Prompt Engineering
The practice of crafting effective inputs to AI models to get better, more accurate outputs.
AI-generated
Prompt engineering is the skill of writing inputs (prompts) that produce the best possible AI outputs. This includes techniques like providing context, giving examples (few-shot), asking for step-by-step reasoning (chain of thought), assigning roles, and specifying output formats.
The same AI model can produce mediocre or excellent results depending entirely on how you prompt it. Prompt engineering is the most practical AI skill: it costs nothing to learn, works with every AI tool, and the difference between a good and bad prompt can be dramatic. It is the highest-leverage skill for anyone using AI tools.
Anthropic: Prompt engineering guide - https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview
OpenAI: Prompt engineering documentation - https://platform.openai.com/docs/guides/prompt-engineering
Learn Prompting (open-source course) - https://learnprompting.org/
Lilian Weng: "Prompt Engineering" - https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/