doc: Enhance features documentation

README.md

@@ -48,35 +48,13 @@ curl \
 
 ### Features
 
-> [!NOTE]
-> This project is a proof of concept. It is not intended to be used in production. This demonstrates how can be combined Azure Communication Services, Azure Cognitive Services and Azure OpenAI to build an automated call center solution.
+- **Enhanced communication and user experience**: Integrates inbound and outbound calls with a dedicated phone number, supports multiple languages and voice tones, and allows users to provide or receive information via SMS. Conversations are **streamed in real-time** to avoid delays, can be **resumed after disconnections**, and are **stored for future reference**.
+
+- **Advanced intelligence and data management**: Leverages **GPT-4o** and **GPT-4o Realtime** (known for higher performance and a 10–15x cost premium) to achieve nuanced comprehension. Understands domain-specific terms, follows a structured claim schema, and uses **retrieval-augmented generation (RAG)** for context-rich responses. Also generates automated to-do lists, filters inappropriate content, detects jailbreak attempts, and employs Redis caching for efficiency.
+
+- **Customization, oversight, and scalability**: Offers **customizable prompts**, feature flags for controlled experimentation, human agent fallback, and call recording for quality assurance. Integrates Application Insights for monitoring and tracing, provides publicly accessible claim data, and plans future enhancements such as automated callbacks and IVR-like workflows.
 
-- [x] Access the claim on a public website
-- [x] Access to customer conversation history
-- [x] Allow user to change the language of the conversation
-- [x] Assistant can send SMS to the user for futher information
-- [x] Bot can be called from a phone number
-- [x] Bot use multiple voice tones (e.g. happy, sad, neutral) to keep the conversation engaging
-- [x] Company products (= lexicon) can be understood by the bot (e.g. a name of a specific insurance product)
-- [x] Create by itself a todo list of tasks to complete the claim
-- [x] Customizable prompts
-- [x] Disengaging from a human agent when needed
-- [x] Filter out inappropriate content from the LLM, like profanity or concurrence company names
-- [x] Fine understanding of the customer request with GPT-4o and GPT 4o-mini
-- [x] Follow a specific data schema for the claim
-- [x] Has access to a documentation database (few-shot training / RAG)
-- [x] Help the user to find the information needed to complete the claim
-- [x] Jailbreak detection
-- [x] Lower AI Search cost by usign a Redis cache
-- [x] Monitoring and tracing with Application Insights
-- [x] Perform user tests with feature flags
-- [x] Receive SMS during a conversation for explicit wordings
-- [x] Record the calls for audit and quality assurance
-- [x] Responses are streamed from the LLM to the user, to avoid long pauses
-- [x] Send a SMS report after the call
-- [x] Take back a conversation after a disengagement
-- [ ] Call back the user when needed
-- [ ] Simulate a IVR workflow
+- **Cloud-native deployment and resource management**: Deployed on **Azure** with a containerized architecture for easy scaling, cost optimization, and maintainability. Integrates seamlessly with **Azure Communication Services**, **Cognitive Services**, and **OpenAI resources**, ensuring a flexible and secure environment suitable for rapid iteration and continuous improvement.
 
 ### Demo
 
@@ -220,6 +198,9 @@ graph LR
 
 ## Deployment
 
+> [!NOTE]
+> This project is a proof of concept. It is not intended to be used in production. This demonstrates how can be combined Azure Communication Services, Azure Cognitive Services and Azure OpenAI to build an automated call center solution.
+
 ### Prerequisites
 
 [Prefer using GitHub Codespaces for a quick start.](https://codespaces.new/microsoft/call-center-ai?quickstart=1) The environment will setup automatically with all the required tools.