Intro & Table of Contents

Prompt Engineering
Last updated: 2024-05-11
[ assumed audience ]

Individuals with a basic understanding of AI who are interested in exploring the capabilities of language models. Familiarity with technical terms, such as APIs, is required.

Welcome to the Prompt Engineering Interactive Tutorial!

Course introduction and goals

This course is intended to provide you with a comprehensive step-by-step understanding of how to engineer optimal prompts within Claude.

After completing this course, you will be able to:

Course structure and content

This course is structured to allow you many chances to practice writing and troubleshooting prompts yourself. The course is broken up into 9 chapters with accompanying exercises, as well as an appendix of even more advanced methods. It is intended for you to work through the course in chapter order.

Note: This tutorial uses our smallest, fastest, and cheapest model, Claude 3 Haiku. We have two other models, Claude 3 Sonnet and Claude 3 Opus, which are more intelligent than Haiku, with Opus being the most intelligent.

When you are ready to begin, click on the Basic Prompt Structure to proceed.

Table of Contents

[the]nameless note:

This tutorial was originally published on Google Sheets by Anthropic. I've rewritten and adapted the tutorial for the web to suit my needs and preferences. Any formatting or content issues are probably mine. Please DM me on Twitter or open a GitHub issue to report any problems.

Enough intro, let's delve into it!

  • 2024-05-12: Beta release with settings to input a personal API key
    • The tutorial has been shared on Anthropic Discord server
  • 2024-05-09: Utilize tool use for exercises that could benefit from it
  • 2024-05-05: Add metrics such as Time-To-First-Token (TTFT), End-to-End (E2E) latency, and the number of input and output tokens
  • 2024-04-29: Support interactive mode in playground for examples and exercises
  • 2024-04-27: Alpha release with non-interactive playgrounds
  • 2024-04-25: De-sheetify tutorial content
    • (Chapter 1) Update Claude's responses with actual responses from Messages API
    • (Chapter 1) Replace "prompt that has too many newlines" scenario with "prompt that starts with an 'Assistant'"