# Free courses on prompt engineering: from beginner to developer

Prompt engineering has become one of the key skills when working with AI models. A properly formulated request is not only a way to get a high-quality result but also a tool for automation, content generation, analytics, and much more.

**[Prompt Engineering for ChatGPT by Vanderbilt University](<https://www.coursera.org/learn/prompt-engineering>)**One of the most popular free courses on the topic on the Coursera platform. It contains six modules with theory, practice, and examples — from basic concepts to prompt engineering templates. Suitable for both beginners and experienced professionals. Duration is about 18 hours.

**[ChatGPT Prompt Engineering for Developers by DeepLearning.AI](<https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/>)**A course from the OpenAI team and Andrew Ng. Suitable for developers and specialists familiar with Python. Covers techniques for text generation, transformation, classification, and API integration.  

**[Basics of Prompt Engineering by Alison](<https://alison.com/course/basics-of-prompt-engineering>)**An introductory course for beginners who are just starting to work with language and generative AI models. It covers zero-shot and few-shot approaches, as well as practices for creating clear and accurate prompts. Suitable for those who want to quickly get up to speed on the topic.

**[Essentials of Prompt Engineering by AWS](<https://learnprompting.org/blog/prompt_engineering_courses>)**A course by LearnPrompting.org and AWS introduces key principles of working with language models: structuring prompts, choosing formats, and creating chains of thought. Includes practical exercises and analysis of common mistakes.

[**Prompt Engineering Best Practices by OpenAI**](<https://platform.openai.com/docs/guides/prompt-engineering>)An official guide from OpenAI describing best practices for working with GPT models. There are no videos or assignments — only text, but it covers everything: from formatting to managing tone and generation results. Recommended as a foundation before any other courses.

[**Prompt Engineering Guide by IBM**](<https://www.ibm.com/think/topics/prompt-engineering-guide>)A practical guide created for users working with language models such as GPT-4, Gemini, and IBM Granite. It explains key principles for creating effective prompts, presents techniques like zero-shot, few-shot, chain-of-thought, and prompt chaining, and provides examples of prompt templates for various tasks — from text generation to data analysis.

**[Prompt Engineering Guide on GitHub](<https://github.com/brexhq/prompt-engineering>)**An extensive internal document that compiles strategies, techniques, and recommendations for working with language models such as GPT-4. It describes the history and evolution of LLMs, security practices, hidden prompts, token limits, and examples of effective prompt usage in production tasks.

[**Prompt Engineering Guide by DAIR.AI**](<https://www.promptingguide.ai/ru>)Here you will find current prompting techniques, practical examples, articles, tools, and the latest developments in the field of LLMs. The guide is suitable for both researchers and developers who want to create robust prompts, use external tools, improve accuracy, and unlock the full potential of language models.

[**Prompt Engineering Guide by Lee Boonstra**](<https://www.kaggle.com/whitepaper-prompt-engineering>)This guide explains how to properly formulate prompts for language models, including Gemini in Vertex AI. It thoroughly covers methods, tips, and potential challenges so you can confidently use LLMs and improve the quality of their responses.

[**Master the Perfect ChatGPT Prompt Formula by Jeff Su**](<https://youtu.be/jC4v5AS4RIM?si=tQcwCZVIajki8qT9>)In this video, Jeff Su shows in eight minutes how to create effective prompts for ChatGPT and Google Bard. He breaks down six essential elements of a good prompt — task, context, examples, persona, format, and tone — and explains with concrete examples how they improve the model's responses.
