address Copilot feedback

Author: adamsitnik

docs/ai/conceptual/data-ingestion.md

@@ -5,6 +5,7 @@ author: luisquintanilla
 ms.author: luquinta
 ms.date: 11/11/2025
 ms.topic: concept-article
+ai-usage: ai-assisted
 ---
 
 # Data Ingestion
@@ -63,7 +64,7 @@ The [Microsoft.Extensions.DataIngestion](https://www.nuget.org/packages/Microsof
 
 At the foundation of the library is the `IngestionDocument` type, which provides a unified way to represent any file format without losing important information. The `IngestionDocument` is Markdown-centric because large language models work best with Markdown formatting.
 
-The `IngestionDocumentReader` abstraction handles loading documents from various sources, whether local files or streams. There are few readers available:
+The `IngestionDocumentReader` abstraction handles loading documents from various sources, whether local files or streams. A few readers are available:
 
 - **[MarkItDown](https://www.nuget.org/packages/Microsoft.Extensions.DataIngestion.MarkItDown)**
 - **[Markdown](https://www.nuget.org/packages/Microsoft.Extensions.DataIngestion.Markdig/)**
@@ -137,10 +138,10 @@ using VectorStoreWriter<string> writer = new(vectorStore, dimensionCount: 1536);
 
 The `IngestionPipeline<T>` API allows you to chain together the various data ingestion components into a complete workflow. You can combine:
 
-- **Readers** to load documents from various sources
-- **Processors** to transform and enrich document content  
-- **Chunkers** to break documents into manageable pieces
-- **Writers** to store the final results in your chosen data store
+- **Readers** to load documents from various sources.
+- **Processors** to transform and enrich document content.
+- **Chunkers** to break documents into manageable pieces.
+- **Writers** to store the final results in your chosen data store.
 
 This pipeline approach reduces boilerplate code and makes it easy to build, test, and maintain complex data ingestion workflows.