DOCSP-43493 adding ai and data usage

Author: ltran-mdb2

source/ai-data-usage.txt

@@ -0,0 +1,41 @@
+.. vscode-ai-data-usage:
+
+=============================
+AI and Data Usage Information
+=============================
+
+.. contents:: On this page
+   :local:
+   :backlinks: none
+   :depth: 1
+
+The MongoDB Github Copilot Participant is powered by Generative AI (Gen
+AI), and may give inaccurate responses. See our `Generative AI FAQ
+<https://dochub.mongodb.org/core/faq-ai-features>`__ for more
+information about Gen AI in MongoDB products.
+
+Third Party Providers
+---------------------
+
+The MongoDB Github Copilot Participant is powered by Github Copilot.
+This is subject to change in the future. 
+
+How Your Data is Used
+---------------------
+
+When you use the MongoDB Github Copilot Participant, the following
+information is sent to MongoDB's backend and/or the third party AI
+provider: 
+
+- The full text of your natural language prompt.
+- The schema of the collection you are using, 
+  including database name, collection name, field names, and types. 
+- Enable sending sample field values. This is an optional setting to 
+  improve the quality of recommendations. You can manage this through the
+  ``Enable sending sample field values`` setting in 
+  :ref:`Compass settings <compass-settings-reference>`. This setting 
+  is off by default.
+
+The information that is sent will not be shared with any other third 
+parties or stored by the AI provider. We do not send database 
+connection strings, credentials, or rows/documents from your databases. 

source/copilot.txt

@@ -13,7 +13,7 @@ MongoDB Github Copilot Participant
    :class: singlecol
 
 
-|vsce-full| automatically includes a MongoDB Github Copilot Participant
+|vsce-full| includes a MongoDB Github Copilot Participant
 to assist in using Copilot with your MongoDB deployments. Through
 Copilot's chat feature, users with |vsce| can interact their MongoDB
 clusters and generate code with MongoDB domain-specific knowledge on top
@@ -22,15 +22,18 @@ of VSCode Copilot's LLM.
 /query
 ------
 
-Users can use the ``/query`` command to generate queries from a natural
-language against a connected MongoDB cluster. The MongoDB Participant
-provides underlying schema information of the relevant collections and
-MongoDB domain specific knowledge to Copilot to generate a response.
+Users can use the ``/query`` command in the Copilot chat to
+generate queries from a natural language against a connected MongoDB
+cluster. The MongoDB Participant provides underlying schema information
+of the relevant collections to Copilot to generate a response. If you do
+not specify a collection in your prompt to Copilot, the MongoDB
+Participant prompts you to select a relevant collection. 
+
 When the LLM generates a query, users can open the query in a playground
 file or run the query directly in their collection. 
 
-/query Example
-~~~~~~~~~~~~~~
+Example
+~~~~~~~
 
 Consider a ``fruits`` collection that contains documents with the
 following structure:
@@ -44,10 +47,9 @@ following structure:
       type: "citrus"
    }
 
-   
-In the Github Copilot Chat tab, you can ask the MongoDB Copilot
-participant to generate a query to find all documents in the ``fruits``
-collection that have the type ``citrus``. 
+Once you connet to the databse that contains the ``fruits`` collection,
+you can ask the Copilot chat to generate a query that finds all documents
+in the ``fruits`` collection that have the type ``citrus``. 
 
 .. code-block:: javascript
    :copyable: false
@@ -60,11 +62,12 @@ the following query using knowledge of your database schema:
 
 .. code-block:: javascript
 
-   use('fruits');
-   db.getCollection('fruits').find({ type: 'citrus' });
-
+   db.getCollection('fruits').find({ type: 'citrus' })
 
 
+.. toctree::
+   :titlesonly:
 
+   /ai-data-usage