diff --git a/docs/source/reference/ml.rst b/docs/source/reference/ml.rst
index ba63277..bcb44bd 100644
--- a/docs/source/reference/ml.rst
+++ b/docs/source/reference/ml.rst
@@ -5,6 +5,18 @@ Machine Learning
 ================
 .. currentmodule:: eland.ml
 
+Machine learning is built into the Elastic Stack and enables users to gain insights into their Elasticsearch data. 
+There are a wide range of capabilities from identifying in
+anomalies in your data, to training and deploying regression or classification models based on Elasticsearch data.
+
+To use the Elastic Stack machine learning features, you must have the appropriate license and at least one machine 
+learning node in your Elasticsearch cluster. If Elastic Stack security features are enabled, you must also ensure 
+your users have the necessary privileges.
+
+The fastest way to get started with machine learning features is to start a free 14-day trial of Elasticsearch Service in the cloud.
+
+See https://www.elastic.co/guide/en/machine-learning/current/setup.html and other documentation for more detail.
+
 ExternalMLModel
 ~~~~~~~~~~~~~~~
 .. currentmodule:: eland.ml
diff --git a/eland/ml/external_ml_model.py b/eland/ml/external_ml_model.py
index 286dd7c..b30a459 100644
--- a/eland/ml/external_ml_model.py
+++ b/eland/ml/external_ml_model.py
@@ -30,8 +30,8 @@ from xgboost import XGBRegressor, XGBClassifier
 
 class ExternalMLModel(MLModel):
     """
-    Put a trained inference model in Elasticsearch based on an external model.
-    An external model that is transformed and added to Elasticsearch.
+    Transform and serialize a trained 3rd party model into Elasticsearch.
+    This model can then be used for inference in the Elastic Stack.
 
     Parameters
     ----------
@@ -152,9 +152,9 @@ class ExternalMLModel(MLModel):
 
     def predict(self, X):
         """
-        Make a prediction using a trained inference model in Elasticsearch.
+        Make a prediction using a trained model stored in Elasticsearch.
 
-        Parameters for this method are not fully compatible with standard sklearn.predict.
+        Parameters for this method are not yet fully compatible with standard sklearn.predict.
 
         Parameters
         ----------