Rename directory and add links in readme

Rename the sample for clarity to highlight the use-case of single user personalization. Updated the readme files to include links to the the new sample.

Author: annainspace

README.md

@@ -21,6 +21,9 @@ The [next_steps/](next_steps/) folder contains detailed examples of the followin
 
 * Generative AI
   - [Personalized marketing campaigns](/next_steps/generative_ai/personalized_marketing_campaign/)
+  - [User personalized marketing messaging with Amazon Personalize and Generative AI](user_personalized_marketing_messaging_with_amazon_personalize_and_gen_ai/). 
+        - Use this sample to create personalized marketing content (for instance emails) for each user using [Amazon Personalize](https://aws.amazon.com/personalize/) and [Amazon Bedrock](https://aws.amazon.com/bedrock/). In this sample you will train an [Amazon Personalize](https://aws.amazon.com/personalize/) 'Top picks for you' Recommender to get personalized recommendations for each user. You will then generate a prompt that includes the user's preferences, recommendations, and demographics. Finally you will use [Amazon Bedrock](https://aws.amazon.com/bedrock/) to generate a personalized email for each user.
+
 
 * Scalable Operations examples for your Amazon Personalize deployments
     - [Maintaining Personalized Experiences with Machine Learning](https://aws.amazon.com/solutions/implementations/maintaining-personalized-experiences-with-ml/)

next_steps/generative_ai/README.md

@@ -4,3 +4,4 @@ There are many ways to use foundation models, the basis of generative AI, with A
 
 * Marketing use cases
   - [Personalized marketing campaigns](personalized_marketing_campaign/)
+  - [User personalized marketing messaging with Amazon Personalize and Generative AI](user_personalized_marketing_messaging_with_amazon_personalize_and_gen_ai/). Use this sample to create personalized marketing content (for instance emails) for each user using [Amazon Personalize](https://aws.amazon.com/personalize/) and [Amazon Bedrock](https://aws.amazon.com/bedrock/). In this sample you will train an [Amazon Personalize](https://aws.amazon.com/personalize/) 'Top picks for you' Recommender to get personalized recommendations for each user. You will then generate a prompt that includes the user's preferences, recommendations, and demographics. Finally you will use [Amazon Bedrock](https://aws.amazon.com/bedrock/) to generate a personalized email for each user.

next_steps/generative_ai/personalized_marketing_content_generator/01_Introduction_and_Data_Preparation.ipynb renamed to next_steps/generative_ai/user_personalized_marketing_messaging_with_amazon_personalize_and_gen_ai/01_Introduction_and_Data_Preparation.ipynb

@@ -17,7 +17,7 @@
     "\n",
     "## Introduction <a class=\"anchor\" id=\"intro\"></a>\n",
     "\n",
-    "In the previous notebook: [`02_Train_Personalize_Model_01_Data.ipynb`](02_Train_Personalize_Model_01_Data.ipynb) you prepared datasets that represent User interactions, Media catalog data and subscriber/user data and created Datasets in Amazon Personalize for this data.\n",
+    "In the previous notebook: [`02_Train_Personalize_Model_01_Data.ipynb`](02_Train_Personalize_Model_01_Data.ipynb) you prepared datasets that represent User interactions, and Media catalog data, and created Datasets in Amazon Personalize for this data.\n",
     "\n",
     "In this Notebook we will train a Domain Optimized Recommender that returns video recommendations. The goal is to recommend products that are relevant based on a particular user.\n",
     "\n",

next_steps/generative_ai/personalized_marketing_content_generator/02_Train_Personalize_Model_01_Data.ipynb renamed to next_steps/generative_ai/user_personalized_marketing_messaging_with_amazon_personalize_and_gen_ai/02_Train_Personalize_Model_01_Data.ipynb

@@ -8,9 +8,14 @@
     "\n",
     "This notebook demonstrates how to clean up all the resources created in the previous set of notebooks.\n",
     "\n",
-    "This notebook uses the functions defined below, to iterate throught the resources inside a dataset group. The dataset group arn is defined in the Notebook [`01_Personalized_Emails_with_Personalize_and_Generative_AI.ipynb`](01_Personalized_Emails_with_Personalize_and_Generative_AI.ipynb)"
+    "This notebook uses the functions defined below, to iterate throught the resources inside a dataset group. The dataset group arn is defined in the Notebook [`01_Personalized_Emails_with_Amazon_Personalize_and_Generative_AI.ipynb`](01_Personalized_Emails_with_Amazon_Personalize_and_Generative_AI.ipynb)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -27,9 +32,7 @@
    "outputs": [],
    "source": [
     "import sys\n",
-    "import getopt\n",
     "import logging\n",
-    "import botocore\n",
     "import boto3\n",
     "import time\n",
     "from packaging import version\n",

next_steps/generative_ai/personalized_marketing_content_generator/03_Train_Personalize_Model_02_Training.ipynb renamed to next_steps/generative_ai/user_personalized_marketing_messaging_with_amazon_personalize_and_gen_ai/03_Train_Personalize_Model_02_Training.ipynb

@@ -4,18 +4,12 @@
 
 **Industry: Media & Entertainment (M&E)**
 
-**Horizontal Use Case: Personalization**
-
-This example helps solve a use case where you are sending marketing emails to a user base using automatically generated text and want to recommend content (in this case movies) using a personalization engine.
-
-This design pattern is broadly applicable to use cases where LLM's are generating personalized messages with an infinite number of combinations of user meta data and personalized product recommendations.
-
 # Key Technologies
 
 - Amazon Bedrock
   - Claude model
 - Amazon Personalize
-  - Real time product recommendations
+  - Real-time item recommendations
 
 # Getting Started
 
@@ -28,7 +22,7 @@ This demo will walk you through how to create personalized marketing content (fo
 
 3. Train an Amazon Personalize 'Top picks for you' Recommender to get personalized recommendations for each user.
 4. Generate a prompt that includes the user's preferences, recommendations, and demographics.
-5. Generate a custom email for each user with [Amazon Bedrock](https://aws.amazon.com/bedrock/).
+5. Generate a personalized email for each user with [Amazon Bedrock](https://aws.amazon.com/bedrock/).
 
 ## Environment Prerequisites