Prompt Engineering Guide
πŸ˜ƒ Basics
πŸ’Ό Applications
πŸ§™β€β™‚οΈ Intermediate
πŸ€– Đẑi lΓ½
βš–οΈ Reliability
πŸ–ΌοΈ Image Prompting
πŸ”“ Prompt Hacking
πŸ”¨ Tooling
πŸ’ͺ Prompt Tuning
🎲 Miscellaneous
Models
πŸ“™ Vocabulary Reference
πŸ“š Bibliography
πŸ“¦ Prompted Products
πŸ›Έ Additional Resources
πŸ”₯ Hot Topics
✨ Credits
πŸ’Ό Applications🟒 Writing An Email

Writing An Email

🟒 This article is rated easy
Reading Time: 2 minutes
Last updated on August 7, 2024

Sander Schulhoff

Writing emails can be a time consuming task, especially when you need to read through an email you received first. This section will cover use cases ranging from a simple email telling your boss you are sick today to more complex cold lead emails.

Basic Sick Day Email

Imagine that you wake up sick one day and can't go into work (or just don't want to 😈). Here is a simple prompt that writes an email to your boss telling them you are sick.

This email works, but is pretty boring. Let's spice it up a bit!

Style Modifiers/Instructions

It is very easy to modify the style of the email. For example, you can ask the AI to be 'humorous' or instruct it to 'Include a funny reason'.


Here is another example that is more serious/professional.


Responding to an Email

Imagine that you receive a long email from your boss with a lot of information. You need to respond to the email, but you don't have time to read through the entire thing. You can plug the email into an AI and ask it to Generate a summary of this and a list of action items.


You can then use this summary to write a response email.


Note that you can often combine these two steps into one. You can ask the AI to generate a response email directly from the email you received.

Cold Emails

Cold emails are emails sent to people that you don't know. It is difficult to get a response from cold emails, so it can be helpful to send out a lot of personally customized emails. Let's see how to do that with GPT-3.

This is neat, but we can do better. Let's add some more information to the prompt.

Using unstructured information

Say you have the linkedin profile of the person you are sending the email to. You can add that information to the prompt to make the email more personalized. Let's use the founder of Strive's LinkedIn as an example. We'll copy a bunch of information from his profile and add it to the prompt.

It is super useful that LLMs can cut through the clutter of all the information we copied from LinkedIn. This cold outreach process can also be automated at a larger scale by scraping LinkedIn for relevant information.

Conclusion

LLMs can help you write emails! Make sure you read what they write before sending it πŸ˜‰

More

Sander Schulhoff

Sander Schulhoff is the Founder of Learn Prompting and an ML Researcher at the University of Maryland. He created the first open-source Prompt Engineering guide, reaching 3M+ people and teaching them to use tools like ChatGPT. Sander also led a team behind Prompt Report, the most comprehensive study of prompting ever done, co-authored with researchers from the University of Maryland, OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions. This 76-page survey analyzed 1,500+ academic papers and covered 200+ prompting techniques.

Footnotes

  1. Bonta, A. (2022). How to use OpenAI’s ChatGPT to write the perfect cold email. https://www.streak.com/post/how-to-use-ai-to-write-perfect-cold-emails ↩