Prompt engineering techniques: clear instructions, few-shot examples, output formats and step-by-step reasoning

Prompt engineering is the practice of writing inputs that reliably get the output you need. It is the cheapest way to improve a generative AI app, so it comes before RAG or fine-tuning. The model only knows what is in its training and in the prompt, and it cannot ask you what you meant, so ambiguity in the prompt becomes inconsistency in the output.