diff --git a/nlp-sentiment-analysis/README.md b/nlp-sentiment-analysis/README.md
index 114f7f2..b5e67cd 100644
--- a/nlp-sentiment-analysis/README.md
+++ b/nlp-sentiment-analysis/README.md
@@ -1,6 +1,6 @@
 [![banner](../banner.png)](https://cloud.google.com/?utm_source=github&utm_medium=referral&utm_campaign=GCP&utm_content=packages_repository_banner)
 
-# Perform Sentiment Analysis on your Text Data
+# Perform Sentiment Analysis on your Text Data using Google Cloud
 
 ## Introduction
 This architecture uses click-to-deploy to orchestrate a seamless sentiment analysis pipeline by leveraging Google Cloud's robust suite of services. It empowers users to glean valuable insights from text data through automated processes and intuitive visualizations.
diff --git a/nlp-sentiment-analysis/tutorial.md b/nlp-sentiment-analysis/tutorial.md
index 67dbbbc..e2e435e 100644
--- a/nlp-sentiment-analysis/tutorial.md
+++ b/nlp-sentiment-analysis/tutorial.md
@@ -1,4 +1,4 @@
-# Extract data from your documents using Generative AI on Google Cloud
+# Perform Sentiment Analysis on your Text Data using Google Cloud
 
 ## Let's get started
 
@@ -57,7 +57,7 @@ It happens because the Eventarc permissions take some time to propagate. First,
 
 ## Result
 
-At this point you should have successfully deployed the foundations for a Three Tier Web Application!.
+At this point you should have successfully deployed sentiment analysis for text in Google Cloud.
 
 This process may take a while to deploy, please do not close the window when deploying.
 
@@ -67,10 +67,10 @@ Next we are going to test the architecture and finally clean up your environment
 Once you deployed the solution successfully, upload the form.pdf to the input bucket using either Cloud Console or gsutil.
 
 ```bash
-gsutil cp assets/form.pdf gs://<YOUR PROJECT NAME>-doc-ai-form-input
+gsutil cp assets/form.pdf gs://<YOUR PROJECT NAME>-sentiment-analysis_input
 ```
 
-Then, check the parsed results in the output bucket in text (OCR) and json (Key=value) formats
+Then, check the parsed results in the output bucket in json (Key=value) format.
 
 Finally, check the json results on BigQuery