fix(readme): update structure

Author: dineshpinto

README.md

@@ -4,46 +4,43 @@ Flare AI Kit template for Social AI Agents.
 
 ## 🚀 Key Features
 
-- **AI-Powered Social Response**: Automatically monitor and respond to mentions across Twitter/X and Telegram using Gemini AI
-- **Custom Model Fine-tuning**: Train personalized models using your own dataset or provided examples
-- **TEE Security Integration**: Run in Trusted Execution Environment for hardware-level security
-- **Multi-Platform Support**: Single interface to manage multiple social media platforms with rate limiting and retry mechanisms
+- **Secure AI Execution**  
+  Runs within a Trusted Execution Environment (TEE) featuring remote attestation support for robust security.
 
-## 🎯 Getting Started
+- **Built-in Chat UI**  
+  Interact with your AI via a TEE-served chat interface.
 
-1. **Build with Docker**:
-   ```bash
-   # Build the image
-   docker build -t flare-ai-social .
-   
-   # Run the container
-   docker run -p 80:80 -it --env-file .env flare-ai-social
-   ```
+- **Gemini Fine-Tuning Support**  
+  Fine-tune foundational models with custom datasets.
 
-2. **Access UI**: Navigate to `http://localhost:80`
+- **Social media integrations**  
+  X and Telegram integrations with with rate limiting and retry mechanisms.
 
-## 🛠 Build Manually
+## 🎯 Getting Started
 
-### Fine tuning a model over a dataset
+### Prerequisites
 
-1. **Prepare Environment File**: Rename `.env.example` to `.env` and update these model fine-tuning parameters:
+- [uv](https://docs.astral.sh/uv/getting-started/installation/)
 
-| Parameter | Description | Default |
-|-----------|-------------|---------|
-| `tuned_model_name` | Name of the newly tuned model | pugo-hilion |
-| `tuning_source_model` | Name of the foundational model to tune on | models/gemini-1.5-flash-001-tuning |
-| `epoch_count` | Number of tuning epochs to run. An epoch is a pass over the whole dataset | 30 |
-| `batch_size` | Number of examples to use in each training batch | 4 |
-| `learning_rate` | Step size multiplier for the gradient updates | 0.001 |
+### Fine-tune a model
 
+1. **Prepare Environment File**: Rename `.env.example` to `.env` and update these model fine-tuning parameters:
+
+   | Parameter             | Description                                                               | Default                            |
+   | --------------------- | ------------------------------------------------------------------------- | ---------------------------------- |
+   | `tuned_model_name`    | Name of the newly tuned model                                             | pugo-hilion                        |
+   | `tuning_source_model` | Name of the foundational model to tune on                                 | models/gemini-1.5-flash-001-tuning |
+   | `epoch_count`         | Number of tuning epochs to run. An epoch is a pass over the whole dataset | 30                                 |
+   | `batch_size`          | Number of examples to use in each training batch                          | 4                                  |
+   | `learning_rate`       | Step size multiplier for the gradient updates                             | 0.001                              |
 
 2. **Prepare a dataset:**
    An example dataset is provided in `src/data/training_data.json`, which consists of tweets from
    [Hugo Philion's X](https://x.com/HugoPhilion) account. You can use any publicly available dataset
    for model fine-tuning.
 
-3. **Tune a new model**
-   Set the name of the new tuned model in `src/flare_ai_social/tune_model.py`, then:
+3. **Tune a new model:**
+   Depending on the size of your dataset, this process can take several minutes:
 
    ```bash
    uv run start-tuning
@@ -55,28 +52,28 @@ Flare AI Kit template for Social AI Agents.
 
    ![pugo-hilion_mean_loss](https://github.com/user-attachments/assets/f6c4d82b-678a-4ae5-bfb7-39dc59e1103d)
 
-5. **Test the new model**
+5. **Test the new model:**
    Select the new tuned model and compare it against a set of prompting techniques (zero-shot, few-shot and chain-of-thought):
 
    ```bash
    uv run start-compare
    ```
 
-6. **Start Social Bots**:
+6. **Start Social Bots (optional):**:
+
    - Set up Twitter/X API credentials
    - Configure Telegram bot token
    - Enable/disable platforms as needed
+
    ```bash
    uv run start-bots
    ```
 
-### Build using Docker (Recommended)
-
-**Note:** You can only perform this step once you have finishing training a new model.
+### Interact with model
 
 The Docker setup mimics a TEE environment and includes an Nginx server for routing, while Supervisor manages both the backend and frontend services in a single container.
 
-1. **Build the Docker Image:**
+1. **Build the Docker image**:
 
    ```bash
    docker build -t flare-ai-social .
@@ -89,11 +86,11 @@ The Docker setup mimics a TEE environment and includes an Nginx server for routi
    ```
 
 3. **Access the Frontend:**  
-   Open your browser and navigate to [http://localhost:80](http://localhost:80) to interact with the Chat UI.
+   Open your browser and navigate to [http://localhost:80](http://localhost:80) to interact with the tuned model via the Chat UI.
 
 ## 📁 Repo Structure
 
-```
+```plaintext
 src/flare_ai_social/
 ├── ai/                            # AI Provider implementations
 │   ├── base.py                    # Base AI provider abstraction
@@ -226,4 +223,4 @@ If you encounter issues, follow these steps:
 
 ## 💡 Next Steps
 
-TODO
+TODO