diff --git a/docs/faq.md b/docs/faq.md
index dce4324..f415815 100644
--- a/docs/faq.md
+++ b/docs/faq.md
@@ -31,10 +31,10 @@ CodeRabbit works with all programming languages, with varying proficiency based
 
 <Tabs>
   <TabItem value="storage" label="Code Storage" default>
-    - No persistent code storage
-    - Temporary cloning during review only
     - Complete data isolation
-    - Immediate disposal post-review
+    - Caching of encrypted code and dependency archives for faster reviews
+    - Code indexing in which we store vector representations of code for efficient code base context
+    - Both caching and code indexing can be disabled which means we store nothing post-review
   </TabItem>
   <TabItem value="training" label="Training Data">
     - Uses only public datasets
diff --git a/docs/overview/introduction.md b/docs/overview/introduction.md
index e215f57..ed73a15 100644
--- a/docs/overview/introduction.md
+++ b/docs/overview/introduction.md
@@ -81,7 +81,6 @@ For more information, see [Issue Creation](/guides/issue-creation) and [Issue Ch
 CodeRabbit collects only the minimum amount of information needed to provide you with our code review services. Our privacy and security posture centers around protecting your data through ephemerality:
 
 - All queries to large language models (LLMs) exist in-memory only, with zero retention after each query completes.
-- We don't store a copy of your code.
 - We don't use your code, code reviews, or other collected data to train LLMs.
 - CodeRabbit doesn't share any collected customer data with third parties.
 - We keep all customer data confidential, and isolated by organization.