One doubt about L2: Module 3 - Evaluate inputs: Classification

In the course explanation of Isa, in the video, she explains that using delimiters is useful and recommended to diferenciate different sections, and make clearer to the model the different parts of the prompt.

Following this thought, would not be recommended to separate probably with other delimiter…for example $$$$ the primary category definitions and then to separate the second category:

delimiter = "####"
delimitercategory = "$$$$"

system_message = f"""
You will be provided with customer service queries. \
The customer service query will be delimited with \
{delimiter} characters.
Classify each query into a primary category \
and a secondary category. 
Provide your output in json format with the \
keys: primary and secondary.
Primary categories: Billing, Technical Support, \
Account Management, or General Inquiry.
Billing secondary categories:
Unsubscribe or upgrade
Add a payment method
Explanation for charge
Dispute a charge
Technical Support secondary categories:
General troubleshooting
Device compatibility
Software updates
Account Management secondary categories:
Password reset
Update personal information
Close account
Account security
General Inquiry secondary categories:
Product information
Speak to a human

Or even create an additional delimeter for second category:

delimetersecondcategory= "////"

Would this be a good/recommended practice ? Or would confuss the model ?