来源:https://github.com/anthropics/courses/blob/master/real_world_prompting/01_prompting_recap.ipynb 爬取日期:2026-03-22
Lesson 1: Essential prompting techniques: a recap
Introduction
Welcome to the first lesson in our “Applied Prompting” course! This course is designed for experienced developers who have already dipped their toes into the world of prompt engineering, particularly those who have completed the comprehensive Prompt Engineering Interactive Tutorial. If you haven’t gone through that tutorial yet, we strongly recommend you do so before continuing, as it provides an in-depth exploration of various prompting techniques with hands-on exercises.
In this initial brief lesson, “Essential prompting techniques: a recap,” we aim to recap the foundational prompting knowledge that we’ll draw from throughout the rest of this course. Our goal with this course is not to rehash the basics but to reinforce these techniques by demonstrating their critical importance in high-stakes, scaled production environments.
Let’s dive in and see how these fundamental techniques can transform the way you interact with Claude in production environments.
Key prompting tips
In this lesson, we’ll cover the following critical prompting tips:
- Use the Prompt Generator
- Be clear and direct
- Use XML tags
- Use examples (multishot prompting)
- Let Claude think (chain of thought prompting)
- Give Claude a role (system prompts)
- Long context tips
This notebook covers the fundamental prompting techniques from Anthropic’s Prompt Engineering Interactive Tutorial. The course is structured for developers with prior prompt engineering experience and focuses on applying these techniques in production environments. The lessons progress from basic technique recaps to real-world applications including medical prompts, prompt engineering optimization, call summarization, and customer support AI systems.