@@ -32,10 +32,7 @@ You can enable answer synthesis in two ways:
 
 + A knowledge base that uses the [2025-11-01-preview syntax](agentic-retrieval-how-to-migrate.md).
 
-+ [Visual Studio Code](https://code.visualstudio.com/) with the [REST Client extension](https://marketplace.visualstudio.com/items?itemName=humao.rest-client) or a prerelease package of an Azure SDK that provides the knowledge base REST APIs.
-
-> [!NOTE]
-> Although you can use the Azure portal to configure answer synthesis, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](agentic-retrieval-how-to-migrate.md).
++ [Visual Studio Code](https://code.visualstudio.com/) with the [REST Client extension](https://marketplace.visualstudio.com/items?itemName=humao.rest-client) or a preview Azure SDK package that provides the knowledge base REST APIs.
 
 ## Enable answer synthesis on a knowledge base
 

@@ -312,7 +312,7 @@ index_client.delete_knowledge_base(base_name)
 print(f"Knowledge base '{base_name}' deleted successfully")
 
 # Delete the knowledge source
-index_client.delete_knowledge_source(knowledge_source=knowledge_source_name) # This is new feature in 2025-08-01-Preview api version
+index_client.delete_knowledge_source(knowledge_source=knowledge_source_name)
 print(f"Knowledge source '{knowledge_source_name}' deleted successfully.")
 
 # Delete the search index

@@ -41,7 +41,7 @@ You can continue to run older code with no updates if you retain the API version
 
 ### [**2025-11-01-preview**](#tab/migrate-11-01)
 
-If you're migrating from [2025-08-01-preview](#2025-08-01-preview-1), *knowledge agent* is renamed to *knowledge base*, and multiple properties are relocated to different objects and levels within an object definition.
+If you're migrating from [2025-08-01-preview](#2025-08-01-preview-1), "knowledge agent" is renamed to "knowledge base," and multiple properties are relocated to different objects and levels within an object definition.
 
 1. [Update searchIndex knowledge sources](#update-a-searchindex-knowledge-source).
 1. [Update azureBlob knowledge sources](#update-an-azureblob-knowledge-source).

@@ -40,9 +40,6 @@ You can also use optional [answer synthesis](agentic-retrieval-how-to-answer-syn
 
 To follow the steps in this guide, we recommend [Visual Studio Code](https://code.visualstudio.com/download) with a [REST client](https://marketplace.visualstudio.com/items?itemName=humao.rest-client) for sending REST API calls to Azure AI Search.
 
-> [!NOTE]
-> Although you can use the Azure portal to retrieve data from knowledge bases, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](agentic-retrieval-how-to-migrate.md).
-
 ## Set up the retrieve action
 
 A retrieve action is specified on a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md). The knowledge base has one or more knowledge sources. Retrieval can return a synthesized answer in natural language or raw grounding chunks from the knowledge sources.

@@ -98,16 +98,14 @@ Your application drives the pipeline by calling the knowledge base and handling
 
 ## How to get started
 
-To create an agentic retrieval solution, you must use a preview REST API version or a prerelease Azure SDK package that provides the functionality.
+To create an agentic retrieval solution, you can use the Azure portal, the latest preview REST APIs, or a preview Azure SDK package that provides the functionality.
 
-Currently, Azure portal support for agentic retrieval is limited to the 2025-08-01-preview. We recommend using a programmatic approach to access the latest features.
+Currently, the portal only supports the creation of search index and blob knowledge sources. We recommend using a programmatic approach to create other types of knowledge sources.
 
 ### [**Quickstarts**](#tab/quickstarts)
 
-+ [Quickstart: Use agentic retrieval in Azure AI Search](search-get-started-agentic-retrieval.md)
-  + This quickstart supports C#, Java, JavaScript, Python, TypeScript, and REST.
 + [Quickstart: Use agentic retrieval in the Azure portal](get-started-portal-agentic-retrieval.md)
-  + The portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. Breaking changes apply to objects created in this quickstart.
++ [Quickstart: Use agentic retrieval in Azure AI Search](search-get-started-agentic-retrieval.md) (C#, Java, JavaScript, Python, TypeScript, REST)
 
 ### [**How-to guides**](#tab/how-to-guides)
 

@@ -9,7 +9,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2025
 ms.topic: quickstart
-ms.date: 11/07/2025
+ms.date: 12/18/2025
 ---
 
 # Quickstart: Use agentic retrieval in the Azure portal
@@ -27,7 +27,7 @@ The portal guides you through the process of creating the following objects:
 Afterwards, you test the knowledge base by submitting a complex query that requires information from multiple documents and reviewing the synthesized answer.
 
 > [!IMPORTANT]
-> Because the portal uses the 2025-08-01-preview REST API version for agentic retrieval, the knowledge source and knowledge base created in this quickstart aren't compatible with the latest 2025-11-01-preview. For help with breaking changes, see [Migrate your agentic retrieval code](agentic-retrieval-how-to-migrate.md).
+> The portal now uses the 2025-11-01-preview REST APIs for knowledge sources and knowledge bases. If you previously created agentic retrieval objects in the portal, those objects use the 2025-08-01-preview and are subject to breaking changes. We recommend that you [migrate existing objects and code](agentic-retrieval-how-to-migrate.md) as soon as possible.
 
 ## Prerequisites
 
@@ -127,44 +127,41 @@ To create the knowledge source for this quickstart:
 
 1. Sign in to the [Azure portal](https://portal.azure.com/) and select your search service.
 
-1. From the left pane, select **Knowledge retrieval** > **Knowledge sources**.
+1. From the left pane, select **Agentic retrieval** > **Knowledge sources**.
 
 1. Select **Add knowledge source** > **Add knowledge source**.
 
-1. Enter **earth-at-night-ks** for the name.
+1. Select **Azure blob**.
 
-1. Select **Azure blob**, and then select your subscription, storage account, and container with the sample data.
+1. Enter **earth-at-night-ks** for the name, and then select your subscription, storage account, and container with the sample data.
 
 1. Select the **Authenticate using managed identity** checkbox. Leave the identity type as **System-assigned**.
 
 1. Select **Add vectorizer**.
 
 1. Select **Azure AI Foundry** for the kind, and then select your subscription, project, and embedding model deployment.
 
-1. Select **System managed identity** for the authentication type.
+1. Select **System assigned identity** for the authentication type.
 
 1. Create the knowledge source.
 
    :::image type="content" source="media/get-started-portal-agentic-retrieval/create-knowledge-source.png" alt-text="Screenshot of the knowledge source configuration for this quickstart." lightbox="media/get-started-portal-agentic-retrieval/create-knowledge-source.png" :::
 
 ## Create a knowledge base
 
-> [!NOTE]
-> The portal uses the 2025-08-01-preview, which refers to "knowledge bases" as "knowledge agents." Although the portal UI uses the latest terminology, the underlying REST API objects and JSON payloads still use "knowledge agents."
-
 A knowledge base uses your knowledge source and deployed LLM to orchestrate agentic retrieval. When a user submits a complex query, the LLM generates subqueries that are sent simultaneously to your knowledge source. Azure AI Search then semantically ranks the results for relevance and combines the best results into a single, unified response.
 
 The output mode determines how the knowledge base formulates answers. You can either use extractive data for verbatim content or [answer synthesis](agentic-retrieval-how-to-answer-synthesis.md) for natural-language answer generation. By default, the portal uses answer synthesis.
 
 To create the knowledge base for this quickstart:
 
-1. From the left pane, select **Knowledge retrieval** > **Knowledge bases**.
+1. From the left pane, select **Agentic retrieval** > **Knowledge bases**.
 
 1. Select **Add knowledge base** > **Add knowledge base**.
 
 1. Enter **earth-at-night-kb** for the name.
 
-1. Under **Model deployment**, select **Add model deployment**.
+1. Under **Chat completion model**, select **Add model deployment**.
 
 1. Select **Azure AI Foundry** for the kind, and then select your subscription, project, and LLM deployment.
 
@@ -193,55 +190,69 @@ To query the knowledge base:
 1. Review the synthesized, citation-backed answer, which should be similar to the following example.
 
     ```
-    The suburban belts exhibit larger December brightening compared to urban cores due to the increased use of decorative and festive lighting in residential areas, which are more prevalent in suburban regions. In contrast, urban cores, despite having higher absolute light levels, experience less seasonal variation in lighting. The Phoenix nighttime street grid is sharply visible from space because of its regular grid layout and the extensive use of street lighting, which creates a consistent and bright pattern. Conversely, large stretches of interstate highways between Midwestern cities are less illuminated, as they primarily serve as transit routes with minimal lighting infrastructure, resulting in comparatively dim visibility from space.
+    Suburban belts show larger December brightening in satellite nighttime lights than urban cores mainly because of relative (percentage) change effects and differences in how light is used and distributed. Areas with lower baseline light (suburbs, residential streets) can increase lighting use or reflect more light in winter and so show a bigger percent change, while bright urban cores are already near sensor saturation so their relative increase is small. The retrieved material explains that brightest lights are generally the most urbanized but not necessarily the most populated, and that poor or low‑light areas can have large populations but low availability or use of electric lights; thus lower‑light suburbs can exhibit larger relative changes when seasonal lighting rises.
     ```
 
-1. Select the debug icon to review the activity log, which should be similar to the following example.
+1. Select the debug icon to review the activity log, which should be similar to the following JSON.
 
-    ```
+    ```JSON
     [
       {
         "type": "modelQueryPlanning",
         "id": 0,
-        "inputTokens": 2081,
-        "outputTokens": 128,
-        "elapsedMs": 1577
+        "inputTokens": 1518,
+        "outputTokens": 284,
+        "elapsedMs": 3001
       },
       {
         "type": "azureBlob",
         "id": 1,
         "knowledgeSourceName": "earth-at-night-ks",
-        "queryTime": "2025-11-03T15:09:28.172Z",
-        "count": 0,
-        "elapsedMs": 731,
+        "queryTime": "2025-12-12T18:54:28.792Z",
+        "count": 1,
+        "elapsedMs": 456,
         "azureBlobArguments": {
-          "search": "Why do suburban belts display larger December brightening than urban cores despite higher downtown light levels?"
+          "search": "causes of December brightening in satellite nighttime lights suburban vs urban cores"
         }
       },
       {
         "type": "azureBlob",
         "id": 2,
         "knowledgeSourceName": "earth-at-night-ks",
-        "queryTime": "2025-11-03T15:09:28.669Z",
+        "queryTime": "2025-12-12T18:54:29.389Z",
         "count": 3,
-        "elapsedMs": 497,
+        "elapsedMs": 596,
         "azureBlobArguments": {
-          "search": "Why is the Phoenix nighttime street grid sharply visible from space compared to dim interstates in the Midwest?"
+          "search": "factors affecting seasonal variation in nighttime lights December winter brightening suburban belts urban cores"
         }
       },
       {
-        "type": "semanticReranker",
+        "type": "azureBlob",
         "id": 3,
-        "inputTokens": 0
+        "knowledgeSourceName": "earth-at-night-ks",
+        "queryTime": "2025-12-12T18:54:29.862Z",
+        "count": 6,
+        "elapsedMs": 472,
+        "azureBlobArguments": {
+          "search": "why is Phoenix street grid highly visible at night from space compared to dim interstates in the Midwest reasons lighting patterns road lighting urban form"
+        }
       },
       {
-        "type": "modelAnswerSynthesis",
+        "type": "agenticReasoning",
         "id": 4,
-        "inputTokens": 3938,
-        "outputTokens": 136,
-        "elapsedMs": 1963
+        "retrievalReasoningEffort": {
+          "kind": "low"
+        },
+        "reasoningTokens": 111243
+      },
+      {
+        "type": "modelAnswerSynthesis",
+        "id": 5,
+        "inputTokens": 7514,
+        "outputTokens": 1058,
+        "elapsedMs": 12334
       }
-    ]   
+    ]
     ```
 
    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#review-the-activity-array).

@@ -33,9 +33,6 @@ Unlike a [search index knowledge source](../../agentic-knowledge-source-how-to-s
 
 + Permission to create and use objects on Azure AI Search. We recommend [role-based access](../../search-security-rbac.md), but you can use [API keys](../../search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](../../search-get-started-rbac.md).
 
-> [!NOTE]
-> Although you can use the Azure portal to create blob knowledge sources, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](../../agentic-retrieval-how-to-migrate.md).
-
 ## Check for existing knowledge sources
 
 [!INCLUDE [Check for existing knowledge sources using C#](knowledge-source-check-csharp.md)]

@@ -33,9 +33,6 @@ Unlike a [search index knowledge source](../../agentic-knowledge-source-how-to-s
 
 + Permission to create and use objects on Azure AI Search. We recommend [role-based access](../../search-security-rbac.md), but you can use [API keys](../../search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](../../search-get-started-rbac.md).
 
-> [!NOTE]
-> Although you can use the Azure portal to create blob knowledge sources, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](../../agentic-retrieval-how-to-migrate.md).
-
 ## Check for existing knowledge sources
 
 [!INCLUDE [Check for existing knowledge sources using Python](knowledge-source-check-python.md)]

@@ -33,9 +33,6 @@ Unlike a [search index knowledge source](../../agentic-knowledge-source-how-to-s
 
 + Permission to create and use objects on Azure AI Search. We recommend [role-based access](../../search-security-rbac.md), but you can use [API keys](../../search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](../../search-get-started-rbac.md).
 
-> [!NOTE]
-> Although you can use the Azure portal to create blob knowledge sources, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](../../agentic-retrieval-how-to-migrate.md).
-
 ## Check for existing knowledge sources
 
 [!INCLUDE [Check for existing knowledge sources using REST](knowledge-source-check-rest.md)]

@@ -21,9 +21,6 @@ A *search index knowledge source* specifies a connection to an Azure AI Search i
 
 + Permission to create and use objects on Azure AI Search. We recommend [role-based access](../../search-security-rbac.md), but you can use [API keys](../../search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](../../search-get-started-rbac.md).
 
-> [!NOTE]
-> Although you can use the Azure portal to create search index knowledge sources, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](../../agentic-retrieval-how-to-migrate.md).
-
 ## Check for existing knowledge sources
 
 [!INCLUDE [Check for existing knowledge sources using C#](knowledge-source-check-csharp.md)]

@@ -21,9 +21,6 @@ A *search index knowledge source* specifies a connection to an Azure AI Search i
 
 + Permission to create and use objects on Azure AI Search. We recommend [role-based access](../../search-security-rbac.md), but you can use [API keys](../../search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](../../search-get-started-rbac.md).
 
-> [!NOTE]
-> Although you can use the Azure portal to create search index knowledge sources, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](../../agentic-retrieval-how-to-migrate.md).
-
 ## Check for existing knowledge sources
 
 [!INCLUDE [Check for existing knowledge sources using Python](knowledge-source-check-python.md)]

@@ -21,9 +21,6 @@ A *search index knowledge source* specifies a connection to an Azure AI Search i
 
 + Permission to create and use objects on Azure AI Search. We recommend [role-based access](../../search-security-rbac.md), but you can use [API keys](../../search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](../../search-get-started-rbac.md).
 
-> [!NOTE]
-> Although you can use the Azure portal to create search index knowledge sources, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](../../agentic-retrieval-how-to-migrate.md).
-
 ## Check for existing knowledge sources
 
 [!INCLUDE [Check for existing knowledge sources using REST](knowledge-source-check-rest.md)]

@@ -21,7 +21,7 @@ A knowledge base specifies:
 After you create a knowledge base, you can update its properties at any time. If the knowledge base is in use, updates take effect on the next retrieval.
 
 > [!IMPORTANT]
-> 2025-11-01-preview renames the 2025-08-01-preview *knowledge agent* to *knowledge base*. This is a breaking change. We recommend [migrating existing code](../../agentic-retrieval-how-to-migrate.md) to the new APIs as soon as possible.
+> 2025-11-01-preview renames the 2025-08-01-preview "knowledge agent" to "knowledge base." This is a breaking change. We recommend [migrating existing code](../../agentic-retrieval-how-to-migrate.md) to the new APIs as soon as possible.
 
 ## Prerequisites
 
@@ -35,9 +35,6 @@ After you create a knowledge base, you can update its properties at any time. If
 
 + The latest preview version of the [`azure-search-documents` client library](https://pypi.org/project/azure-search-documents/11.7.0b2/) for Python.
 
-> [!NOTE]
-> Although you can use the Azure portal to create knowledge bases, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](../../agentic-retrieval-how-to-migrate.md).
-
 ### Supported models
 
 Use one of the following LLMs from Azure OpenAI or an equivalent open-source model. For deployment instructions, see [Deploy Azure OpenAI models with Microsoft Foundry](/azure/ai-foundry/how-to/deploy-models-openai).

@@ -21,7 +21,7 @@ A knowledge base specifies:
 After you create a knowledge base, you can update its properties at any time. If the knowledge base is in use, updates take effect on the next retrieval.
 
 > [!IMPORTANT]
-> 2025-11-01-preview renames the 2025-08-01-preview *knowledge agent* to *knowledge base*. This is a breaking change. We recommend [migrating existing code](../../agentic-retrieval-how-to-migrate.md) to the new APIs as soon as possible.
+> 2025-11-01-preview renames the 2025-08-01-preview "knowledge agent" to "knowledge base." This is a breaking change. We recommend [migrating existing code](../../agentic-retrieval-how-to-migrate.md) to the new APIs as soon as possible.
 
 ## Prerequisites
 
@@ -35,9 +35,6 @@ After you create a knowledge base, you can update its properties at any time. If
 
 + The latest preview version of the [`azure-search-documents` client library](https://pypi.org/project/azure-search-documents/11.7.0b2/) for Python.
 
-> [!NOTE]
-> Although you can use the Azure portal to create knowledge bases, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](../../agentic-retrieval-how-to-migrate.md).
-
 ### Supported models
 
 Use one of the following LLMs from Azure OpenAI or an equivalent open-source model. For deployment instructions, see [Deploy Azure OpenAI models with Microsoft Foundry](/azure/ai-foundry/how-to/deploy-models-openai).

@@ -21,7 +21,7 @@ A knowledge base specifies:
 After you create a knowledge base, you can update its properties at any time. If the knowledge base is in use, updates take effect on the next retrieval.
 
 > [!IMPORTANT]
-> 2025-11-01-preview renames the 2025-08-01-preview *knowledge agent* to *knowledge base*. This is a breaking change. We recommend [migrating existing code](../../agentic-retrieval-how-to-migrate.md) to the new APIs as soon as possible.
+> 2025-11-01-preview renames the 2025-08-01-preview "knowledge agent" to "knowledge base." This is a breaking change. We recommend [migrating existing code](../../agentic-retrieval-how-to-migrate.md) to the new APIs as soon as possible.
 
 ## Prerequisites
 
@@ -35,9 +35,6 @@ After you create a knowledge base, you can update its properties at any time. If
 
 + The latest preview version of the [`Azure.Search.Documents` client library](https://www.nuget.org/packages/Azure.Search.Documents/11.8.0-beta.1) for the .NET SDK.
 
-> [!NOTE]
-> Although you can use the Azure portal to create knowledge bases, the portal uses the 2025-08-01-preview, which uses the previous "knowledge agent" terminology and doesn't support all 2025-11-01-preview features. For help with breaking changes, see [Migrate your agentic retrieval code](../../agentic-retrieval-how-to-migrate.md).
-
 ### Supported models
 
 Use one of the following LLMs from Azure OpenAI or an equivalent open-source model. For deployment instructions, see [Deploy Azure OpenAI models with Microsoft Foundry](/azure/ai-foundry/how-to/deploy-models-openai).

@@ -25,7 +25,7 @@ Preview features are removed from this list if they're retired or transition to
 
 | Feature | Description | Availability |
 |--|--|--|
-| [**Agentic retrieval**](agentic-retrieval-overview.md) | Create a conversational search experience powered by large language models (LLMs). Agentic retrieval breaks down complex user queries into subqueries, runs the subqueries simultaneously, reranks the results for relevance, and either extracts grounding data or synthesizes answers into natural language. To get started, see [Quickstart: Agentic retrieval](search-get-started-agentic-retrieval.md).<p>The pipeline involves one or more [knowledge sources](agentic-knowledge-source-overview.md#supported-knowledge-sources) within a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), whose [response payload](agentic-retrieval-how-to-retrieve.md) provides full transparency into the query plan and reference data.<p>Knowledge sources and knowledge bases created in the Azure portal use the 2025-08-01-preview schema and aren't compatible with the latest 2025-11-01-preview. To get started, see [Quickstart: Agentic retrieval in the Azure portal](get-started-portal-agentic-retrieval.md). | [Knowledge Sources (preview)](/rest/api/searchservice/knowledge-sources?view=rest-searchservice-2025-11-01-preview&preserve-view=true), [Knowledge bases (preview)](/rest/api/searchservice/knowledge-bases?view=rest-searchservice-2025-11-01-preview&preserve-view=true), [Knowledge Retrieval (preview)](/rest/api/searchservice/knowledge-retrieval?view=rest-searchservice-2025-11-01-preview&preserve-view=true), and the Azure portal |
+| [**Agentic retrieval**](agentic-retrieval-overview.md) | Create a conversational search experience powered by large language models (LLMs). Agentic retrieval breaks down complex user queries into subqueries, runs the subqueries simultaneously, reranks the results for relevance, and either extracts grounding data or synthesizes answers into natural language.<p>The pipeline involves one or more [knowledge sources](agentic-knowledge-source-overview.md#supported-knowledge-sources) within a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), whose [response payload](agentic-retrieval-how-to-retrieve.md) provides full transparency into the query plan and reference data.<p>To get started, see [Quickstart: Use agentic retrieval in Azure AI Search](search-get-started-agentic-retrieval.md) (programmatic) or [Quickstart: Use agentic retrieval in the Azure portal](get-started-portal-agentic-retrieval.md). | [Knowledge Sources (preview)](/rest/api/searchservice/knowledge-sources?view=rest-searchservice-2025-11-01-preview&preserve-view=true), [Knowledge bases (preview)](/rest/api/searchservice/knowledge-bases?view=rest-searchservice-2025-11-01-preview&preserve-view=true), [Knowledge Retrieval (preview)](/rest/api/searchservice/knowledge-retrieval?view=rest-searchservice-2025-11-01-preview&preserve-view=true), and the Azure portal |
 | [**Purview index configuration**](search-indexer-sensitivity-labels.md) | Apply Microsoft Purview classifications and sensitivity labels to indexed content based on source metadata for enhanced data governance. | [Create or Update Index (preview)](/rest/api/searchservice/indexes/create-or-update?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |
 | [**Scoring function aggregation**](index-add-scoring-profiles.md#example-function-aggregation) | Combine and aggregate multiple scoring functions, enabling more sophisticated relevance customization and weighted signal combination. | [Create or Update Index (preview)](/rest/api/searchservice/indexes/create-or-update?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |
 | [**Facet aggregations**](search-faceted-navigation-examples.md#facet-aggregation-example) | Use sum, count, minimum, maximum, and other aggregate functions to provide enhanced analytics in faceted search experiences. | [Search Documents (preview)](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |

@@ -79,7 +79,7 @@ As a best practice, use [`Group` sets](search-indexer-access-control-lists-and-r
 
 [Create an index](search-how-to-create-search-index.md#create-an-index) that contains fields for content and [permission metadata](search-indexer-access-control-lists-and-role-based-access.md#create-permission-fields-in-the-index).
 
-Be sure to use the [latest preview REST API](/rest/api/searchservice/operation-groups?view=rest-searchservice-2025-11-01-preview&preserve-view=true) or a prerelease Azure SDK that provides equivalent functionality. The permission filter properties are only available in the preview APIs.
+Be sure to use the [latest preview REST API](/rest/api/searchservice/operation-groups?view=rest-searchservice-2025-11-01-preview&preserve-view=true) or a preview Azure SDK package that provides equivalent functionality. The permission filter properties are only available in the preview APIs.
 
 For demo purposes, the permission field has `retrievable` enabled so that you can check the values from the index. In a production environment, you should disable `retrievable` to avoid leaking sensitive information.
 

@@ -4,7 +4,7 @@ description: Announcements of new and enhanced features, including a service ren
 author: haileytap
 ms.author: haileytapia
 manager: nitinme
-ms.date: 11/18/2025
+ms.date: 12/18/2025
 ms.service: azure-ai-search
 ms.topic: overview
 ms.custom:
@@ -20,6 +20,12 @@ Learn about the latest updates to Azure AI Search functionality, docs, and sampl
 > [!NOTE]
 > Preview features are announced here, but we also maintain a [preview features list](search-api-preview.md) so you can find them in one place.
 
+## December 2025
+
+| Item | Description |
+|--|--|
+| [2025-11-01-preview portal migration for agentic retrieval](get-started-portal-agentic-retrieval.md) | [Knowledge bases](agentic-retrieval-how-to-create-knowledge-base.md) and [knowledge sources](agentic-knowledge-source-overview.md) in the Azure portal have been updated to use the 2025-11-01-preview REST APIs instead of the 2025-08-01-preview. Portal-created knowledge bases now support the [retrieval reasoning effort](agentic-retrieval-how-to-set-retrieval-reasoning-effort.md), and query-time properties (maximum runtime and maximum output size) have been removed from the UI. The portal continues to support search index and blob knowledge sources only; other knowledge source types must be created programmatically.<p>If you previously created knowledge bases or knowledge sources in the portal, those objects still use the 2025-08-01-preview schema. For help with breaking changes, see [Migrate your agentic retrieval code](agentic-retrieval-how-to-migrate.md). |
+
 ## November 2025
 
 | Item | Description |