What Is Prompt Engineering?
Prompt engineering is writing and refining the text you give an AI model, such as instructions, examples and documents, so it returns the output you want.
The prompt engineering guide covers the core techniques with before-and-after examples. Vendors publish their own advice, including Anthropic, Google and OpenAI.
Two techniques have their own guides. Few-shot prompting puts worked examples in the prompt, and takes its terms from the 2020 GPT-3 paper. Chain-of-thought prompting gets the model to write out its reasoning before answering, as studied in a 2022 Google paper.
Few-Shot Prompting Explained: Zero-Shot, One-Shot and In-Context Learning
Few-shot prompting explained with examples: zero-, one- and few-shot as defined in the GPT-3 paper, in-context learning, and what research found about examples.
Chain-of-Thought Prompting Explained: Step-by-Step AI Reasoning
What chain-of-thought prompting is, with examples: the 2022 Wei paper, zero-shot "Let's think step by step" (17.7% to 78.7%), self-consistency and thinking modes.
Prompt Engineering Guide: How to Write Better AI Prompts
How to write AI prompts that work: be specific, add context, few-shot examples, chain-of-thought, roles and output formats, with before-and-after examples.
Showing 1–3 of 3 guides