It covers everything from zero-shot prompting to advanced techniques like chain-of-thought reasoning, RAG pipelines, AI agents, function calling, and adversarial prompting — with model-specific guides for ChatGPT, Claude, Gemini, Llama, Mistral, and more. Includes Jupyter notebooks for hands-on practice and links to 60+ research papers.

Best for: developers, researchers, and anyone learning to write better prompts for any LLM. Works with: any LLM (ChatGPT, Claude, Gemini, Llama, Mistral, etc.). Languages: available in 13 languages.


Prompt Engineering Guide — Topics Covered

Fundamentals

  • Zero-shot prompting — No examples, just instructions
  • Few-shot prompting — Learning from examples
  • Chain-of-thought (CoT) — Step-by-step reasoning
  • Self-consistency — Multiple reasoning paths
  • Tree-of-thoughts — Branching exploration

Advanced Techniques

  • Retrieval Augmented Generation (RAG) — Ground responses in external data
  • ReAct prompting — Reasoning + acting for agents
  • Function calling — LLM triggers external tools
  • Multimodal prompting — Text + images + audio

AI Agents

  • Agent architectures and patterns
  • Tool use and orchestration
  • Memory and planning
  • Multi-agent systems

Safety & Security

  • Adversarial prompting attacks
  • Prompt injection defense
  • Jailbreak prevention
  • Output validation

Model-Specific Guides

GPT-4, ChatGPT, Claude, Gemini, Llama 3, Mistral, Phi, Cohere, and more.

FAQ

Q: What is the Prompt Engineering Guide? A: The most comprehensive open-source learning resource for prompt engineering, covering fundamentals to advanced techniques across all major LLMs. 72,900+ stars, 3M+ learners.

Q: Is it free? A: Yes, MIT license. Additional paid courses available through DAIR.AI Academy.


🙏

Source & Thanks

Created by DAIR.AI. Licensed under MIT.

Prompt-Engineering-Guide — ⭐ 72,900+

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.