# Awesome-Prompt-Engineering

A hand-curated collection of papers, tools, models, benchmarks, courses, and communities covering prompt engineering and context engineering for large language models.

The list organizes research papers by topic, including major surveys, prompt optimization and compression, in-context learning, agentic and multi-agent prompting, multimodal prompting, structured output control, and prompt injection and security, alongside a separate section of tools and code covering prompt management and testing, LLM evaluation, agent frameworks, red-teaming, MCP servers, and coding agents and IDEs. Further sections point to datasets and benchmarks, models, AI content detectors, books, courses, tutorials, videos, and communities.

A suggested starting path for a newcomer moves from a short free course, through a widely used open-source prompting guide, to provider-specific guides from OpenAI and Anthropic, and then to a survey paper covering more than fifty prompting techniques drawn from over 1,500 papers.

It is distributed under the Apache-2.0 license.

Website: https://github.com/promptslab/Awesome-Prompt-Engineering