Structuring Data
- Use AI to organize data into tables: LLMs like ChatGPT can help summarize important points from reports and articles into clear, structured tables for easy use.
- Extract valuable information: By inputting text from business reports, ChatGPT can generate tables that highlight key metrics, such as revenue and profit margins, for better clarity.
- Easily transfer to other formats: Once the table is generated, it can be copied and pasted into spreadsheets like Excel or Google Sheets, as well as documents and presentations.
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. Chatbots like ChatGPT can help you do this.
We can extract information from the following report:
Prompt
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 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:
AI Output
Metric | Value |
---|---|
Revenue | $50 million |
Profit Margin | 12% |
Net Profit | $6 million |
Customer Base | 100,000 |
Operating Expenses | $10 million |
Employee Headcount | 500 |
Revenue Increase | 15% |
Customer Increase | 20% |
Operating Expenses Increase | 10% |
Employee Headcount Increase | 25% |
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.