prose vs rasa NLU: What are the differences?

# Introduction
In this Markdown, we will discuss the key differences between prose and Rasa NLU.

1. **Contextual Understanding**: A major difference between prose and Rasa NLU is that while prose relies on the human ability to understand context and nuances in language, Rasa NLU uses machine learning algorithms to identify patterns in the data and understand the context of a conversation.
   
2. **Intent Recognition**: In prose, the understanding of intent is based on the reader's interpretation, while in Rasa NLU, intents are predefined and the system is trained to recognize these intents based on the input it receives.
   
3. **Entity Extraction**: Unlike prose, Rasa NLU includes entity extraction, which involves identifying specific pieces of information within a text, such as dates, locations, and names. This allows for a more detailed understanding of the user's input.
   
4. **Training Process**: Prose does not require a specific training process, as it relies on the reader's ability to discern meaning. On the other hand, Rasa NLU needs to be trained with labeled data to improve its understanding and accuracy in recognizing intents and entities.
   
5. **Response Generation**: In prose, responses are generated based on manual input from the writer, whereas in Rasa NLU, responses are generated using predefined templates or by executing custom actions based on the intent and entities identified.
   
6. **Scalability and Flexibility**: Rasa NLU offers more scalability and flexibility compared to prose, as it can be trained to recognize new intents and entities, making it adaptable to a wide range of conversational scenarios.

In Summary, Rasa NLU differs from prose in terms of its contextual understanding, intent recognition, entity extraction, training process, response generation, and scalability and flexibility.