Text to Structured Text

Examples or demos you can use to explain Text-to-Structured Text (like CSV).

Demo 1: Extracting Emails to a CSV Table

Imagine you’ve received a message with multiple recipients in CC, and you need to organize those email addresses into a clean table. Manually copying and pasting each one can be tedious, time-consuming, and prone to errors.

With a Text-to-CSV prompt, you can extract these emails and transform them into a structured CSV file in seconds.

Transform this list of emails into a CSV, if needed infer missing information from the email structure:

[email protected]; DOE, Global Solutions <[email protected]>; BROWN, Michael (Tech Innovators) <[email protected]>; MARTINEZ, Sophia (World Corp) <[email protected]>; JOHNSON, Emily (Future Ventures) <[email protected]>

Demo 2: Representing a List of Contacts as a Mind Map

When working with a long list of contacts, a visual format like a mind map can help you quickly identify relationships, groupings, or patterns.

By converting your contact list into an OPML (Outline Processor Markup Language) file, you can easily import it into popular mind-mapping tools and see your data organized in a hierarchical structure.

Mindmap of a contact list

Create a mindmap OPML for this Here’s the list of contacts organized by company:

### **Company XYZ** 
- John Smith ([email protected]) 
- Alice Green ([email protected]) 
- Robert Wilson ([email protected]) 

### **Global Solutions** 
- Jane Doe ([email protected]) 
- Susan Lee ([email protected]) 
- Daniel Kim ([email protected]) 

### **Tech Innovators** 
- Michael Brown ([email protected]) 
- Sarah Davis ([email protected]) 
- David Clark ([email protected]) 

### **World Corp** 
- Sophia Martinez ([email protected]) 
- Emily White ([email protected]) 
- Jack Turner ([email protected]) 

### **Future Ventures** 
- Emily Johnson ([email protected]) 
- Olivia Taylor ([email protected]) 
- James Harris ([email protected])