Prompt Engineering Guide
πŸ˜ƒ Basics
πŸ’Ό Applications
πŸ§™β€β™‚οΈ Intermediate
πŸ€– АгСнты
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🟒 Structuring Data

Structuring Data

🟒 This article is rated easy
Reading Time: 1 minute
Last updated on August 7, 2024

Sander Schulhoff

One simple and exciting use case for LLMs is organizing data into tables. Perhaps you have a bunch of news articles or business reports, and you would like all of the important points to be summarized in a table that you can then put into a spreadsheet or database. Chat bots like ChatGPT can help you do this.

We can extract information from the following report by appending Generate a table containing this information: to it.

In a recent business report presentation, the CEO of Zana Corp. highlighted their remarkable growth in the past fiscal year. She shared that the company experienced a 15% increase in revenue, reaching $50 million, with a 12% profit margin ($6 million in net profit). The report also showcased a 20% growth in their customer base, now totaling 100,000 customers. Additionally, the company's operating expenses went up by 10%, amounting to $10 million, while the employee headcount increased by 25%, resulting in a current workforce of 500 employees.

Generate a table containing this information:

ChatGPT will output a table like the following:

MetricValue
Revenue$50 million
Profit Margin12%
Net Profit$6 million
Customer Base100,000
Operating Expenses$10 million
Employee Headcount500
Revenue Increase15%
Customer Increase20%
Operating Expenses Increase10%
Employee Headcount Increase25%

You can then copy and paste it into a spreadsheet like Excel/Sheets or even documents and powerpoints.

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.