ClassroomThe classroom
Back to the lesson libraryFOUNDATION · 12 MIN
M21.9 CONNECT THE MECHANISM

Prompting in practice: instructions, examples, and step-by-step requests

Mei runs a small bakery and asks a chat assistant for help. Her first prompts get bland, wrong, or made-up answers. Six small rewrites fix them, and each one works for your prompts too.

LESSON OVERVIEW12 min lesson

Lesson overview

Mei runs a small bakery and asks a chat assistant for help. Her first prompts get bland, wrong, or made-up answers. Six small rewrites fix them, and each one works for your prompts too.

What you’ll explore

  • A prompt is the model's only information about your situation. Clear instructions, standing rules in a system prompt, examples, requests for working, a stated output format, and supplied source text make answers more useful, and the answers still need checking.
GO TO THE SOURCE

Original explanations, connected to the research.

Language Models are Few-Shot Learners (Brown et al., 2020)Training language models to follow instructions with human feedback (Ouyang et al., 2022)Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (Wei et al., 2022)Large Language Models are Zero-Shot Reasoners (Kojima et al., 2022)Prompt engineering guide (OpenAI)Prompt engineering overview (Anthropic)
Suggest a correction

A precise note can make an explanation better.

Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.

The file includes this note, the scene title, and lesson metadata. Your saved progress and quiz responses are excluded. Download before leaving or reloading to keep your note.