@@ -20,7 +20,7 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-Use an *indexed Azure SQL knowledge source* (preview) to ingest rows from Azure SQL Database or Azure SQL Managed Instance into an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+An *indexed Azure SQL knowledge source* (preview) ingests rows from Azure SQL Database or Azure SQL Managed Instance into an agentic retrieval pipeline in Azure AI Search. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
 Unlike file-based knowledge sources, such as Azure Blob Storage and OneLake, each SQL row is treated as one logical document. The index schema is customer driven through explicit column mappings rather than a fixed document schema.
 
@@ -41,7 +41,7 @@ The generated indexer conforms to the *Azure SQL indexer*, whose prerequisites,
 
 ## Prerequisites
 
-+ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md).
++ An Azure AI Search service in any [region that provides agentic retrieval](search-region-support.md).
 
 + Completion of the [Azure SQL indexer prerequisites](search-how-to-index-sql-database.md#prerequisites), including:
 
@@ -83,6 +83,28 @@ The generated indexer conforms to the *Azure SQL indexer*, whose prerequisites,
 + Real-time synchronization isn't supported. The generated indexer is schedule based.
 + Real-time SQL retrieval isn't supported. The knowledge source is indexed, not remote.
 
+## Prepare the generated indexer
+
+An indexed Azure SQL knowledge source automatically creates an indexer to drive ingestion. Review the following details before you create the knowledge source.
+
+### Change detection
+
+The generated indexer uses standard [Azure SQL indexer change detection](search-how-to-index-sql-database.md#indexing-new-changed-and-deleted-rows):
+
++ **Tables:** The service applies [SQL integrated change tracking](search-how-to-index-sql-database.md#sql-integrated-change-tracking-policy) automatically. Enable [SQL change tracking](/sql/relational-databases/track-changes/about-change-tracking-sql-server) on the source table before you create the knowledge source.
+
++ **Views:** The service applies [high-water-mark change detection](search-how-to-index-sql-database.md#high-water-mark-change-detection-policy). Specify the column to use in `highWaterMarkColumn`. A `rowversion` column is strongly recommended. To detect deletions in a view, include a soft-delete marker column in the view as described in [Soft delete column deletion detection policy](search-how-to-index-sql-database.md#soft-delete-column-deletion-detection-policy).
+
+### Authentication
+
+The generated indexer supports two authentication options:
+
++ **SQL authentication:** Provide a username and password in the connection string.
+
++ **Managed identity authentication:** Use a system-assigned or user-assigned managed identity that has Azure RBAC and database-level roles on the SQL resource.
+
+For connection string formats, role requirements, and setup steps, see the [Azure SQL indexer prerequisites](search-how-to-index-sql-database.md#prerequisites) and [Connect through a managed identity](search-how-to-managed-identities.md).
+
 ## Check for existing knowledge sources
 
 [!INCLUDE [Check for existing knowledge sources](includes/how-tos/knowledge-source-check.md)]
@@ -126,9 +148,6 @@ The following JSON is an example response for an indexed Azure SQL knowledge sou
 }
 ```
 
-> [!NOTE]
-> The generated resources appear at the end of the response under `createdResources`.
-
 ## Create a knowledge source
 
 Run the following code to create an indexed Azure SQL knowledge source.
@@ -306,62 +325,62 @@ Content-Type: application/json
 
 The following properties apply to indexed Azure SQL knowledge sources.
 
-| Property | Description | Required |
-|--|--|--|
-| `name` | The name of the knowledge source. The name must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | Yes |
-| `kind` | The kind of knowledge source, which is `indexedSql` in this case. | Yes |
-| `description` | A description of the knowledge source. | No |
-| `encryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | No |
-| `indexedSqlParameters` | Parameters specific to indexed Azure SQL knowledge sources, which are described in the following section. | Yes |
+| Property | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source. The name must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | Yes | Yes |
+| `kind` | The kind of knowledge source, which is `indexedSql` in this case. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `indexedSqlParameters` | Parameters specific to indexed Azure SQL knowledge sources, which are described in the following section. | Object | | Yes |
 
 ### `indexedSqlParameters` properties
 
 The following properties are specific to the `indexedSqlParameters` object of an indexed Azure SQL knowledge source.
 
-| Property | Description | Required |
-|--|--|--|
-| `connectionString` | A SQL authentication or managed-identity connection string for Azure SQL Database or Azure SQL Managed Instance. For supported credential formats, see the [Azure SQL indexer prerequisites](search-how-to-index-sql-database.md#prerequisites). | Yes |
-| `tableOrView` | The fully qualified name of the SQL table or view to ingest, specified in the `schema.objectName` format. A knowledge source ingests from exactly one table or one view. | Yes |
-| `highWaterMarkColumn` | Required when `tableOrView` refers to a view. The name of the column used for high-water-mark change detection. We strongly recommend a `rowversion` column. For more information, see [High water mark change detection policy](search-how-to-index-sql-database.md#high-water-mark-change-detection-policy). | Conditional |
-| `contentColumns` | An array of [column mappings](#column-mapping) that defines which SQL columns are treated as searchable text content in the generated index. Each mapping must use `Edm.String` as the `searchFieldType`. | No |
-| `embeddingColumns` | An array of [embedding mappings](#embedding-mapping) that defines which SQL columns are used to generate vector fields. | No |
-| `ingestionParameters` | A subset of the standard knowledge source [ingestion parameters](#ingestionparameters-properties). | No |
+| Property | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `connectionString` | A SQL authentication or managed-identity connection string for Azure SQL Database or Azure SQL Managed Instance. For supported credential formats, see the [Azure SQL indexer prerequisites](search-how-to-index-sql-database.md#prerequisites). | String | No | Yes |
+| `tableOrView` | The fully qualified name of the SQL table or view to ingest, specified in the `schema.objectName` format. A knowledge source ingests from exactly one table or one view. | String | No | Yes |
+| `highWaterMarkColumn` | Required when `tableOrView` refers to a view. The name of the column used for high-water-mark change detection. We strongly recommend a `rowversion` column. For more information, see [High water mark change detection policy](search-how-to-index-sql-database.md#high-water-mark-change-detection-policy). | String | No | Conditional |
+| `contentColumns` | An array of [column mappings](#column-mapping) that defines which SQL columns are treated as searchable text content in the generated index. Each mapping must use `Edm.String` as the `searchFieldType`. | Array | No | No |
+| `embeddingColumns` | An array of [embedding mappings](#embedding-mapping) that defines which SQL columns are used to generate vector fields. | Array | No | No |
+| `ingestionParameters` | A subset of the standard knowledge source [ingestion parameters](#ingestionparameters-properties). | Object | | No |
 
 ### Column mapping
 
 `contentColumns` uses the following column mapping shape.
 
-| Property | Description |
-|--|--|
-| `name` | The name of the field as it appears in the generated Azure AI Search index. |
-| `sourceField` | The SQL column whose value populates the target field. |
-| `searchFieldType` | The Azure AI Search field type for the generated field. For `contentColumns`, this must be `Edm.String`. |
+| Property | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the field as it appears in the generated Azure AI Search index. | String | No | Yes |
+| `sourceField` | The SQL column whose value populates the target field. | String | No | Yes |
+| `searchFieldType` | The Azure AI Search field type for the generated field. For `contentColumns`, this must be `Edm.String`. | String | No | Yes |
 
 ### Embedding mapping
 
 `embeddingColumns` uses the following embedding mapping shape.
 
-| Property | Description |
-|--|--|
-| `name` | The name of the target vector field that the service creates in the generated index. For example, it could be `descriptionVector`. |
-| `sourceField` | The SQL column whose text content is sent to the embedding model. |
+| Property | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the target vector field that the service creates in the generated index. For example, it could be `descriptionVector`. | String | No | Yes |
+| `sourceField` | The SQL column whose text content is sent to the embedding model. | String | No | Yes |
 
 ### `ingestionParameters` properties
 
 For indexed Azure SQL knowledge sources, the existing `ingestionParameters` schema is unchanged, but only the following properties apply.
 
-| Property | Description |
-|--|--|
-| `contentExtractionMode` | Must be `"minimal"`. Other modes aren't supported because Azure SQL ingestion is row based and doesn't extract content from binary documents. |
-| `embeddingModel` | An Azure OpenAI embedding model used to vectorize the columns listed in `embeddingColumns`. Required only when `embeddingColumns` is specified. |
-| `identity` | An optional user-assigned managed identity used to authenticate to Azure SQL and Azure OpenAI. |
-| `ingestionSchedule` | An optional schedule that controls how often the generated indexer runs. |
+| Property | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `contentExtractionMode` | Must be `"minimal"`. Other modes aren't supported because Azure SQL ingestion is row based and doesn't extract content from binary documents. | String | No | No |
+| `embeddingModel` | An Azure OpenAI embedding model used to vectorize the columns listed in `embeddingColumns`. Required only when `embeddingColumns` is specified. | Object | Only `apiKey` and `deploymentId` are editable | Conditional |
+| `identity` | An optional user-assigned managed identity used to authenticate to Azure SQL and Azure OpenAI. | Object | Yes | No |
+| `ingestionSchedule` | An optional schedule that controls how often the generated indexer runs. | Object | Yes | No |
 
 Image extraction and image verbalization aren't supported for indexed Azure SQL knowledge sources, so `chatCompletionModel`, `assetStore`, `aiServices`, and image-related settings have no effect.
 
 ### Defaulting and validation rules
 
-The following defaults apply when you create an indexed Azure SQL knowledge source:
+The following defaults apply when you create an indexed Azure SQL knowledge source.
 
 + If you omit `contentColumns`, the service automatically maps SQL columns that can be safely represented as text to `Edm.String` fields in the generated index, using a 1:1 mapping where `name` equals `sourceField`.
 
@@ -371,40 +390,29 @@ The following defaults apply when you create an indexed Azure SQL knowledge sour
 
 + The primary key of the source table or view is auto-discovered. Explicit overrides aren't supported, and the source must have a single-valued primary key.
 
-## Configure the generated indexer
-
-An indexed Azure SQL knowledge source automatically creates an indexer to drive ingestion. The following sections cover change detection and authentication options for the generated indexer.
-
-### Change detection
-
-The generated indexer uses standard [Azure SQL indexer change detection](search-how-to-index-sql-database.md#indexing-new-changed-and-deleted-rows):
+## Check ingestion status
 
-+ **Tables:** The service applies [SQL integrated change tracking](search-how-to-index-sql-database.md#sql-integrated-change-tracking-policy) automatically. Enable [SQL change tracking](/sql/relational-databases/track-changes/about-change-tracking-sql-server) on the source table before you create the knowledge source.
+[!INCLUDE [Check ingestion status](includes/how-tos/knowledge-source-status.md)]
 
-+ **Views:** The service applies [high-water-mark change detection](search-how-to-index-sql-database.md#high-water-mark-change-detection-policy). Specify the column to use in `highWaterMarkColumn`. A `rowversion` column is strongly recommended. To detect deletions in a view, include a soft-delete marker column in the view as described in [Soft delete column deletion detection policy](search-how-to-index-sql-database.md#soft-delete-column-deletion-detection-policy).
+## Review the generated objects
 
-### Authentication
-
-The generated indexer supports two authentication options:
-
-+ **SQL authentication:** Provide a username and password in the connection string.
-
-+ **Managed identity authentication:** Use a system-assigned or user-assigned managed identity that has Azure RBAC and database-level roles on the SQL resource.
-
-For connection string formats, role requirements, and setup steps, see the [Azure SQL indexer prerequisites](search-how-to-index-sql-database.md#prerequisites) and [Connect through a managed identity](search-how-to-managed-identities.md).
+[!INCLUDE [Review the generated objects](includes/how-tos/knowledge-source-review-objects.md)]
 
 ## Assign to a knowledge base
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+
+## Query a knowledge base
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
 
 ## Delete a knowledge source
 
 [!INCLUDE [Delete a knowledge source](includes/how-tos/knowledge-source-delete.md)]
 
 ## Related content
 
++ [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
 + [What is a knowledge source?](agentic-knowledge-source-overview.md)
 + [Create a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md)
 + [Query a knowledge base](agentic-retrieval-how-to-retrieve.md)

@@ -1,14 +1,14 @@
 ---
 title: Create a Blob Knowledge Source for Agentic Retrieval
-description: A blob knowledge source specifies a blob container that you want to read from. It also includes models and properties for creating an indexer, data source, skillset, and index used for agentic retrieval workloads.
+description: Learn how to create a blob knowledge source in Azure AI Search that ingests content from Azure Blob Storage or ADLS Gen2 for agentic retrieval.
 ms.service: azure-ai-search
 ms.topic: how-to
 ms.date: 06/02/2026
 ai-usage: ai-assisted
 zone_pivot_groups: search-csharp-python-rest
 ---
 
-# Create a blob knowledge source from Azure Blob Storage and ADLS Gen2
+# Create a blob knowledge source from Azure Blob Storage or ADLS Gen2
 
 [!INCLUDE [GA feature](./includes/previews/agentic-retrieval-ga-feature.md)]
 
@@ -23,7 +23,7 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-Use a *blob knowledge source* to index and query Azure blob content in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+A *blob knowledge source* ingests Azure Blob Storage or ADLS Gen2 content into an agentic retrieval pipeline in Azure AI Search. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
 When you create a blob knowledge source, you specify an external data source, models, and properties to automatically generate the following Azure AI Search objects:
 
@@ -43,7 +43,7 @@ When you create a blob knowledge source, you specify an external data source, mo
 
 ## Prerequisites
 
-+ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md).
++ An Azure AI Search service in any [region that provides agentic retrieval](search-region-support.md).
 
 + An [Azure Blob Storage](/azure/storage/common/storage-account-create) or [Azure Data Lake Storage (ADLS) Gen2](/azure/storage/blobs/create-data-lake-storage-account) account.
 
@@ -492,7 +492,7 @@ Content-Type: application/json
 
 ### Source-specific properties
 
-For both the 2026-05-01-preview and 2026-04-01 API versions, you can pass the following properties to create a blob knowledge source.
+The following properties apply to blob knowledge sources.
 
 ::: zone pivot="csharp"
 
@@ -556,29 +556,25 @@ For both the 2026-05-01-preview and 2026-04-01 API versions, you can pass the fo
 
 [!INCLUDE [Check ingestion status](includes/how-tos/knowledge-source-status.md)]
 
-## Review the created objects
+## Review the generated objects
 
-When you create a blob knowledge source, your search service also creates an indexer, index, skillset, and data source. We don't recommend that you edit these objects, as introducing an error or incompatibility can break the pipeline.
+[!INCLUDE [Review the generated objects](includes/how-tos/knowledge-source-review-objects.md)]
 
-After you create a knowledge source, the response lists the created objects. These objects are created according to a fixed template, and their names are based on the name of the knowledge source. You can't change the object names.
+## Assign to a knowledge base
 
-We recommend using the Azure portal to validate output creation. The workflow is:
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
-1. Check the indexer for success or failure messages. Connection or quota errors appear here.
-1. Check the index for searchable content. Use Search Explorer to run queries.
-1. Check the skillset to learn how your content is chunked and optionally vectorized.
-1. Check the data source for connection details. Our example uses API keys for simplicity, but you can use Microsoft Entra ID for authentication and role-based access control for authorization.
+## Query a knowledge base
 
-## Assign to a knowledge base
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query the knowledge source. This knowledge source supports optional configurations for document-level permissions enforcement and document-embedded image surfacing.
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+### Enforce document-level permissions
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+To enforce document-level permissions, set `ingestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time (preview)](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time-preview).
 
-> [!TIP]
-> + To enforce document-level permissions, set `ingestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time-preview).
->
-> + To surface document-embedded images (such as diagrams or scans) in answer synthesis responses, configure `assetStore` on this knowledge source and enable image serving on the knowledge base. For more information, see [Surface document-embedded images in agentic retrieval (preview)](agentic-retrieval-how-to-image-serving.md).
+### Surface document-embedded images
+
+To surface document-embedded images (such as diagrams or scans) in answer synthesis responses, configure `assetStore` on this knowledge source, and then enable image serving on the knowledge base. For more information, see [Surface document-embedded images in agentic retrieval (preview)](agentic-retrieval-how-to-image-serving.md).
 
 ## Delete a knowledge source
 
@@ -587,6 +583,7 @@ After the knowledge base is configured, use the [retrieve action](agentic-retrie
 ## Related content
 
 + [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
-+ [Azure AI Search blob knowledge source Python sample](https://github.com/Azure/azure-search-vector-samples/blob/main/demo-python/code/knowledge/blob-knowledge-source.ipynb)
-+ [Agentic RAG: Build a reasoning retrieval engine with Azure AI Search (YouTube video)](https://www.youtube.com/watch?v=PeTmOidqHM8)
-+ [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)
++ [What is a knowledge source?](agentic-knowledge-source-overview.md)
++ [Create a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md)
++ [Query a knowledge base](agentic-retrieval-how-to-retrieve.md)
++ [Blob knowledge source Python sample](https://github.com/Azure/azure-search-vector-samples/blob/main/demo-python/code/knowledge/blob-knowledge-source.ipynb)

@@ -19,7 +19,9 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-A *Fabric Data Agent knowledge source* (preview) connects your [Microsoft Fabric Data Agent](/fabric/data-science/concept-data-agent) to an agentic retrieval pipeline in Azure AI Search. The data agent acts as a virtual analyst, generating and running queries against your live Microsoft Fabric data to return natural-language answers, tables, and charts as grounding data.
+A *Fabric Data Agent knowledge source* (preview) connects your [Microsoft Fabric Data Agent](/fabric/data-science/concept-data-agent) to an agentic retrieval pipeline in Azure AI Search. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
+
+The data agent acts as a virtual analyst, generating and running queries against your Microsoft Fabric data to return natural-language answers, tables, and charts. This makes Fabric Data Agent knowledge sources useful for high-churn data and analytical queries.
 
 Unlike indexed knowledge sources, Fabric Data Agent knowledge sources query live data directly at retrieval time. No ingestion pipeline is needed. Queries require an end-user access token, which the retrieval engine uses to query the Fabric Data Agent on behalf of the end user.
 
@@ -74,7 +76,7 @@ Fabric IQ inherits Microsoft Fabric's compliance certifications for the workspac
 
 ## Check for existing knowledge sources
 
-[!INCLUDE [](./includes/how-tos/knowledge-source-check.md)]
+[!INCLUDE [Check for existing knowledge sources](includes/how-tos/knowledge-source-check.md)]
 
 The following JSON is an example response for a Fabric Data Agent knowledge source.
 
@@ -190,14 +192,14 @@ The following properties apply to Fabric Data Agent knowledge sources.
 
 ## Assign to a knowledge base
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
 > [!IMPORTANT]
 > Fabric Data Agent knowledge sources don't support the `minimal` [retrieval reasoning effort](agentic-retrieval-how-to-set-retrieval-reasoning-effort.md). Use `low` or `medium` instead.
 
 ## Query a knowledge base
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query Fabric Data Agent content. This knowledge source has unique query-time permissions enforcement and response characteristics.
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query Fabric Data Agent content. This knowledge source has unique query-time permissions enforcement and response characteristics.
 
 ### Enforce permissions at query time
 
@@ -267,7 +269,7 @@ The following example shows a retrieve response containing a Fabric Data Agent k
 
 ## Delete a knowledge source
 
-[!INCLUDE [](./includes/how-tos/knowledge-source-delete.md)]
+[!INCLUDE [Delete a knowledge source](includes/how-tos/knowledge-source-delete.md)]
 
 ## Related content
 

@@ -19,9 +19,11 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-A *Fabric Ontology knowledge source* (preview) connects your [Microsoft Fabric ontology](/fabric/iq/ontology/overview) to an agentic retrieval pipeline in Azure AI Search, providing ontology-defined entities, relationships, and content as grounding data. Because ontologies capture how your business defines its data, agents can answer in business terms rather than reasoning over raw tables and columns.
+A *Fabric Ontology knowledge source* (preview) connects your [Microsoft Fabric ontology](/fabric/iq/ontology/overview) to an agentic retrieval pipeline in Azure AI Search. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
-Unlike indexed knowledge sources, Fabric Ontology knowledge sources query live data directly. No ingestion pipeline is needed. Queries require an end-user access token, which the retrieval engine uses to authenticate with Microsoft Fabric on the caller's behalf.
+Ontologies capture how your business defines its data, entities, and relationships, allowing agents to answer in business terms rather than reasoning over raw tables and columns.
+
+Unlike indexed knowledge sources, Fabric Ontology knowledge sources query live data directly at retrieval time. No ingestion pipeline is needed. Queries require an end-user access token, which the retrieval engine uses to authenticate with Microsoft Fabric on the caller's behalf.
 
 ### Usage support
 
@@ -74,7 +76,7 @@ Fabric IQ inherits Microsoft Fabric's compliance certifications for the workspac
 
 ## Check for existing knowledge sources
 
-[!INCLUDE [](./includes/how-tos/knowledge-source-check.md)]
+[!INCLUDE [Check for existing knowledge sources](includes/how-tos/knowledge-source-check.md)]
 
 The following JSON is an example response for a Fabric Ontology knowledge source.
 
@@ -190,14 +192,14 @@ The following properties apply to Fabric Ontology knowledge sources.
 
 ## Assign to a knowledge base
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
 > [!NOTE]
 > Fabric Ontology knowledge sources don't support the `minimal` [retrieval reasoning effort](agentic-retrieval-how-to-set-retrieval-reasoning-effort.md). Use `low` or `medium` instead.
 
 ## Query a knowledge base
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query Fabric Ontology content. This knowledge source has unique query-time permissions enforcement and response characteristics.
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query Fabric Ontology content. This knowledge source has unique query-time permissions enforcement and response characteristics.
 
 ### Enforce permissions at query time
 
@@ -261,7 +263,7 @@ The following example shows a retrieve response containing a Fabric Ontology kno
 
 ## Delete a knowledge source
 
-[!INCLUDE [](./includes/how-tos/knowledge-source-delete.md)]
+[!INCLUDE [Delete a knowledge source](includes/how-tos/knowledge-source-delete.md)]
 
 ## Related content
 

@@ -1,5 +1,5 @@
 ---
-title: Create File Knowledge Source for Agentic Retrieval
+title: Create a File Knowledge Source for Agentic Retrieval
 description: Learn how to create a file knowledge source in Azure AI Search, upload files directly, and use the processed content in a knowledge base.
 ms.service: azure-ai-search
 ms.topic: how-to
@@ -19,9 +19,11 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-Use a *file knowledge source* (preview) to upload small and medium file sets directly to Azure AI Search for agentic retrieval. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+A *file knowledge source* (preview) uploads small and medium file sets directly to Azure AI Search for agentic retrieval. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
-A file knowledge source is useful when you want a managed upload experience instead of provisioning Azure Storage, configuring access, and creating an indexer pipeline over an external container. Azure AI Search processes uploaded files so their extracted content can be retrieved from a knowledge base. Use [blob knowledge sources](agentic-knowledge-source-how-to-blob.md) instead when your content already lives in Azure Blob Storage or ADLS Gen2, when you need large-scale ingestion, or when you depend on storage-account capabilities.
+File knowledge sources are useful when you want a managed upload experience instead of provisioning Azure Storage, configuring access, and creating an indexer pipeline over an external container. Azure AI Search processes uploaded files so their extracted content can be retrieved from a knowledge base.
+
+If your content already lives in Azure Blob Storage or ADLS Gen2, or if you need large-scale ingestion or storage account capabilities, use a [blob knowledge source](agentic-knowledge-source-how-to-blob.md) instead.
 
 ### Usage support
 
@@ -57,6 +59,27 @@ A file knowledge source is useful when you want a managed upload experience inst
 
 ::: zone-end
 
+## Supported formats and limits
+
+The following file types are supported.
+
+| Category | Extensions |
+|--|--|
+| Text | `.txt`, `.md`, `.html`, `.json`, `.csv` |
+| Code | `.c`, `.cs`, `.cpp`, `.java`, `.py`, `.js`, `.ts`, `.php`, `.rb`, `.sh` |
+| Documents | `.pdf`, `.docx`, `.pptx`, `.doc` |
+
+The following limits apply to file knowledge sources.
+
+| Limit | Value |
+|--|--|
+| Maximum file size per upload | 50 MB |
+| Maximum files per file knowledge source | 100 |
+
+> [!NOTE]
+> Uploaded content is stored in the generated search index. For total storage limits by pricing tier, see [Service limits](search-limits-quotas-capacity.md#service-limits).
+
+
 ## Check for existing knowledge sources
 
 [!INCLUDE [Check for existing knowledge sources](includes/how-tos/knowledge-source-check.md)]
@@ -208,13 +231,13 @@ Prefer: return=representation
 }
 ```
 
-**Reference:** [Knowledge Sources - Create or Update](/rest/api/searchservice/knowledgesources/create-or-update?view=rest-searchservice-2026-05-01-preview&preserve-view=true)
+**Reference:** [Knowledge Sources - Create or Update](/rest/api/searchservice/knowledge-sources/create-or-update?view=rest-searchservice-2026-05-01-preview&preserve-view=true)
 
 ::: zone-end
 
 ### Source-specific properties
 
-You can pass the following properties to create a file knowledge source.
+The following properties apply to file knowledge sources.
 
 ::: zone pivot="csharp"
 
@@ -252,7 +275,7 @@ You can pass the following properties to create a file knowledge source.
 
 ### Ingestion parameters properties
 
-You can pass the following ingestion parameter properties to control how uploaded files are processed.
+The following ingestion parameter properties control how uploaded files are processed.
 
 ::: zone pivot="csharp"
 
@@ -283,9 +306,9 @@ You can pass the following ingestion parameter properties to control how uploade
 
 ## Upload files
 
-After the source exists, upload files directly to it. Each upload is a synchronous call: Azure AI Search extracts content from the uploaded file, chunks the content, creates embeddings when needed, and prepares the extracted content for retrieval before the call returns. You don't have to configure or run a separate ingestion pipeline.
+After the knowledge source exists, upload files directly to it. Each upload is a synchronous call: Azure AI Search extracts content from the uploaded file, chunks the content, creates embeddings when needed, and prepares the extracted content for retrieval before the call returns. You don't have to configure or run a separate ingestion pipeline.
 
-The request body contains the file content. The listed `fileName` is taken from the `Content-Disposition: attachment; filename="..."` header on the upload request; if the header isn't set, the service assigns an auto-generated `fileName`. SDKs can set the header through the upload method parameters shown in the following examples.
+The request body contains the file content. The listed `fileName` is taken from the `Content-Disposition: attachment; filename="..."` header on the upload request. If the header isn't set, the service assigns an auto-generated `fileName`. SDKs can set the header through the upload method parameters shown in the following examples.
 
 ::: zone pivot="csharp"
 
@@ -345,7 +368,9 @@ Content-Disposition: attachment; filename="installation-guide.pdf"
 ::: zone-end
 
 > [!NOTE]
-> Uploading a file doesn't replace an existing file even if you reuse the same `fileName`. Each upload creates a new file with its own `fileId`, and the list of uploaded files can contain multiple entries that share a `fileName`. To replace content, delete the prior file by `fileId` before or after the new upload.
+> Uploading a file doesn't replace an existing file, even if you reuse the same `fileName`. Each upload creates a new file with its own `fileId`, so the list of uploaded files can contain multiple entries that share a `fileName`.
+>
+> To replace content, delete the prior file by `fileId` before or after the new upload.
 
 ## List uploaded files
 
@@ -449,296 +474,21 @@ api-key: {{api-key}}
 
 ::: zone-end
 
-## Create a knowledge base
-
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
-
-::: zone pivot="csharp"
-
-```csharp
-using Azure;
-using Azure.Search.Documents.Indexes;
-using Azure.Search.Documents.Indexes.Models;
-using Azure.Search.Documents.KnowledgeBases.Models;
-
-var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new AzureKeyCredential(apiKey));
-
-var knowledgeBase = new KnowledgeBase(
-    name: "my-file-kb",
-    knowledgeSources: new[] { new KnowledgeSourceReference("my-file-ks") }
-)
-{
-    Description = "A knowledge base for uploaded product manuals.",
-    OutputMode = KnowledgeRetrievalOutputMode.ExtractiveData,
-    RetrievalReasoningEffort = new KnowledgeRetrievalMinimalReasoningEffort()
-};
-
-await indexClient.CreateOrUpdateKnowledgeBaseAsync(knowledgeBase);
-Console.WriteLine($"Knowledge base '{knowledgeBase.Name}' created or updated successfully.");
-```
-
-**Reference:** [KnowledgeBase](/dotnet/api/azure.search.documents.indexes.models.knowledgebase?view=azure-dotnet-preview&preserve-view=true)
-
-::: zone-end
-
-::: zone pivot="python"
-
-```python
-from azure.core.credentials import AzureKeyCredential
-from azure.search.documents.indexes import SearchIndexClient
-from azure.search.documents.indexes.models import (
-    KnowledgeBase,
-    KnowledgeRetrievalOutputMode,
-    KnowledgeSourceReference,
-)
-from azure.search.documents.knowledgebases.models import KnowledgeRetrievalMinimalReasoningEffort
-
-index_client = SearchIndexClient(endpoint="search_url", credential=AzureKeyCredential("api_key"))
-
-knowledge_base = KnowledgeBase(
-    name="my-file-kb",
-    description="A knowledge base for uploaded product manuals.",
-    knowledge_sources=[KnowledgeSourceReference(name="my-file-ks")],
-    output_mode=KnowledgeRetrievalOutputMode.EXTRACTIVE_DATA,
-    retrieval_reasoning_effort=KnowledgeRetrievalMinimalReasoningEffort(),
-)
-
-index_client.create_or_update_knowledge_base(knowledge_base=knowledge_base)
-print(f"Knowledge base '{knowledge_base.name}' created or updated successfully.")
-```
-
-**Reference:** [KnowledgeBase](/python/api/azure-search-documents/azure.search.documents.indexes.models.knowledgebase)
-
-::: zone-end
-
-::: zone pivot="rest"
+## Assign to a knowledge base
 
-```http
-PUT {{search-url}}/knowledgebases/my-file-kb?api-version=2026-05-01-preview
-api-key: {{api-key}}
-Content-Type: application/json
-Prefer: return=representation
-
-{
-  "name": "my-file-kb",
-  "description": "A knowledge base for uploaded product manuals.",
-  "outputMode": "extractiveData",
-  "retrievalReasoningEffort": {
-    "kind": "minimal"
-  },
-  "knowledgeSources": [
-    {
-      "name": "my-file-ks"
-    }
-  ]
-}
-```
-
-::: zone-end
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
 ## Query a knowledge base
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
-
-The simplest retrieve call sends an intent and lets the knowledge base apply its configured defaults for each attached knowledge source.
-
-::: zone pivot="csharp"
-
-```csharp
-using Azure;
-using Azure.Search.Documents.KnowledgeBases;
-using Azure.Search.Documents.KnowledgeBases.Models;
-
-var kbClient = new KnowledgeBaseRetrievalClient(
-    new Uri(searchEndpoint),
-    "my-file-kb",
-    new AzureKeyCredential(apiKey));
-
-var request = new KnowledgeBaseRetrievalRequest
-{
-    IncludeActivity = true
-};
-request.Intents.Add(new KnowledgeRetrievalSemanticIntent(
-    "What does the installation guide say about network prerequisites?"));
-
-var result = await kbClient.RetrieveAsync(request);
-```
-
-**Reference:** [KnowledgeBaseRetrievalClient](/dotnet/api/azure.search.documents.knowledgebases.knowledgebaseretrievalclient?view=azure-dotnet-preview&preserve-view=true)
-
-::: zone-end
-
-::: zone pivot="python"
-
-```python
-from azure.core.credentials import AzureKeyCredential
-from azure.search.documents.knowledgebases import KnowledgeBaseRetrievalClient
-from azure.search.documents.knowledgebases.models import (
-    KnowledgeBaseRetrievalRequest,
-    KnowledgeRetrievalSemanticIntent,
-)
-
-kb_client = KnowledgeBaseRetrievalClient(
-    endpoint="search_url",
-    knowledge_base_name="my-file-kb",
-    credential=AzureKeyCredential("api_key"),
-)
-
-request = KnowledgeBaseRetrievalRequest(
-    intents=[
-        KnowledgeRetrievalSemanticIntent(
-            search="What does the installation guide say about network prerequisites?"
-        )
-    ],
-    include_activity=True,
-)
-
-result = kb_client.retrieve(request)
-```
-
-**Reference:** [KnowledgeBaseRetrievalClient](/python/api/azure-search-documents/azure.search.documents.knowledgebases.knowledgebaseretrievalclient)
-
-::: zone-end
-
-::: zone pivot="rest"
-
-```http
-POST {{search-url}}/knowledgebases/my-file-kb/retrieve?api-version=2026-05-01-preview
-api-key: {{api-key}}
-Content-Type: application/json
-Accept: application/json
-
-{
-  "includeActivity": true,
-  "intents": [
-    {
-      "type": "semantic",
-      "search": "What does the installation guide say about network prerequisites?"
-    }
-  ],
-  "knowledgeSourceParams": [
-    {
-      "kind": "file",
-      "knowledgeSourceName": "my-file-ks",
-      "includeReferences": true,
-      "includeReferenceSourceData": true
-    }
-  ]
-}
-```
-
-::: zone-end
-
-## Supported formats and limits
-
-The following file types are supported in this preview.
-
-| Category | Extensions |
-|--|--|
-| Text | `.txt`, `.md`, `.html`, `.json`, `.csv` |
-| Code | `.c`, `.cs`, `.cpp`, `.java`, `.py`, `.js`, `.ts`, `.php`, `.rb`, `.sh` |
-| Documents | `.pdf`, `.docx`, `.pptx`, `.doc` |
-
-The file knowledge source preview has the following limits.
-
-| Limit | Value |
-|--|--|
-| Maximum file size per upload | 50 MB |
-| Maximum files per file knowledge source | 100 |
-
-> [!NOTE]
-> Uploaded content is stored in the generated search index. For total storage limits by SKU, see [Service limits](search-limits-quotas-capacity.md#service-limits).
-
-File knowledge sources are designed for direct upload scenarios, not large-scale scheduled crawling. If you need recurring ingestion from durable external storage, use a [blob knowledge source](agentic-knowledge-source-how-to-blob.md) instead.
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
 
 ## Delete a knowledge source
 
-Before you can delete a knowledge source, you must delete any knowledge base that references it or update the knowledge base definition to remove the reference. If you try to delete a knowledge source that's in use, the action fails and returns a list of affected knowledge bases.
-
-::: zone pivot="csharp"
-
-```csharp
-using Azure;
-using Azure.Search.Documents.Indexes;
-
-var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new AzureKeyCredential(apiKey));
-
-// List knowledge bases on the service.
-await foreach (var kb in indexClient.GetKnowledgeBasesAsync())
-{
-    Console.WriteLine(kb.Name);
-}
-
-// Delete the knowledge base that references the file knowledge source.
-await indexClient.DeleteKnowledgeBaseAsync("my-file-kb");
-
-// Delete the file knowledge source.
-await indexClient.DeleteKnowledgeSourceAsync("my-file-ks");
-```
-
-::: zone-end
-
-::: zone pivot="python"
-
-```python
-from azure.core.credentials import AzureKeyCredential
-from azure.search.documents.indexes import SearchIndexClient
-
-index_client = SearchIndexClient(endpoint="search_url", credential=AzureKeyCredential("api_key"))
-
-# List knowledge bases on the service.
-for kb in index_client.list_knowledge_bases():
-    print(kb.name)
-
-# Delete the knowledge base that references the file knowledge source.
-index_client.delete_knowledge_base("my-file-kb")
-
-# Delete the file knowledge source.
-index_client.delete_knowledge_source("my-file-ks")
-```
-
-::: zone-end
-
-::: zone pivot="rest"
-
-To delete a knowledge source:
-
-1. Get a list of all knowledge bases on your search service.
-
-    ```http
-    ### Get knowledge bases
-    GET {{search-url}}/knowledgebases?api-version=2026-05-01-preview&$select=name
-    api-key: {{api-key}}
-    ```
-
-1. Get an individual knowledge base definition to check for knowledge source references.
-
-    ```http
-    ### Get a knowledge base definition
-    GET {{search-url}}/knowledgebases/{{knowledge-base-name}}?api-version=2026-05-01-preview
-    api-key: {{api-key}}
-    ```
-
-1. Either delete the knowledge base or update the knowledge base by removing the knowledge source if you have multiple sources. This example shows deletion.
-
-    ```http
-    ### Delete a knowledge base
-    DELETE {{search-url}}/knowledgebases/{{knowledge-base-name}}?api-version=2026-05-01-preview
-    api-key: {{api-key}}
-    ```
-
-1. Delete the knowledge source.
-
-    ```http
-    ### Delete a knowledge source
-    DELETE {{search-url}}/knowledgesources/{{knowledge-source-name}}?api-version=2026-05-01-preview
-    api-key: {{api-key}}
-    ```
-
-::: zone-end
+[!INCLUDE [Delete a knowledge source](includes/how-tos/knowledge-source-delete.md)]
 
 ## Related content
 
 + [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
 + [What is a knowledge source?](agentic-knowledge-source-overview.md)
 + [Create a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md)
++ [Query a knowledge base](agentic-retrieval-how-to-retrieve.md)

@@ -21,9 +21,11 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-An *MCP Server knowledge source* (preview) connects your agentic retrieval pipeline to any external system that exposes a [Model Context Protocol](https://modelcontextprotocol.io/docs/getting-started/intro) (MCP)–compatible endpoint. Use this knowledge source to reach internal tools, third-party APIs, or custom backends that Azure AI Search doesn't natively support.
+An *MCP Server knowledge source* (preview) connects any system that exposes a [Model Context Protocol](https://modelcontextprotocol.io/docs/getting-started/intro) (MCP)–compatible endpoint to an agentic retrieval pipeline in Azure AI Search. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
-Unlike indexed knowledge sources, MCP Server knowledge sources query live data directly at retrieval time. No ingestion pipeline is needed. You provide the MCP server URL and specify which tools to allow, and Azure AI Search calls those tools on each query.
+MCP tools surface data and functionality from external systems as callable functions that agents invoke at query time. This makes MCP Server knowledge sources useful when the information you need lives in internal tools, third-party APIs, or custom backends that Azure AI Search doesn't natively support.
+
+Unlike indexed knowledge sources, MCP Server knowledge sources query live data directly at retrieval time. No ingestion pipeline is needed. You provide the MCP server URL and specify which tools Azure AI Search can call at query time.
 
 ### Usage support
 
@@ -67,7 +69,7 @@ Unlike indexed knowledge sources, MCP Server knowledge sources query live data d
 
 ## Check for existing knowledge sources
 
-[!INCLUDE [](./includes/how-tos/knowledge-source-check.md)]
+[!INCLUDE [Check for existing knowledge sources](includes/how-tos/knowledge-source-check.md)]
 
 The following JSON is an example response for an MCP Server knowledge source.
 
@@ -462,11 +464,11 @@ The `none` mode requires no configuration. The entire tool output is treated as
 
 ## Assign to a knowledge base
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
 ## Query a knowledge base
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query MCP server content. MCP Server knowledge sources have source-specific retrieval behavior and response fields.
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query MCP server content. MCP Server knowledge sources have source-specific retrieval behavior and response fields.
 
 ### How retrieval works for MCP Server knowledge sources
 
@@ -527,7 +529,7 @@ The following example shows a retrieve response containing an MCP Server knowled
 
 ## Delete a knowledge source
 
-[!INCLUDE [](./includes/how-tos/knowledge-source-delete.md)]
+[!INCLUDE [Delete a knowledge source](includes/how-tos/knowledge-source-delete.md)]
 
 ## Related content
 

@@ -25,7 +25,7 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-Use an *indexed OneLake knowledge source* to index and query Microsoft OneLake files in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+An *indexed OneLake knowledge source* ingests Microsoft OneLake files into an agentic retrieval pipeline in Azure AI Search. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
 When you create an indexed OneLake knowledge source, you specify an external data source, models, and properties to automatically generate the following Azure AI Search objects:
 
@@ -44,7 +44,7 @@ The generated indexer conforms to the *OneLake indexer*, whose prerequisites, su
 
 ## Prerequisites
 
-+ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md).
++ An Azure AI Search service in any [region that provides agentic retrieval](search-region-support.md).
 
 + Completion of the [OneLake indexer prerequisites](search-how-to-index-onelake-files.md#prerequisites).
 
@@ -139,9 +139,6 @@ The following JSON is an example response for an indexed OneLake knowledge sourc
 }
 ```
 
-> [!NOTE]
-> Sensitive information is redacted. The generated resources appear at the end of the response.
-
 ## Create a knowledge source
 
 Run the following code to create an indexed OneLake knowledge source.
@@ -477,7 +474,7 @@ Content-Type: application/json
 
 ### Source-specific properties
 
-For both the 2026-05-01-preview and 2026-04-01 API versions, you can pass the following properties to create an indexed OneLake knowledge source.
+The following properties apply to indexed OneLake knowledge sources.
 
 ::: zone pivot="csharp"
 
@@ -538,31 +535,27 @@ For both the 2026-05-01-preview and 2026-04-01 API versions, you can pass the fo
 
 [!INCLUDE [Check ingestion status](includes/how-tos/knowledge-source-status.md)]
 
-## Review the created objects
+## Review the generated objects
 
-When you create an indexed OneLake knowledge source, your search service also creates an indexer, index, skillset, and data source. We don't recommend that you edit these objects, as introducing an error or incompatibility can break the pipeline.
+[!INCLUDE [Review the generated objects](includes/how-tos/knowledge-source-review-objects.md)]
+
+## Assign to a knowledge base
 
-After you create a knowledge source, the response lists the created objects. These objects are created according to a fixed template, and their names are based on the name of the knowledge source. You can't change the object names.
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
-We recommend using the Azure portal to validate output creation. The workflow is:
+For any knowledge base that specifies an indexed OneLake knowledge source, be sure to set `includeReferenceSourceData` to `true`. This step is necessary for pulling the source document URL into the citation.
 
-1. Check the indexer for success or failure messages. Connection or quota errors appear here.
-1. Check the index for searchable content. Use Search Explorer to run queries.
-1. Check the skillset to learn how your content is chunked and optionally vectorized.
-1. Check the data source for connection details. Our example uses API keys for simplicity, but you can use Microsoft Entra ID for authentication and role-based access control for authorization.
+## Query a knowledge base
 
-## Assign to a knowledge base
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query the knowledge source. This knowledge source supports optional configurations for document-level permissions enforcement and document-embedded image surfacing.
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+### Enforce document-level permissions
 
-For any knowledge base that specifies an indexed OneLake knowledge source, be sure to set `includeReferenceSourceData` to `true`. This step is necessary for pulling the source document URL into the citation.
+To enforce document-level permissions, set `ingestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time (preview)](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time-preview).
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+### Surface document-embedded images
 
-> [!TIP]
-> + To enforce document-level permissions, set `ingestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time-preview).
->
-> + To surface document-embedded images (such as diagrams or scans) in answer synthesis responses, configure `assetStore` on this knowledge source and enable image serving on the knowledge base. For more information, see [Surface document-embedded images in agentic retrieval (preview)](agentic-retrieval-how-to-image-serving.md).
+To surface document-embedded images (such as diagrams or scans) in answer synthesis responses, configure `assetStore` on this knowledge source, and then enable image serving on the knowledge base. For more information, see [Surface document-embedded images in agentic retrieval (preview)](agentic-retrieval-how-to-image-serving.md).
 
 ## Delete a knowledge source
 
@@ -571,5 +564,6 @@ After the knowledge base is configured, use the [retrieve action](agentic-retrie
 ## Related content
 
 + [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
-+ [Agentic RAG: Build a reasoning retrieval engine with Azure AI Search (YouTube video)](https://www.youtube.com/watch?v=PeTmOidqHM8)
-+ [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)
++ [What is a knowledge source?](agentic-knowledge-source-overview.md)
++ [Create a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md)
++ [Query a knowledge base](agentic-retrieval-how-to-retrieve.md)

@@ -21,7 +21,7 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-A *search index knowledge source* specifies a connection to an Azure AI Search index that provides searchable content in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+A *search index knowledge source* connects an existing Azure AI Search index, including its indexed text and vectors, to an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
 ### Usage support
 
@@ -31,7 +31,7 @@ A *search index knowledge source* specifies a connection to an Azure AI Search i
 
 ## Prerequisites
 
-+ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md).
++ An Azure AI Search service in any [region that provides agentic retrieval](search-region-support.md).
 
 + A search index containing plain text or vector content with a semantic configuration. [Review the index criteria for agentic retrieval](agentic-retrieval-how-to-create-index.md#criteria-for-agentic-retrieval). The index must be on the same search service as the knowledge base.
 
@@ -281,7 +281,7 @@ Content-Type: application/json
 
 ### Source-specific properties
 
-You can pass the following properties to create a search index knowledge source. Most properties are supported in both the 2026-05-01-preview and 2026-04-01 API versions; preview-only properties are marked in the description.
+The following properties apply to search index knowledge sources.
 
 ::: zone pivot="csharp"
 
@@ -458,9 +458,11 @@ Because the filters are combined with `AND`, `filterAddOn` can only narrow the p
 
 ## Assign to a knowledge base
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+## Query a knowledge base
+
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
 
 ## Delete a knowledge source
 
@@ -469,5 +471,6 @@ After the knowledge base is configured, use the [retrieve action](agentic-retrie
 ## Related content
 
 + [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
-+ [Agentic RAG: Build a reasoning retrieval engine with Azure AI Search (YouTube video)](https://www.youtube.com/watch?v=PeTmOidqHM8)
-+ [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)
++ [What is a knowledge source?](agentic-knowledge-source-overview.md)
++ [Create a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md)
++ [Query a knowledge base](agentic-retrieval-how-to-retrieve.md)

@@ -23,7 +23,7 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-Use an *indexed SharePoint knowledge source* (preview) to index and query SharePoint content in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+An *indexed SharePoint knowledge source* (preview) ingests SharePoint content into an agentic retrieval pipeline in Azure AI Search. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
 When you create an indexed SharePoint knowledge source, you specify a SharePoint connection string, models, and properties to automatically generate the following Azure AI Search objects:
 
@@ -40,7 +40,7 @@ When you create an indexed SharePoint knowledge source, you specify a SharePoint
 
 ## Prerequisites
 
-+ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md).
++ An Azure AI Search service in any [region that provides agentic retrieval](search-region-support.md).
 
 + Completion of the [SharePoint indexer prerequisites](search-how-to-index-sharepoint-online.md#prerequisites).
 
@@ -121,9 +121,6 @@ The following JSON is an example response for an indexed SharePoint knowledge so
 }
 ```
 
-> [!NOTE]
-> Sensitive information is redacted. The generated resources appear at the end of the response.
-
 ## Create a knowledge source
 
 Run the following code to create an indexed SharePoint knowledge source.
@@ -282,7 +279,7 @@ Content-Type: application/json
 
 ### Source-specific properties
 
-You can pass the following properties to create an indexed SharePoint knowledge source.
+The following properties apply to indexed SharePoint knowledge sources.
 
 ::: zone pivot="csharp"
 
@@ -335,31 +332,27 @@ You can pass the following properties to create an indexed SharePoint knowledge
 
 [!INCLUDE [Check ingestion status](includes/how-tos/knowledge-source-status.md)]
 
-## Review the created objects
+## Review the generated objects
 
-When you create an indexed SharePoint knowledge source, your search service also creates an indexer, index, skillset, and data source. We don't recommend that you edit these objects, as introducing an error or incompatibility can break the pipeline.
+[!INCLUDE [Review the generated objects](includes/how-tos/knowledge-source-review-objects.md)]
 
-After you create a knowledge source, the response lists the created objects. These objects are created according to a fixed template, and their names are based on the name of the knowledge source. You can't change the object names.
+## Assign to a knowledge base
 
-We recommend using the Azure portal to validate output creation. The workflow is:
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
-1. Check the indexer for success or failure messages. Connection or quota errors appear here.
-1. Check the index for searchable content. Use Search Explorer to run queries.
-1. Check the skillset to learn how your content is chunked and optionally vectorized.
-1. Check the data source for connection details. Our example uses API keys for simplicity, but you can use Microsoft Entra ID for authentication and role-based access control for authorization.
+For any knowledge base that specifies an indexed SharePoint knowledge source, be sure to set `includeReferenceSourceData` to `true`. This step is necessary for pulling the source document URL into the citation.
 
-## Assign to a knowledge base
+## Query a knowledge base
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query the knowledge source. This knowledge source supports optional configurations for document-level permissions enforcement and document-embedded image surfacing.
 
-For any knowledge base that specifies an indexed SharePoint knowledge source, be sure to set `includeReferenceSourceData` to `true`. This step is necessary for pulling the source document URL into the citation.
+### Enforce document-level permissions
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+To enforce document-level permissions, set `ingestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time (preview)](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time-preview).
 
-> [!TIP]
-> + To enforce document-level permissions, set `ingestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time-preview).
->
-> + To surface document-embedded images (such as diagrams or scans) in answer synthesis responses, configure `assetStore` on this knowledge source and enable image serving on the knowledge base. For more information, see [Surface document-embedded images in agentic retrieval (preview)](agentic-retrieval-how-to-image-serving.md).
+### Surface document-embedded images
+
+To surface document-embedded images (such as diagrams or scans) in answer synthesis responses, configure `assetStore` on this knowledge source, and then enable image serving on the knowledge base. For more information, see [Surface document-embedded images in agentic retrieval (preview)](agentic-retrieval-how-to-image-serving.md).
 
 ## Delete a knowledge source
 
@@ -368,5 +361,6 @@ After the knowledge base is configured, use the [retrieve action](agentic-retrie
 ## Related content
 
 + [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
-+ [Agentic RAG: Build a reasoning retrieval engine with Azure AI Search (YouTube video)](https://www.youtube.com/watch?v=PeTmOidqHM8)
-+ [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)
++ [What is a knowledge source?](agentic-knowledge-source-overview.md)
++ [Create a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md)
++ [Query a knowledge base](agentic-retrieval-how-to-retrieve.md)

@@ -21,11 +21,11 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-A *remote SharePoint knowledge source* (preview) uses the [Copilot Retrieval API](/microsoft-365-copilot/extensibility/api/ai-services/retrieval/overview) (preview) to query textual content directly from SharePoint in Microsoft 365. No search index or connection string is needed. Only textual content is queried, and usage is billed through Microsoft 365 and a Copilot license.
+A *remote SharePoint knowledge source* (preview) uses the [Copilot Retrieval API](/microsoft-365-copilot/extensibility/api/ai-services/retrieval/overview) (preview) to query textual content directly from SharePoint in Microsoft 365. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
 To limit sites or constrain search, set a [filter expression](#filter-expression-examples) to scope by URLs, date ranges, file types, and other metadata. The caller's identity must be recognized by both the Azure tenant and the Microsoft 365 tenant because the retrieval engine queries SharePoint on behalf of the user.
 
-Like any other knowledge source, you specify a remote SharePoint knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md) and use the results as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+Unlike indexed knowledge sources, remote SharePoint knowledge sources query live data directly at retrieval time. No search index or connection string is needed, and usage is billed through Microsoft 365 and a Copilot license.
 
 ### Usage support
 
@@ -35,7 +35,7 @@ Like any other knowledge source, you specify a remote SharePoint knowledge sourc
 
 ## Prerequisites
 
-+ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md). 
++ An Azure AI Search service in any [region that provides agentic retrieval](search-region-support.md). 
 
 + SharePoint in a Microsoft 365 tenant that's under the same Microsoft Entra ID tenant as Azure.
 
@@ -61,25 +61,25 @@ Like any other knowledge source, you specify a remote SharePoint knowledge sourc
 
 ::: zone-end
 
-## Limitations
+## Limitations and considerations
 
-The following limitations in the [Copilot Retrieval API](/microsoft-365-copilot/extensibility/api/ai-services/retrieval/overview) apply to remote SharePoint knowledge sources.
+The following limitations and considerations in the [Copilot Retrieval API](/microsoft-365-copilot/extensibility/api/ai-services/retrieval/overview) apply to remote SharePoint knowledge sources.
 
 + There's no support for Copilot connectors or OneDrive content. Content is retrieved from SharePoint sites only.
 
 + Limit of 200 requests per user per hour.
 
 + Query character limit of 1,500 characters.
 
-+ Hybrid queries are only supported for the following file extensions: .doc, .docx, .pptx, .pdf, .aspx, and .one.
++ Hybrid queries are only supported for the following file extensions: `.doc`, `.docx`, `.pptx`, `.pdf`, `.aspx`, and `.one`.
 
 + Multimodal retrieval (nontextual content, including tables, images, and charts) isn't supported.
 
 + Maximum of 25 results from a query.
 
-+ Results are returned by Copilot Retrieval API as unordered.
++ Results are returned by the Copilot Retrieval API as unordered.
 
-+ Invalid Keyword Query Language (KQL) filter expressions are ignored and the query continues to execute without the filter.
++ Invalid Keyword Query Language (KQL) filter expressions are ignored, and the query continues to execute without the filter.
 
 ## Check for existing knowledge sources
 
@@ -193,7 +193,7 @@ Content-Type: application/json
 
 ### Source-specific properties
 
-You can pass the following properties to create a remote SharePoint knowledge source.
+The following properties apply to remote SharePoint knowledge sources.
 
 ::: zone pivot="csharp"
 
@@ -255,11 +255,11 @@ Learn more about [KQL filters](/microsoft-365-copilot/extensibility/api/ai-servi
 
 ## Assign to a knowledge base
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
 ## Query a knowledge base
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query SharePoint content. Remote SharePoint has source-specific behaviors for query-time filtering, query formulation, response fields, and permissions enforcement.
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query SharePoint content. Remote SharePoint has source-specific behaviors for query-time filtering, query formulation, response fields, and permissions enforcement.
 
 ### Apply a KQL filter at query time
 
@@ -427,5 +427,6 @@ For instructions on passing the token, see [Enforce permissions at query time](a
 ## Related content
 
 + [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
-+ [Agentic RAG: Build a reasoning retrieval engine with Azure AI Search (YouTube video)](https://www.youtube.com/watch?v=PeTmOidqHM8)
-+ [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)
++ [What is a knowledge source?](agentic-knowledge-source-overview.md)
++ [Create a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md)
++ [Query a knowledge base](agentic-retrieval-how-to-retrieve.md)

@@ -6,6 +6,7 @@ ms.custom:
   - ignite-2025
 ms.topic: how-to
 ms.date: 06/02/2026
+ai-usage: ai-assisted
 zone_pivot_groups: search-csharp-python-rest
 ---
 
@@ -31,11 +32,11 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > + Learn more about how Azure admins can [manage access to use of Web Knowledge Source](agentic-knowledge-source-how-to-web-manage.md).
 
-*Web Knowledge Source* enables retrieval of real-time web data from Microsoft Bing in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+*Web Knowledge Source* enables retrieval of real-time web data from Microsoft Bing in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
 Bing Custom Search is always the search provider for Web Knowledge Source. Although you can't specify alternative search providers or engines, you can include or exclude specific *domains*, such as https://learn.microsoft.com. When no domains are specified, Web Knowledge Source has unrestricted access to the entire public internet.
 
-Web Knowledge Source works best alongside other knowledge sources. Use Web Knowledge Source when your proprietary content doesn't provide complete, up-to-date answers or when you want to supplement results with information from a commercial search engine.
+Web Knowledge Source works best alongside other knowledge sources. Use it when your proprietary content doesn't provide complete, up-to-date answers or when you want to supplement results with information from a commercial search engine.
 
 ### Usage support
 
@@ -305,7 +306,7 @@ api-key: {{api-key}}
 
 ### Source-specific properties
 
-For the 2026-05-01-preview and 2026-04-01 API versions, you can pass the following properties to create a web knowledge source.
+The following properties apply to web knowledge sources.
 
 ::: zone pivot="csharp"
 
@@ -352,9 +353,7 @@ For the 2026-05-01-preview and 2026-04-01 API versions, you can pass the followi
 
 ## Assign to a knowledge base
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
-
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
 ## Query a knowledge base
 
@@ -398,3 +397,6 @@ When you query a knowledge base that includes Web Knowledge Source, the retrieve
 
 + [Manage access to Web Knowledge Source in your Azure subscription](agentic-knowledge-source-how-to-web-manage.md)
 + [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
++ [What is a knowledge source?](agentic-knowledge-source-overview.md)
++ [Create a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md)
++ [Query a knowledge base](agentic-retrieval-how-to-retrieve.md)

@@ -19,12 +19,14 @@ zone_pivot_groups: search-csharp-python-rest
 >
 > You're responsible for carefully reviewing and testing applications you build in the context of your specific use cases and making all appropriate decisions and customizations. This includes implementing your own responsible AI mitigations, such as metaprompts, content filters, or other safety systems, and ensuring your applications meet appropriate quality, reliability, security, and trustworthiness standards. For more information, see the [Azure AI Search Transparency Note](/azure/foundry/responsible-ai/search/transparency-note).
 
-A *Work IQ knowledge source* (preview) connects [Work IQ](/microsoft-365/copilot/extensibility/work-iq) to an agentic retrieval pipeline in Azure AI Search, providing intelligence from your organization's Microsoft 365 content as grounding data.
+A *Work IQ knowledge source* (preview) connects [Work IQ](/microsoft-365/copilot/extensibility/work-iq) to an agentic retrieval pipeline in Azure AI Search. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when the knowledge base is [queried at runtime](agentic-retrieval-how-to-retrieve.md).
 
-Unlike indexed knowledge sources, a Work IQ knowledge source queries Work IQ directly at retrieval time. No ingestion pipeline is needed. Queries require an end-user access token, which the retrieval engine uses to call Work IQ on the caller's behalf.
+Work IQ surfaces organizational intelligence from your Microsoft 365 content, including documents, emails, meetings, and activity across Microsoft 365 apps.
+
+Unlike indexed knowledge sources, Work IQ knowledge sources query live data directly at retrieval time. No ingestion pipeline is needed. Queries require an end-user access token, which the retrieval engine uses to call Work IQ on the caller's behalf.
 
 > [!WARNING]
-> In this preview, a Work IQ knowledge source may use Work IQ capabilities that perform actions, not just retrieve information. Use it with care, limit access to trusted applications and users, and review your scenario's permissions and governance controls before enabling it.
+> In this preview, a Work IQ knowledge source might use Work IQ capabilities that perform actions, not just retrieve information. Use it with care, limit access to trusted applications and users, and review your scenario's permissions and governance controls before enabling it.
 
 ### Usage support
 
@@ -113,7 +115,7 @@ Work IQ inherits Microsoft 365's compliance certifications. For details, see [Da
 
 ## Check for existing knowledge sources
 
-[!INCLUDE [](./includes/how-tos/knowledge-source-check.md)]
+[!INCLUDE [Check for existing knowledge sources](includes/how-tos/knowledge-source-check.md)]
 
 The following JSON is an example response for a Work IQ knowledge source.
 
@@ -211,11 +213,11 @@ The following properties apply to Work IQ knowledge sources.
 
 ## Assign to a knowledge base
 
-If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+If you're satisfied with the knowledge source, [add it to a knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
 
 ## Query a knowledge base
 
-After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query Work IQ content. This knowledge source has unique query-time permissions enforcement and response characteristics.
+After the knowledge base is configured, [call the retrieve action or MCP endpoint](agentic-retrieval-how-to-retrieve.md) to query Work IQ content. This knowledge source has unique query-time permissions enforcement and response characteristics.
 
 > [!IMPORTANT]
 > Work IQ can take 40–60 seconds or more to respond. To avoid timeout errors, set `maxRuntimeInSeconds` on the retrieve request to `120` or higher.
@@ -289,7 +291,7 @@ The following example shows a retrieve response containing a Work IQ knowledge s
 
 ## Delete a knowledge source
 
-[!INCLUDE [](./includes/how-tos/knowledge-source-delete.md)]
+[!INCLUDE [Delete a knowledge source](includes/how-tos/knowledge-source-delete.md)]
 
 ## Related content
 

@@ -235,21 +235,21 @@ To query the knowledge base:
 
    The activity log offers insight into the steps taken during retrieval, including query planning and execution, semantic ranking, and answer synthesis. For more information, see [Review the activity array](agentic-retrieval-how-to-retrieve.md#activity-array).
 
-## Review the created objects
+## Review the generated objects
 
 Azure AI Search automatically generates a data source, skillset, index, and indexer for each blob knowledge source. These objects form an end-to-end pipeline for data ingestion, enrichment, chunking, and vectorization. You can review these objects to learn how your data is processed for agentic retrieval.
 
 To review the auto-generated objects:
 
 1. From the left pane, select **Search management**.
 
+1. Check the indexer for success or failure messages. Connection or quota errors appear here.
+
 1. Check the data source to verify the connection to your blob storage container.
 
 1. Check the skillset to see how your content is chunked and vectorized using your embedding model.
 
-1. Check the index to see how your content is indexed and exposed for retrieval, including which fields are searchable and filterable and which fields store vectors for similarity search.
-
-1. Check the indexer for success or failure messages. Connection or quota errors appear here.
+1. Check the index to see how your content is indexed and exposed for retrieval, including which fields are searchable and filterable and which fields store vectors for similarity search. Use Search Explorer to run queries against the generated index.
 
 ## Clean up resources
 

@@ -33,12 +33,19 @@ To delete a knowledge source:
 
    An example response might look like the following:
 
-   ```md
-    Knowledge Bases:
-      - earth-knowledge-base
-      - hotels-sample-knowledge-base
-      - my-demo-knowledge-base
-    ```
+   ```json
+    {
+        "@odata.context": "https://my-search-service.search.windows.net/$metadata#knowledgebases(name)",
+        "value": [
+        {
+            "name": "my-kb"
+        },
+        {
+            "name": "my-kb-2"
+        }
+        ]
+    }
+   ```
 
 1. Get an individual knowledge base definition to check for knowledge source references.
 

@@ -0,0 +1,19 @@
+---
+ms.service: azure-ai-search
+ms.topic: include
+ms.date: 05/29/2026
+---
+
+When you create this knowledge source, Azure AI Search automatically generates a data source, skillset, indexer, and index. The creation response lists each object under `createdResources`.
+
+These objects are generated according to a fixed template, and their names are based on the name of the knowledge source. You can't change the object names. Avoid editing these objects directly, as changes can introduce errors or incompatibilities that break the indexer pipeline.
+
+You can use the Azure portal to validate object creation. The workflow is:
+
+1. Check the indexer for success or failure messages. Connection or quota errors appear here.
+
+1. Check the data source to verify the connection to your data store. The connection uses either a connection string or a managed identity, depending on how you configured the knowledge source.
+
+1. Check the skillset to see how your content is chunked and optionally vectorized.
+
+1. Check the index to see how your content is indexed and exposed for retrieval, including which fields are searchable and filterable and which fields store vectors for similarity search. Use Search Explorer to run queries against the generated index.