README

README.md

@@ -4,22 +4,19 @@ Prompete is a wrapper for LiteLLM.
 It integrates LLMEasyTools, and Jinja2 templates to create a flexible system for
 managing prompts and chat interactions. Part of the API is inspired by Claudette.
 
-The key idea behind Prompete is to address the gap between traditional software and LLMs.
-
-While conventional software primarily deals with structured data, LLMs require both data
-- the information that it is supposed to manipulate and instructions on how to interpret
-and use that data.
-Prompete addresses this by separating prompts into two distinct components:
-
-1. Data: The raw information generated by traditional software.
-2. Template: Instructions for the LLM on how to interpret and reason about the
-   data.
-
-This separation allows for a more natural and flexible interface between
-traditional software systems and LLMs because the data and instructions are
-really different in how they are worked with, they change in different ways,
-and are edited in different ways (and tools) for example long text blocks in
-code demolish the visual clues a programmer relies on when reading that code.
+
+The key idea behind Prompete is that LLM prompts contain two distinct components:
+- data: the information that the LLM is supposed to manipulate
+- instructions: the instructions on how to interpret and use that data
+
+These two parts have different nature, and are manipulated differently.
+They change in different rythms and in different phases of the project. They are
+edited in different ways and mixing them together is error prone and makes the
+prompt management harder. For example long text blocks in code demolish the
+visual clues a programmer relies on when reading that code.
+
+Prompete tries to address this by separating the two components into data structures and
+templates.
 
 But that does not mean that when using Prompete you need to start immediately with 
 templated prompts. You can start working in Prompete with simple string prompts,