dair-ai/Prompt Engineering Guide
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
The Prompt Engineering Guide is the most popular open resource for learning to prompt large language models, maintained by DAIR.AI. It collects techniques, papers, lectures, and notebooks covering prompt engineering, context engineering, RAG, and AI agents.
Our Review
With more than 75,000 GitHub stars and a web version that has reached over 3 million learners, the Prompt Engineering Guide is the reference many people start with when learning to work with LLMs. DAIR.AI keeps it current, expanding from prompting basics into context engineering, RAG, and agent design.
What the guide covers:
- •Prompting foundations LLM settings, prompt elements, and general tips for designing prompts that actually work.
- •Core techniques zero-shot, few-shot, chain-of-thought, self-consistency, ReAct, and other methods explained with examples.
- •Context engineering and RAG newer sections on managing context and retrieval-augmented generation, reflecting where the field moved.
- •AI agents guidance on agent patterns built on top of solid prompting fundamentals.
- •Papers and references a curated, regularly updated list of the key prompt-engineering research.
- •Runnable notebooks code examples you can open and execute rather than only read.
How to use it:
Read it free on the web at promptingguide.ai, which is cleaner than the raw GitHub markdown, or clone the repo to work through the notebooks locally. Start at the introduction and work forward, or jump straight to a specific technique. DAIR.AI also offers optional paid courses through its Academy for a more hands-on path. The guide is available in 13 languages.
Limitations:
This is a learning resource, not a tool or library, so it teaches concepts rather than doing the work for you. Some prompt-specific tactics date quickly as models change, so a few examples lag the newest model behavior. The repository itself updates less often than the web version (last pushed in March 2026), and the deeper hands-on material lives behind the paid DAIR.AI Academy rather than the free guide.
Our Verdict
The Prompt Engineering Guide is the single best free starting point for learning prompt engineering in 2026, and its move into context engineering and agents keeps it relevant as the field shifts.
For Vibe Builders, it explains the techniques behind getting reliable output from tools like ChatGPT and Claude in plain language, with examples you can copy. You do not need to code to get value from the prompting fundamentals.
For Developers, the value is the curated technique catalog and the linked papers: it is a fast way to map the space, from chain-of-thought to ReAct to RAG, before you implement those methods in your own application. The notebooks give you runnable starting points.
Skip it if you want a hands-on, project-based course rather than a reference guide, in which case the paid DAIR.AI Academy or a structured video course will suit you better. As a free reference, though, little else matches its breadth.
Frequently Asked Questions
Is the Prompt Engineering Guide free?
Yes, the Prompt Engineering Guide is free and open-source under the MIT license, maintained by DAIR.AI, and it has more than 75,000 GitHub stars as of 2026. Both the GitHub repository and the polished web version at promptingguide.ai are free to read. Only the optional DAIR.AI Academy courses are paid.
What does the Prompt Engineering Guide cover?
The guide covers prompting foundations, core techniques such as zero-shot, few-shot, and chain-of-thought prompting, and newer areas including context engineering, retrieval-augmented generation, and AI agents. It also curates the key research papers and provides runnable notebooks. The web version is available in 13 different languages.
Is the Prompt Engineering Guide good for beginners?
Yes, it is written to take someone from no prompting knowledge through to advanced techniques, starting with the basics of how prompts work. The plain-language explanations and copyable examples make it approachable for non-developers, while the technique catalog and papers give developers depth. Each section can be read on its own.
Should I read it on GitHub or the website?
The web version at promptingguide.ai is the recommended way to read the guide because it is cleaner and more current than the raw GitHub markdown. Use the GitHub repository when you want to run the notebooks locally or contribute changes. Both cover the same core material and are completely free.
Who created the Prompt Engineering Guide?
The Prompt Engineering Guide is created and maintained by DAIR.AI, an organization focused on democratizing AI research and education. The project reached the top of Hacker News in 2023 and has since grown to millions of learners. It continues to expand with contributions from the open-source community.
What is Prompt Engineering Guide?
The Prompt Engineering Guide is the most popular open resource for learning to prompt large language models, maintained by DAIR.AI. It collects techniques, papers, lectures, and notebooks covering prompt engineering, context engineering, RAG, and AI agents.
How do I install Prompt Engineering Guide?
Visit the GitHub repository at https://github.com/dair-ai/Prompt-Engineering-Guide for installation instructions.
What license does Prompt Engineering Guide use?
Prompt Engineering Guide uses the MIT license.
What are alternatives to Prompt Engineering Guide?
Explore related tools and alternatives on My AI Guide.
Open source & community-verified
MIT licensed: free to use in any project, no strings attached. 75,332 developers have starred this, meaning the community has reviewed and trusted it.
Reviewed by My AI Guide for relevance, quality, and active maintenance before listing.
Topics