diff --git a/README.md b/README.md
index 00dd863..5186475 100644
--- a/README.md
+++ b/README.md
@@ -40,7 +40,7 @@ pip install -r requirements.txt
 AG-A supports using both AWS Bedrock and OpenAI as LLM model providers. You will need to set up API keys for the respective provider you choose. By default, AG-A uses AWS Bedrock for its language models.
 
 #### AWS Bedrock Setup
-AG-A integrates with AWS Bedrock by default. To use AWS Bedrock, you will need to configure your AWS credentials and region settings:
+To use AWS Bedrock, you will need to configure your AWS credentials and region settings:
 
 ```bash
 export AWS_DEFAULT_REGION="<your-region>"
@@ -48,11 +48,11 @@ export AWS_ACCESS_KEY_ID="<your-access-key>"
 export AWS_SECRET_ACCESS_KEY="<your-secret-key>"
 ```
 
-Ensure you have an active AWS account and appropriate permissions set up for using Bedrock models. You can manage your AWS credentials through the AWS Management Console. See [Bedrock supported AWS regions](https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-regions.html)
+Ensure you have an active AWS account and appropriate permissions set up for using Bedrock models. You can manage your AWS credentials through the AWS Management Console. See [Bedrock supported AWS regions](https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html).
 
 
 #### OpenAI Setup
-To use OpenAI, you'll need to set your OpenAI API key as an environment variable:
+To use OpenAI, you will need to set your OpenAI API key as an environment variable:
 
 ```bash
 export OPENAI_API_KEY="sk-..."
diff --git a/src/autogluon/assistant/llm/llm.py b/src/autogluon/assistant/llm/llm.py
index f35b80f..3cc2f76 100644
--- a/src/autogluon/assistant/llm/llm.py
+++ b/src/autogluon/assistant/llm/llm.py
@@ -115,8 +115,7 @@ def get_openai_models() -> List[str]:
     @staticmethod
     def get_bedrock_models() -> List[str]:
         try:
-            # TODO: Remove hardcoding AWS region
-            bedrock = boto3.client("bedrock", region_name="us-west-2")
+            bedrock = boto3.client("bedrock")
             response = bedrock.list_foundation_models()
             return [model["modelId"] for model in response["modelSummaries"]]
         except Exception as e:
@@ -166,8 +165,6 @@ def _get_bedrock_chat_model(config: DictConfig) -> AssistantChatBedrock:
                 "temperature": config.temperature,
                 "max_tokens": config.max_tokens,
             },
-            # TODO: Remove hardcoding AWS region
-            region_name="us-west-2",
             verbose=config.verbose,
         )
 
@@ -177,9 +174,11 @@ def get_chat_model(cls, config: DictConfig) -> Union[AssistantChatOpenAI, Assist
         assert config.provider in valid_providers, f"{config.provider} is not a valid provider in: {valid_providers}"
 
         valid_models = cls.get_valid_models(config.provider)
-        assert (
-            config.model in valid_models
-        ), f"{config.model} is not a valid model in: {valid_models} for provider {config.provider}"
+        assert config.model in valid_models, (
+            f"{config.model} is not a valid model in: {valid_models} for provider {config.provider}. "
+            "Please check if the requested model is available in "
+            f"`AWS_DEFAULT_REGION={os.environ.get('AWS_DEFAULT_REGION')}`."
+        )
 
         if config.model not in WHITE_LIST_LLM:
             logger.warning(f"{config.model} is not on the white list. Our white list models include {WHITE_LIST_LLM}")
diff --git a/src/autogluon/assistant/transformer/feature_transformers/caafe.py b/src/autogluon/assistant/transformer/feature_transformers/caafe.py
index e7638ef..587a955 100644
--- a/src/autogluon/assistant/transformer/feature_transformers/caafe.py
+++ b/src/autogluon/assistant/transformer/feature_transformers/caafe.py
@@ -29,8 +29,7 @@ def __init__(
         num_iterations: int = 2,
         optimization_metric: str = "roc",
         eval_model: str = "lightgbm",
-        # TODO: Remove hardcoding AWS region
-        region_name: str = "us-west-2",
+        region_name: str = os.environ.get("AWS_DEFAULT_REGION", "us-west-2"),
         **kwargs,
     ) -> None:
         # Set up credentials if using OpenAI