export/analysis section

Author: ethanpalm

guides/assistant.mdx

@@ -61,22 +61,25 @@ Structure your documentation to help the assistant provide accurate, relevant an
 - Cross-reference related topics.
 - Add [hidden pages](/guides/hidden-pages) with additional context that users don't need, but the assistant can reference.
 
-## Exporting queries
+## Exporting and analyzing queries
 
-You can review and export queries from your dashboard. Some ways that analyzing queries can help you improve your documentation:
+Review and export queries from your dashboard to understand how people interact with your documentation and identify improvement opportunities. Some ways that analyzing queries can help you improve your documentation:
 
-- Identify content gaps for any queries that are frequent, but have insufficient responses or sources.
-- Conduct lightweight user research by looking for themes and patterns in queries.
-- See which pages are used as sources and prioritize them for accuracy and quality.
+- Identify content gaps where frequent queries receive insufficient answers.
+- Discover user behavior patterns and common information needs from themes and patterns in queries.
+- Prioritize high-traffic pages for accuracy and quality improvements.
 
 You can explore queries from your [dashboard](https://dashboard.mintlify.com/products/assistant), but to get more powerful insights we recommend exporting a `CSV` file of your queries, responses, and sources to analyze with your preferred AI tool.
 
 1. Navigate to the [assistant page](https://dashboard.mintlify.com/products/assistant) in your dashboard.
 2. Select **Export to CSV**.
-3. Upload the queries into your AI tool and ask questions to learn about how your users are engaging with your docs. Some prompts to get you started:
+3. Analyze the exported data using your preferred tool.
+
+Sample analysis prompts:
 
 - Summarize the most common themes of the queries.
 - List any queries that had no sources cited.
+- Find patterns in unsuccessful interactions.
 
 ## Changing the model