README update

README.md

@@ -1,11 +1,13 @@
 ## paramount
 
-Business Evaluations for LLM Chats - let your experts easily evaluate AI chat accuracy.
+Business Evaluations for LLM Chats - let your agents easily evaluate AI chat accuracy.
 
 ### Getting Started
 1) Install the package: 
 
-`pip install paramount`
+```
+pip install paramount
+```
 
 2) Decorate your AI function:
 
@@ -15,15 +17,15 @@ def my_ai_function(message_history, question,  ...): #  Inputs
     # LLM invocations happen here
     return llm_answer, llm_references, llm_message_history,  ...  # Outputs
 ```
-Include a Flask app as the decorator param for "replay" functionality.
+Here a Flask app has been included as the decorator param, for "replay" functionality.
 
 3) After `my_ai_function(...)` has run several times, launch the Paramount UI to evaluate results: 
 
 ```shell
 paramount
 ```
 
-That's it! You are set. Your SMEs can now evaluate recordings and track accuracy improvements over time.
+Your SMEs can now evaluate recordings and track accuracy improvements over time.
 
 Paramount runs completely offline in your private environment.
 
@@ -61,7 +63,7 @@ chat_list = "output__3"  # Matches llm_message_history. Must be a list of dicts
 chat_list_role_param = "role"  # Key in list of dicts describing the role in the chat
 chat_list_content_param = "content"  # Key in list of dicts describing the content
 ```
-It is also possible to describe references via config but has not been shown here for simplicity. 
+It is also possible to describe references via config but is not shown here for simplicity. 
 
 See `paramount.toml.example` for more info.  
 ### Docker
@@ -72,4 +74,5 @@ With Docker, you'll likely want to mount the `paramount.toml` file dynamically i
 
 ```shell
 docker build -t paramount-server -f Dockerfile.server . # or make docker-build-server
-docker run -dp 9001:9001 paramount-server # or make docker-run-server
+docker run -dp 9001:9001 paramount-server # or make docker-run-server
+```