@@ -4,14 +4,14 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: include
-ms.date: 11/18/2025
+ms.date: 12/11/2025
 ms.author: lajanuar
 ---
 [Reference documentation](/dotnet/api/azure.ai.textanalytics?preserve-view=true&view=azure-dotnet) | [More samples](https://github.com/Azure/azure-sdk-for-net/tree/master/sdk/textanalytics/Azure.AI.TextAnalytics/samples) | [Package (NuGet)](https://www.nuget.org/packages/Azure.AI.TextAnalytics/5.2.0) | [Library source code](https://github.com/Azure/azure-sdk-for-net/tree/master/sdk/textanalytics/Azure.AI.TextAnalytics)
 
 Use this quickstart to create an entity linking application with the client library for .NET. In the following example, you create a C# application that can identify and disambiguate entities found in text.
 
-[!INCLUDE [Use Language Studio](../../../includes/use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../../../includes/use-microsoft-foundry.md)]
 
 ## Prerequisites
 

@@ -10,4 +10,4 @@
 ms.custom: include, ignite-2024
 ---
 > [!TIP]
-> You can use [**Microsoft Foundry**](../../../ai-foundry/what-is-azure-ai-foundry.md) to try summarization without needing to write code. 
+> You can use [**Microsoft Foundry**](https://ai.azure.com/) to try Azure Language features without needing to write code. 

@@ -10,7 +10,7 @@ ms.author: lajanuar
 
 Use this quickstart to create a language detection application with the client library for Python. In the following example, you create a Python application that can identify the language a text sample was written in.
 
-[!INCLUDE [Use Language Studio](../../../includes/use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../../../includes/use-microsoft-foundry.md)]
 
 
 ## Prerequisites

@@ -10,7 +10,7 @@ ms.author: lajanuar
 
 Use this quickstart to create a Named Entity Recognition (NER) application with the client library for .NET. In the following example, you will create a C# application that can identify [recognized entities](../../concepts/named-entity-categories.md) in text.
 
-[!INCLUDE [Use Language Studio](../../../includes/use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../../../includes/use-microsoft-foundry.md)]
 
 ## Prerequisites
 

@@ -15,7 +15,7 @@ ms.custom: language-service-orchestration
 
 Orchestration workflow is one of the features offered by [Azure Language in Foundry Tools](../overview.md). It is a cloud-based API service that applies machine-learning intelligence to enable you to build orchestration models to connect [Conversational Language Understanding (CLU)](../conversational-language-understanding/overview.md), [Question Answering](../question-answering/overview.md) projects and [LUIS](../../luis/what-is-luis.md) applications.
 By creating an orchestration workflow, developers can iteratively tag utterances, train and evaluate model performance before making it available for consumption. 
-To simplify building and customizing your model, the service offers a custom web portal that can be accessed through the [Language studio](https://aka.ms/languageStudio). You can easily get started with the service by following the steps in this [quickstart](quickstart.md). 
+To simplify building and customizing your model, the service offers a custom playground that can be accessed through the [Microsoft Foundry](https://ai.azure.com/). You can easily get started with the service by following the steps in this [quickstart](quickstart.md). 
 
 
 This documentation contains the following article types:

@@ -11,7 +11,7 @@ ms.author: lajanuar
 ---
 # What is Azure Language in Foundry Tools?
 
-Azure Language is a cloud-based service that provides Natural Language Processing (NLP) features for understanding and analyzing text. Use this service to help build intelligent applications using the web-based Language Studio, REST APIs, and client libraries.  For AI agent development, the service capabilities are also available as tools in Azure Language [MCP server](#azure-language-mcp-server-), which is available both as a remote server in the **Microsoft Foundry Tool Catalog** and as a local server for self-hosted environments.
+Azure Language is a cloud-based service that provides Natural Language Processing (NLP) features for understanding and analyzing text. Use this service to help build intelligent applications using the web-based Microsoft Foundry, REST APIs, and client libraries. For AI agent development, the service capabilities are also available as tools in Azure Language [MCP server](#azure-language-mcp-server-), which is available both as a remote server in the **Microsoft Foundry Tool Catalog** and as a local server for self-hosted environments.
 
 ## Available tools
 
@@ -61,7 +61,7 @@ The Language also provides several new features as well, which can either be:
 
 :::row:::
    :::column span="":::
-      :::image type="content" source="media/overview/named-entity-recognition.png" alt-text="A screenshot of named entity recognition in Foundry."lightbox="media/overview/named-entity-recognition.png":::
+      :::image type="content" source="media/overview/named-entity-recognition.png" alt-text="A screenshot of named entity recognition in Foundry." lightbox="media/overview/named-entity-recognition.png":::
    :::column-end:::
    :::column span="":::
       [Named entity recognition](./named-entity-recognition/overview.md) identifies different entries in text and categorizes them into predefined types.

@@ -2,7 +2,7 @@
 author: laujan
 ms.author: lajanuar
 manager: nitinme
-ms.date: 11/18/2025
+ms.date: 12/11/2025
 ms.service: azure-ai-language
 ms.topic: include
 ms.custom:
@@ -14,7 +14,7 @@ ms.custom:
 
 Use this quickstart to create a Personally Identifiable Information (PII) detection application with the client library for .NET. In the following example, you create a C# application that can identify [recognized sensitive information](../../concepts/entity-categories.md) in text.
 
-[!INCLUDE [Use Language Studio](../use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../use-microsoft-foundry.md)]
 
 
 ## Prerequisites

@@ -14,7 +14,7 @@ ms.custom:
 
 Use this quickstart to create a Personally Identifiable Information (PII) detection application with the client library for Java. In the following example, you create a Java application that can identify [recognized sensitive information](../../concepts/entity-categories.md) in text.
 
-[!INCLUDE [Use Language Studio](../use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../use-microsoft-foundry.md)]
 
 ## Prerequisites
 

@@ -1,10 +0,0 @@
----
-author: laujan
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
-ms.custom: include, ignite-2024
----
-> [!TIP]
-> You can use [**Microsoft Foundry**](../../../../ai-foundry/what-is-azure-ai-foundry.md) to try summarization without needing to write code. 

@@ -0,0 +1,10 @@
+---
+author: laujan
+ms.service: azure-ai-language
+ms.topic: include
+ms.date: 12/11/2025
+ms.author: lajanuar
+ms.custom: include, ignite-2024
+---
+> [!TIP]
+> You can use [**Microsoft Foundry**](https://ai.azure.com/) to try Azure Language features without needing to write code.

@@ -19,7 +19,7 @@ ms.custom: language-service-pii
 Azure Language in Foundry Tools Personally Identifiable Information (PII) detection is a feature offered by [Azure Language](../overview.md). The PII detection service is a cloud-based API that utilizes machine learning and AI algorithms to help you develop intelligent applications with advanced natural language understanding. Azure Language PII detection uses Named Entity Recognition (NER) to **identify and redact** sensitive information from input data. The service classifies sensitive personal data into predefined categories. These categories include phone numbers, email addresses, and identification documents. This classification helps to efficiently detect and eliminate such information.
 
 > [!TIP]
-> Try PII detection [in Microsoft Foundry portal](https://ai.azure.com/explore/language). There you can [utilize a currently existing Language Studio resource or create a new Foundry resource](../../../ai-services/connect-services-ai-foundry-portal.md).
+> Try PII detection [in Microsoft Foundry portal](https://ai.azure.com/). There you can [utilize a currently existing Language Studio resource or create a new Foundry resource](../../../ai-services/connect-services-ai-foundry-portal.md).
 
 ## What's new
 

@@ -2,10 +2,10 @@
 title: Azure resources - custom question answering
 description: Question answering uses several Azure sources, each with a different purpose. Understanding how they're used individually allows you to plan for and select the correct pricing tier or know when to change your pricing tier. Understanding how they're used in combination allows you to find and fix problems when they occur.
 ms.service: azure-ai-language
-ms.topic: conceptual
+ms.topic: get-started
 author: laujan
 ms.author: lajanuar
-ms.date: 11/18/2025
+ms.date: 12/11/2025
 ms.custom: language-service-question-answering
 ---
 # Azure resources for custom question answering
@@ -37,7 +37,7 @@ Typically there are three parameters you need to consider:
 
 * **Size and the number of projects**: Choose the appropriate [Azure search SKU](https://azure.microsoft.com/pricing/details/search/) for your scenario. Typically, you decide the number of projects you need based on number of different subject domains. One subject domain (for a single language) should be in one project.
 
-    With custom question answering, you have a choice to set up your language resource in a single language or multiple languages. You can make this selection when you create your first project in the [Language Studio](https://language.azure.com/).
+    With custom question answering, you have a choice to set up your language resource in a single language or multiple languages.
 
     > [!IMPORTANT]
     > You can publish N-1 projects  with a single language resource or N-2 projects with multiple language resources in a single tier. The `N` notation is the maximum indexes allowed in the tier.

@@ -4,8 +4,8 @@ description: Use these best practices to improve your project and provide better
 ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
-ms.topic: conceptual
-ms.date: 11/18/2025
+ms.topic: best-practice
+ms.date: 12/12/2025
 ms.custom: language-service-question-answering
 ---
 # Custom question answering best practices
@@ -189,7 +189,7 @@ Custom question answering allows users to collaborate on a project. Users need a
 
 ## Active learning
 
-[Active learning](../tutorials/active-learning.md) does the best job of suggesting alternative questions when it has a wide range of quality and quantity of user-based queries. It's important to allow client-applications' user queries to participate in the active learning feedback loop without censorship. Once questions are suggested in Language Studio, you can review and accept or reject those suggestions.
+[Active learning](../tutorials/active-learning.md) does the best job of suggesting alternative questions when it has a wide range of quality and quantity of user-based queries. It's important to allow client-applications' user queries to participate in the active learning feedback loop without censorship. Once questions are suggested you can review and accept or reject those suggestions.
 
 ## Next steps
 

@@ -4,9 +4,10 @@ description: Custom question answering has meta-limits for parts of the knowledg
 ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
-ms.topic: conceptual
-ms.date: 11/18/2025
+ms.topic: limits-and-quotas
+ms.date: 12/11/2025
 ---
+
 # Project limits and boundaries
 
 The following custom question answering limits are a combination of the [Azure AI Search pricing tier limits](/azure/search/search-limits-quotas-capacity) and custom question answering limits. Both sets of limits affect how many projects you can create per resource and how large each project can grow.
@@ -17,8 +18,7 @@ The maximum number of projects is based on [Azure AI Search tier limits](/azure/
 
 Choose the appropriate [Azure search SKU](https://azure.microsoft.com/pricing/details/search/) for your scenario. Typically, you decide the number of projects you need based on number of different subject domains. One subject domain (for a single language) should be in one project.
 
-With custom question answering, you have a choice to set up your language resource in a single language or multiple languages. You can make this selection when you create your first project in the [Language Studio](https://language.azure.com/).
-
+With custom question answering, you have a choice to set up your language resource in a single language or multiple languages. 
   > [!IMPORTANT]
   > You can publish N-1 projects with a single language resource or N-2 projects with multiple language resources in a single tier. The `N` notation is the maximum indexes allowed in the tier.
   > Also check the maximum size and the number of documents allowed per tier.

@@ -4,9 +4,10 @@ description: Learn how to plan your custom question answering app. Understand ho
 ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
-ms.topic: conceptual
-ms.date: 11/18/2025
+ms.topic: get-started
+ms.date: 12/15/2025
 ---
+
 # Plan your custom question answering app
 
 To plan your custom question answering app, you need to understand how custom question answering works and interacts with other Azure services. You should also have a solid grasp of project concepts.
@@ -26,17 +27,17 @@ Custom question answering throughput is currently capped at 10 text records per
 
 ### Language resource
 
-A single language resource with the custom question answering feature enabled can host more than one project. The number of projects is determined by the Azure AI Search pricing tier's quantity of supported indexes. Learn more about the [relationship of indexes to projects](azure-resources.md#index-usage).
+A single language resource with the custom question answering feature enabled can host more than one project. The number of projects is determined via the Azure AI Search pricing tier's quantity of supported indexes. Learn more about the [relationship of indexes to projects](azure-resources.md#index-usage).
 
 ### Project size and throughput
 
-When you build a real app, plan sufficient resources for the size of your project and for your expected query prediction requests.
+When you build a real app, plan sufficient resources for the size of your project and your expected query prediction requests.
 
-A project size is controlled by the:
+Project size control factors:
 * [Azure AI Search resource](/azure/search/search-limits-quotas-capacity) pricing tier limits
 * [Custom question answering limits](./limits.md)
 
-The project query prediction request is controlled by the web app plan and web app. Refer to [recommended settings](azure-resources.md#recommended-settings) to plan your pricing tier.
+The project query prediction request is controlled via the web app plan and web app. Refer to [recommended settings](azure-resources.md#recommended-settings) to plan your pricing tier.
 
 ### Understand the impact of resource selection
 
@@ -52,15 +53,15 @@ A project is directly tied its language resource. It holds the question and answ
 
 ### Language considerations
 
-You can now have projects in different languages within the same language resource where the custom question answering feature is enabled. When you create the first project, you can choose whether you want to use the resource for projects in a single language that will apply to all subsequent projects or make a language selection each time a project is created.
+You can now have projects in different languages within the same language resource where the custom question answering feature is enabled. When you create your first project, you can decide whether to set a single language for all future projects or to select a language each time you start a new one. This choice determines if the resource applies to projects in one language or allow for language selection with each new project.
 
 ### Ingest data sources
 
 Custom question answering also supports unstructured content. You can upload a file that has unstructured content.
 
-Currently we do not support URLs for unstructured content.
+Currently we don't support URLs for unstructured content.
 
-The ingestion process converts supported content types to markdown. All further editing of the *answer* is done with markdown. After you create a project, you can edit QnA pairs in Language Studio with rich text authoring.
+The ingestion process converts supported content types to markdown. All further editing of the *answer* is done with markdown. After you create a project, you can edit QnA pairs with rich text authoring.
 
 ### Data format considerations
 
@@ -70,19 +71,19 @@ Because the final format of a QnA pair is markdown, it's important to understand
 
 Add a bot personality to your project with [chit-chat](../how-to/chit-chat.md). This personality comes through with answers provided in a certain conversational tone such as *professional* and *friendly*. This chit-chat is provided as a conversational set, which you have total control to add, edit, and remove.
 
-A bot personality is recommended if your bot connects to your project. You can choose to use chit-chat in your project even if you also connect to other services, but you should review how the bot service interacts to know if that is the correct architectural design for your use.
+A bot personality is recommended if your bot connects to your project. You can include chit-chat in your project even if you're connecting to other services. However, it's important to review how the bot service interacts with these integrations to ensure this approach fits your overall architectural design.
 
 ### Conversation flow with a project
 
 Conversation flow usually begins with a salutation from a user, such as `Hi` or `Hello`. Your project can answer with a general answer, such as `Hi, how can I help you`, and it can also provide a selection of follow-up prompts to continue the conversation.
 
-You should design your conversational flow with a loop in mind so that a user knows how to use your bot and isn't abandoned by the bot in the conversation. [Follow-up prompts](../tutorials/guided-conversations.md) provide linking between QnA pairs, which allow for the conversational flow.
+Design your conversational flow so that users always know how to interact with your bot and are never left without guidance. By including a loop or clear navigation, you ensure users aren't abandoned during the conversation. [Follow-up prompts](../tutorials/guided-conversations.md) provide linking between QnA pairs, which allow for the conversational flow.
 
 ### Authoring with collaborators
 
 Collaborators may be other developers who share the full development stack of the project application or may be limited to just authoring the project.
 
-project authoring supports several role-based access permissions you apply in the Azure portal to limit the scope of a collaborator's abilities.
+Project authoring supports several role-based access permissions you apply in the Azure portal to limit the scope of a collaborator's abilities.
 
 ## Integration with client applications
 
@@ -94,7 +95,7 @@ To authenticate a client request correctly, the client application must send the
 
 Conversation flow in a client application, such as an Azure bot, may require functionality before and after interacting with the project.
 
-Does your client application support conversation flow, either by providing alternate means to handle follow-up prompts or including chit-chit? If so, design these early and make sure the client application query is handled correctly by another service or when sent to your project.
+Does your client application support conversation flow, either by providing alternate means to handle follow-up prompts or including chit-chit? If so, design these features early and make sure the client application query is handled correctly via another service or when sent to your project.
 
 ### Active learning from a client application
 
@@ -104,7 +105,7 @@ Custom question answering uses _active learning_ to improve your project by sugg
 
 If your project doesn't find an answer, it returns the _default answer_. This answer is configurable on the **Settings** page.
 
-This default answer is different from the Azure bot default answer. You configure the default answer for your Azure bot in the Azure portal as part of configuration settings. It's returned when the score threshold isn't met.
+This default answer is different from the Azure bot default answer. You configure the default answer for your Azure bot in the Azure portal as part of configuration settings. The default answer is then returned when the score threshold isn't met.
 
 ## Prediction
 
@@ -140,7 +141,7 @@ Each pair can contain:
 
 Developing a project to insert into a DevOps pipeline requires that the project is isolated during batch testing.
 
-A project shares the Azure AI Search index with all other projects on the language resource. While the project is isolated by partition, sharing the index can cause a difference in the score when compared to the published project.
+A project shares the Azure AI Search index with all other projects on the language resource. While the project is isolated via a partition, sharing the index can cause a difference in the score when compared to the published project.
 
 To have the _same score_ on the `test` and `production` projects, isolate a language resource to a single project. In this architecture, the resource only needs to live as long as the isolated batch test.
 

@@ -2,12 +2,13 @@
 title: Precise answering using answer span detection - custom question answering
 description: Understand Precise answering feature available in custom question answering.
 ms.service: azure-ai-language
-ms.topic: conceptual
+ms.topic: feature-guide
 author: laujan
 ms.author: lajanuar
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.custom: language-service-question-answering
 ---
+
 # Precise answering
 
 The precise answering feature introduced, allows you to get the precise short answer from the best candidate answer passage present in the project for any user query. This feature uses a deep learning model at runtime, which understands the intent of the user query and detects the precise short answer from the answer passage, if there is a short answer present as a fact in the answer passage.
@@ -16,7 +17,7 @@ This feature is beneficial for both content developers as well as end users. Now
 
 ## Precise answering via the portal
 
-In the [Language Studio portal](https://aka.ms/languageStudio), when you open the test pane, you can see an option to **Include short answer response** on the top above show advanced options.
+When you open the test pane, you can see an option to **Include short answer response** on the top above show advanced options.
 
 When you enter a query in the test pane, you can see a short-answer along with the answer passage, if there is a short answer present in the answer passage.
 

@@ -4,8 +4,8 @@ description: Custom question answering learns best in an iterative cycle of mode
 ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
-ms.topic: conceptual
-ms.date: 11/18/2025
+ms.topic: lifecycle
+ms.date: 12/15/2025
 ---
 # Custom question answering project lifecycle
 
@@ -23,7 +23,7 @@ Learn how to [create a project](../how-to/create-test-deploy.md).
 
 ## Testing and updating your project
 
-The project is ready for testing once it is populated with content, either editorially or through automatic extraction. Interactive testing can be done in Language Studio, in the custom question answering menu through the **Test** panel. You enter common user queries. Then you verify that the responses returned with both the correct response and a sufficient confidence score.
+The project is ready for testing once it is populated with content, either editorially or through automatic extraction. Then you verify that the responses returned with both the correct response and a sufficient confidence score.
 
 * **To fix low confidence scores**: add alternate questions.
 * **When a query incorrectly returns the [default response](../How-to/change-default-answer.md)**: add new answers to the correct question.
@@ -46,7 +46,7 @@ Based on what you learn from your analytics, make appropriate updates to your pr
 
 ## Version control for data in your project
 
-Version control for data is provided through the import/export features on the project page in the custom question answering section of Language Studio.
+Version control for data is provided through the import/export features on your project page.
 
 You can back up a project by exporting the project, in either `.tsv` or `.xls` format. Once exported, include this file as part of your regular source control check.
 
@@ -58,9 +58,6 @@ A project is the repository of questions and answer sets created, maintained, an
 
 A project has two states: *test* and *published*.
 
-### Test project
-
-The *test project* is the version currently edited and saved. The test version has been tested for accuracy, and for completeness of responses. Changes made to the test project don't affect the end user of your application or chat bot. The test project is known as `test` in the HTTP request. The `test` knowledge is available with Language Studio's interactive **Test** pane.
 
 ### Production project
 

@@ -6,7 +6,7 @@ ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
 ms.topic: how-to
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ---
 # Authoring API
 
@@ -26,8 +26,8 @@ To create a project programmatically:
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively, you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`. If the prior example was your endpoint in the following code sample, you would only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively, you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`. If the prior example was your endpoint in the following code sample, you would only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `NEW-PROJECT-NAME` | The name for your new custom question answering project.|
 
 You can also adjust more values, such as the project language. Another option is to set the default answer that is provided when no response meets or exceeds the confidence threshold. In addition, you can specify whether this language resource supports multiple languages.
@@ -74,8 +74,8 @@ To delete a project programmatically:
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`. If the prior example was your endpoint in the following code sample, you would only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`. If the prior example was your endpoint in the following code sample, you would only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to delete.|
 
 ### Example query
@@ -122,8 +122,8 @@ To check on the status of your delete project request:
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively, you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to check on the deployment status for.|
 | `JOB-ID` | When you delete a project programmatically, a `JOB-ID` is generated as part of the `operation-location` response header to the deletion request. The `JOB-ID` is the guid at the end of the `operation-location`. For example: `operation-location: https://southcentralus.cognitiveservices.azure.com:443/language/query-knowledgebases/projects/sample-proj1/deletion-jobs/{THIS GUID IS YOUR JOB ID}` |
 
@@ -151,8 +151,8 @@ To retrieve information about a given project, update the following values in th
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to retrieve information about.|
 
 ### Example query
@@ -189,8 +189,8 @@ To retrieve question answer pairs and related information for a given project, u
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to retrieve all the question answer pairs for.|
 
 ### Example query
@@ -259,8 +259,8 @@ To retrieve the sources and related information for a given project, update the
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to retrieve all the source information for.|
 
 ### Example query
@@ -302,8 +302,8 @@ To retrieve synonyms and related information for a given project, update the fol
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to retrieve synonym information for.|
 
 ### Example query
@@ -345,8 +345,8 @@ To deploy a project to production, update the following values in the query:
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to deploy to production.|
 
 ### Example query
@@ -374,8 +374,8 @@ date: Tue, 23 Nov 2021 20:35:00 GMT
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to check on the deployment status for.|
 | `JOB-ID` | When you deploy a project programmatically, a `JOB-ID` is generated as part of the `operation-location` response header to the deployment request. The `JOB-ID` is the guid at the end of the `operation-location`. For example: `operation-location: https://southcentralus.cognitiveservices.azure.com:443/language/query-knowledgebases/projects/sample-proj1/deployments/production/jobs/{THIS GUID IS YOUR JOB ID}` |
 
@@ -407,8 +407,8 @@ curl -X GET -H "Ocp-Apim-Subscription-Key: {API-KEY}" -H "Content-Type: applicat
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to export.|
 
 ### Example query
@@ -434,8 +434,8 @@ date: Tue, 23 Nov 2021 21:24:03 GMT
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to check on the export status for.|
 | `JOB-ID` | When you export a project programmatically, a `JOB-ID` is generated as part of the `operation-location` response header to the export request. The `JOB-ID` is the guid at the end of the `operation-location`. For example: `operation-location: https://southcentralus.cognitiveservices.azure.com/language/query-knowledgebases/projects/sample-proj1/export/jobs/{THIS GUID IS YOUR JOB ID}` |
 
@@ -464,8 +464,8 @@ If you try to access the resultUrl directly, you get a 404 error. You must appen
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you would only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you would only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to be the destination for the import.|
 | `FILE-URI-PATH` | When you export a project programmatically, and then check the status the export a `resultUrl` is generated as part of the response. For example: `"resultUrl": "https://southcentralus.cognitiveservices.azure.com:443/language/query-knowledgebases/projects/sample-proj1/export/jobs/{JOB-ID_GUID}/result"` you can use the resultUrl with the API version appended as a source file to import a project from: `https://southcentralus.cognitiveservices.azure.com:443/language/query-knowledgebases/projects/sample-proj1/export/jobs/{JOB-ID_GUID}/result?api-version=2021-10-01`.|
 
@@ -496,8 +496,8 @@ date: Wed, 24 Nov 2021 00:35:11 GMT
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to be the destination for the import.|
 | `JOB-ID` | When you import a project programmatically, a `JOB-ID` is generated as part of the `operation-location` response header to the export request. The `JOB-ID` is the GUID at the end of the `operation-location`. For example: `operation-location: https://southcentralus.cognitiveservices.azure.com/language/query-knowledgebases/projects/sample-proj1/import/jobs/{THIS GUID IS YOUR JOB ID}` |
 
@@ -524,8 +524,8 @@ curl -X GET -H "Ocp-Apim-Subscription-Key: {API-KEY}" -H "Content-Type: applicat
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to generate a deployment list for.|
 
 ### Example query
@@ -551,8 +551,8 @@ Retrieve a list of all question answering projects your account has access to.
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 
 ### Example query
 
@@ -587,8 +587,8 @@ In this example, we add a new source to an existing project. You can also replac
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project where you would like to update sources.|
 |`METHOD`| PATCH |
 
@@ -627,8 +627,8 @@ date: Wed, 24 Nov 2021 02:47:53 GMT
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively, you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to be the destination for the import.|
 | `JOB-ID` | When you update a source programmatically, a `JOB-ID` is generated as part of the `operation-location` response header to the update source request. The `JOB-ID` is the GUID at the end of the `operation-location`. For example: `operation-location: https://southcentralus.cognitiveservices.azure.com/language/query-knowledgebases/projects/sample-proj1/sources/jobs/{THIS GUID IS YOUR JOB ID}` |
 
@@ -658,8 +658,8 @@ In this example, we add a question answer pair to an existing source. You can al
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to be the destination for the import.|
 
 ```bash
@@ -702,8 +702,8 @@ date: Wed, 24 Nov 2021 03:16:01 GMT
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to be the destination for the question answer pairs updates.|
 | `JOB-ID` | When you update a question answer pair programmatically, a `JOB-ID` is generated as part of the `operation-location` response header to the update request. The `JOB-ID` is the GUID at the end of the `operation-location`. For example: `operation-location: https://southcentralus.cognitiveservices.azure.com/language/query-knowledgebases/projects/sample-proj1/qnas/jobs/{THIS GUID IS YOUR JOB ID}` |
 
@@ -728,8 +728,8 @@ curl -X GET -H "Ocp-Apim-Subscription-Key: {API-KEY}" -H "Content-Type: applicat
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to add synonyms.|
 
 ### Example query
@@ -774,8 +774,8 @@ date: Wed, 24 Nov 2021 03:59:09 GMT
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region specific portion of `southcentral`. The rest of the endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project you would like to be the destination for the active learning feedback updates.|
 
 ### Example query

@@ -3,7 +3,7 @@ title: Get default answer - custom question answering
 description: The default answer is returned when there is no match to the question. You might want to change the default answer from the standard default answer in custom question answering.
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 author: laujan
 ms.author: lajanuar
 ms.custom: language-service-question-answering
@@ -26,17 +26,6 @@ For a client application, such as a bot with the [Azure AI Bot Service](/azure/b
 * Use your project's setting
 * Use different text in the client application to distinguish when an answer is returned but doesn't meet the score threshold. This text can either be static text stored in code, or can be stored in the client application's settings list.
 
-## Change default answer in Language Studio
-
-The project default answer is returned when no answer is returned from custom question answering.
-
-1. Sign in to the [Language Studio](https://language.azure.com). Go to custom question answering and select your project from the list.
-1. Select **Settings** from the left pane.
-1. Change the value of **Default answer when no answer found** > Select **Save**.
-
-> [!div class="mx-imgBorder"]
-> ![Screenshot of project settings with red box around the default answer](../media/change-default-answer/settings.png)
-
 ## Next steps
 
 * [Create a project](manage-knowledge-base.md)

@@ -5,7 +5,7 @@ ms.service: azure-ai-language
 ms.topic: how-to
 author: laujan
 ms.author: lajanuar
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.custom: language-service-question-answering, mode-other
 ---
 # Create, test, and deploy: CQA knowledge base

@@ -6,7 +6,7 @@ author: erindormier
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.author: egeaney
 ms.custom: language-service-question-answering
 ---
@@ -47,7 +47,7 @@ Customer-managed keys are available in all Azure Search regions.
 
 ## Encryption of data in transit
 
-Language Studio runs in the user's browser. Every action triggers a direct call to the respective Foundry Tools API. Hence, custom question answering is compliant for data in transit.
+Every action triggers a direct call to the respective Foundry Tools API. Hence, custom question answering is compliant for data in transit.
 
 ## Next steps
 

@@ -6,7 +6,7 @@ ms.topic: how-to
 author: laujan
 ms.author: lajanuar
 recommendations: false
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ---
 # Export-import-refresh in custom question answering
 
@@ -21,51 +21,15 @@ You might want to create a copy of your custom question answering project or rel
 * An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn) before you begin.
 * A [language resource](https://aka.ms/create-language-resource) with the custom question answering feature enabled. Remember your Microsoft Entra ID, Subscription, language resource name you selected when you created the resource.
 
-## Export a project
-
-1. Sign in to the [Language Studio](https://language.azure.com/) with your Azure credentials.
-
-2. Scroll down to the **Answer questions** section and select **Open custom question answering**.
-
-3. Select the project you wish to export > Select **Export** > You can export the project as an **Excel** or **TSV** file.
-
-4. You're prompted to save your exported file locally as a zip file.
 
 ### Export a project programmatically
 
 To automate the export process, use the [export functionality of the authoring API](./authoring.md#export-project-metadata-and-assets)
 
-## Import a project
-
-1. Sign in to the [Language Studio](https://language.azure.com/) with your Azure credentials.
-
-2. Scroll down to the **Answer questions** section and select **Open custom question answering**.
-
-3. Select **Import** and specify the file type you selected for the export process. Either **Excel**, or **TSV**.
-
-4. Select Choose File and browse to the local zipped copy of your project that you exported previously.
-
-5. Provide a unique name for the project you're importing.
-
-6. Remember that a project that is only imported still needs to be deployed/published if you want it to be live.
-
 ### Import a project programmatically
 
 To automate the import process, use the [import functionality of the authoring API](./authoring.md#import-project)
 
-## Refresh source url
-
-1. Sign in to the [Language Studio](https://language.azure.com/) with your Azure credentials.
-
-2. Scroll down to the **Answer questions** section and select **Open custom question answering**.
-
-3. Select the project that contains the source you want to refresh > select manage sources.
-
-4. We recommend having a backup of your project/question answer pairs before running each refresh so that you can always roll back if needed.
-
-5. Select a URL-based source to refresh > Select **Refresh URL**.
-6. Only one URL can be refreshed at a time.
-
 ### Refresh a URL programmatically
 
 To automate the URL refresh process, use the [update sources functionality of the authoring API](./authoring.md#update-sources)
@@ -74,8 +38,8 @@ The update sources example in the [Authoring API docs](./authoring.md#update-sou
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region-specific portion of `southcentral`. The endpoint path is already present.|
-| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `ENDPOINT`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/` and you only need to add the region-specific portion of `southcentral`. The endpoint path is already present.|
+| `API-KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys allows for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `PROJECT-NAME` | The name of project where you would like to update sources.|
 
 ```bash
@@ -92,43 +56,6 @@ curl -X PATCH -H "Ocp-Apim-Subscription-Key: {API-KEY}" -H "Content-Type: applic
 ]'  -i 'https://{ENDPOINT}.cognitiveservices.azure.com/language/query-knowledgebases/projects/{PROJECT-NAME}/sources?api-version=2021-10-01'
 ```
 
-## Export questions and answers
-
-It's also possible to export/import a specific project of question and answers rather than the entire custom question answering project.
-
-1. Sign in to the [Language Studio](https://language.azure.com/) with your Azure credentials.
-
-2. Scroll down to the **Answer questions** section and select **Open custom question answering**.
-
-3. Select the project that contains the project question and answer pairs you want to export.
-
-4. Select **Edit project**.
-
-5. To the right of show columns are `...` an ellipsis button. > Select the `...` > a dropdown reveals the option to export/import questions and answers.
-
-    Depending on the size of your web browser, you may experience the UI differently. Smaller browsers see two separate ellipsis buttons.
-
-    > [!div class="mx-imgBorder"]
-    > ![Screenshot of selecting multiple UI ellipsis buttons to get to import/export question and answer pair option](../media/export-import-refresh/export-questions.png)
-
-## Import questions and answers
-
-It's also possible to export/import a specific project of question and answers rather than the entire custom question answering project.
-
-1. Sign in to the [Language Studio](https://language.azure.com/) with your Azure credentials.
-
-2. Scroll down to the **Answer questions** section and select **Open custom question answering**.
-
-3. Select the project that contains the project question and answer pairs you want to export.
-
-4. Select **Edit project**.
-
-5. To the right of show columns are `...` an ellipsis button. > Select the `...` > a dropdown reveals the option to export/import questions and answers.
-
-    Depending on the size of your web browser, you may experience the UI differently. Smaller browsers see two separate ellipsis buttons.
-
-    > [!div class="mx-imgBorder"]
-    > ![Screenshot of selecting multiple UI ellipsis buttons to get to import/export question and answer pair option](../media/export-import-refresh/export-questions.png)
 
 ## Next steps
 

@@ -5,7 +5,7 @@ ms.service: azure-ai-language
 ms.topic: how-to
 author: laujan
 ms.author: lajanuar
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.custom: language-service-question-answering
 ---
 #  Network isolation and private endpoints
@@ -55,10 +55,5 @@ This will establish a private endpoint connection between language resource and
 
 Follow these steps to restrict public access to custom question answering language resources. Protect a Foundry resource from public access by [configuring the virtual network](../../../cognitive-services-virtual-networks.md?tabs=portal).
 
-After you restrict access to a Foundry resource based on virtual network, to browse projects on Language Studio from your on-premises network or your local browser:
-- Grant access to [on-premises network](../../../cognitive-services-virtual-networks.md?tabs=portal#configure-access-from-on-premises-networks).
-- Grant access to your [local browser/machine](../../../cognitive-services-virtual-networks.md?tabs=portal#managing-ip-network-rules).
-- Add the **public IP address of the machine  under the Firewall** section of the **Networking** tab. By default `portal.azure.com` shows the current browsing machine's public IP (select this entry) and then select **Save**.
-
   > [!div class="mx-imgBorder"]
   > [![Screenshot of firewall and virtual networks configuration UI](../../../qnamaker/media/network-isolation/firewall.png)](../../../qnamaker/media/network-isolation/firewall.png#lightbox)

@@ -6,13 +6,13 @@ ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
 ms.topic: how-to
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ---
 # Use smart URL refresh with a project
 
-Custom question answering gives you the ability to refresh your source contents by getting the latest content from a source URL and updating the corresponding project with one click. The service will ingest content from the URL and either create, merge, or delete question-and-answer pairs in the project. 
+Custom question answering allows you to keep your source content up to date by retrieving the latest information from a source URL. With just one selection, you can update the corresponding project to reflect these changes. The service ingests content from the URL and either creates, merges, or deletes question-and-answer pairs in the project. 
 
-This functionality is provided to support scenarios where the content in the source URL changes frequently, such as the FAQ page of a product that's updated often. The service will refresh the source and update the project to the latest content while retaining any manual edits made previously.
+This functionality is provided to support scenarios where the content in the source URL changes frequently, such as product FAQ page updates. The service refreshes the source and update the project to the latest content while retaining any manual edits made previously.
 
 > [!NOTE]
 > This feature is only applicable to URL sources, and they must be refreshed individually, not in bulk. 
@@ -22,30 +22,26 @@ This functionality is provided to support scenarios where the content in the sou
 
 ## How it works
 
-If you have a project with a URL source that has changed, you can trigger a smart URL refresh to keep your project up to date. The service will scan the URL for updated content and generate QnA pairs. It will add any new QnA pairs to your project and also delete any pairs that have disappeared from the source (with exceptions—see below). It also merges old and new QnA pairs in some situations (see below).
+If you have a project with a URL source that changed, you can trigger a smart URL refresh to keep your project up to date. The service scans the URL for updated content and generates QnA pairs. It adds any new QnA pairs to your project and also delete any pairs that disappeared from the source (with exceptions—). It also merges old and new QnA pairs in some situations.
 
 > [!IMPORTANT]
 > Because smart URL refresh can involve deleting old content from your project, you might want to [create a backup](./export-import-refresh.md) of your project before you do any refresh operations.
 
-You can trigger a URL refresh in Language Studio by opening your project, selecting the source in the **Manage sources** list, and selecting **Refresh URL**.
-
-:::image type="content" source="../media/question-answering/refresh-url.png" alt-text="screenshot of language studio with refresh URL button highlighted.":::
-
-You can also trigger a refresh programmatically using the REST API. See the **[Update Sources](/rest/api/questionanswering/question-answering-projects/update-sources)** reference documentation for parameters and a sample request.
+You can trigger a refresh programmatically using the REST API. See the **[Update Sources](/rest/api/questionanswering/question-answering-projects/update-sources)** reference documentation for parameters and a sample request.
 
 ## Smart refresh behavior
 
 When the user refreshes content using this feature, the project of QnA pairs may be updated in the following ways:
 
 ### Delete old pair
 
-If the content of the URL is updated so that an existing QnA pair from the old content of the URL is no longer found in the source, that pair is deleted from the refreshed project. For example, if a QnA pair Q1A1 existed in the old project, but after refreshing, there's no A1 answer generated by the newly refreshed source, then the pair Q1A1 is considered outdated and is dropped from the project altogether.
+If the content at the source URL changes and an existing QnA pair from the previous version is no longer present, that pair is removed from the updated project. This process ensures that your refreshed project only contains QnA pairs that match the current source content. For example, if a QnA pair like Q1A1 existed in the previous version of the project, but after refreshing, the updated source no longer generates the A1 answer, that pair is considered outdated. As a result, Q1A1 is removed from the project entirely.
 
-However, if the old QnA pairs have been manually edited in the authoring portal, they won't be deleted.
+However, if the old QnA pairs are manually edited in the authoring portal, they aren't deleted.
 
 ### Add new pair
 
-If the content of the URL is updated in such a way that a new QnA pair exists which didn't exist in the old KB, then it's added to the KB. For example, if the service finds that a new answer A2 can be generated, then the QnA pair Q2A2 is inserted into the KB.
+If the URL has new content, and a new QnA pair appears in the old knowledge base, the new pair is added. This addition ensures your knowledge base always includes the latest information from the source. For example, if the service finds that a new answer A2 can be generated, then the QnA pair Q2A2 is inserted into the KB.
 
 ### Merge pairs
 
@@ -54,8 +50,8 @@ If the answer of a new QnA pair matches the answer of an old QnA pair, the two p
 If the old QnA pair has a metadata value, that data is retained and persisted in the newly merged pair.
   
 If the old QnA pair has follow-up prompts associated with it, then the following scenarios may arise:
-* If the prompt attached to the old pair is from the source being refreshed, then it's deleted, and the prompt of the new pair (if any exists) is appended to the newly merged QnA pair.
-* If the prompt attached to the old pair is from a different source, then it's maintained as-is and the prompt from the new question (if any exists) is appended to the newly merged QnA pair.
+* If the prompt attached to the old pair is from the source being refreshed, that prompt is deleted, and the prompt of the new pair (if any exists) is appended to the newly merged QnA pair.
+* If the prompt attached to the old pair is from a different source, then that prompt is maintained as-is. The prompt from the new question (if any exists) is appended to the newly merged QnA pair.
 
 
 #### Merge example
@@ -70,13 +66,13 @@ The prompts P1 and P2 come from the original source and are different from promp
 
 |Question  |Answer  |Prompts  |
 |---------|---------|--|
-|"What is the new HR policy?" </br>(alternate question: "What is the new payroll policy?")    |  "You might have to choose among the following options:"       | P3, P4  |
+|"What is the new HR policy?" </br>(Alternate question: "What is the new payroll policy?")    |  "You might have to choose among the following options:"       | P3, P4  |
 
 #### Duplicate answers scenario
 
 When the original source has two or more QnA pairs with the same answer (as in, Q1A1 and Q2A1), the merge behavior may be more complex.
 
-If these two QnA pairs have individual prompts attached to them (for example, Q1A1+P1 and Q2A1+P2), and the refreshed source content has a new QnA pair generated with the same answer A1 and a new prompt P3 (Q1'A1+P3), then the new question will be added as an alternate question to the original pairs (as described above). But all of the original attached prompts will be overwritten by the new prompt. So the final pair set will look like this:
+If each QnA pair has its own prompt (like Q1A1 with P1 and Q2A1 with P2), the updated source might make a new QnA pair with the same answer but a new prompt, such as Q1'A1 with P3. In this case, the new question is added as an alternate to the originals. This process helps keep the QnA pairs up to date with the latest source content. However, all of the original prompts are replaced via the new prompt from the refreshed content. So the final pair set looks like this:
 
 |Question  |Answer  |Prompts  |
 |---------|---------|--|

@@ -1,23 +1,23 @@
 ---
 title: Troubleshooting - custom question answering
-description: The curated list of the most frequently asked questions regarding custom question answering will help you adopt the feature faster and with better results.
+description: The curated list of the most frequently asked questions regarding custom question answering helps you adopt the feature faster and with better results.
 ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
 ms.topic: troubleshooting
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ---
 # Troubleshooting for custom question answering
 
-The curated list of the most frequently asked questions regarding custom question answering will help you adopt the feature faster and with better results.
+The curated list of the most frequently asked questions regarding custom question answering helps you adopt the feature faster and with better results.
 
 ## Manage predictions
 
 <details>
 <summary><b>How can I improve the throughput performance for query predictions?</b></summary>
 
 **Answer**:
-Throughput performance issues indicate you need to scale up your Azure AI Search. Consider adding a replica to your Azure AI Search to improve performance.
+Throughput performance issues indicate you need to scale up your Azure AI Search. Consider adding a replica to your Azure AI Search and improve performance.
 
 Learn more about [pricing tiers](../Concepts/azure-resources.md).
 </details>
@@ -28,7 +28,7 @@ Learn more about [pricing tiers](../Concepts/azure-resources.md).
 <summary><b>Why is my URL(s)/file(s) not extracting question-answer pairs?</b></summary>
 
 **Answer**:
-It's possible that custom question answering can't auto-extract some question-and-answer (QnA) content from valid FAQ URLs. In such cases, you can paste the QnA content in a .txt file and see if the tool can ingest it. Alternately, you can editorially add content to your project through the [Language Studio portal](https://language.azure.com).
+It's possible that custom question answering can't autoextract some question-and-answer (QnA) content from valid FAQ URLs. In such cases, you can paste the QnA content in a .txt file and see if the tool can ingest it.
 
 </details>
 
@@ -44,7 +44,7 @@ The size of the project depends on the SKU of Azure search you choose when creat
 <summary><b>How do I share a project with others?</b></summary>
 
 **Answer**:
-Sharing works at the level of the language resource, that is, all projects associated a language resource can be shared.
+Project sharing works at the level of the language resource, that is, all projects associated a language resource can be shared.
 </details>
 
 <details>
@@ -67,7 +67,7 @@ You can share an entire language resource, not individual projects.
 <summary><b>The updates that I made to my project are not reflected in production. Why not?</b></summary>
 
 **Answer**:
-Every edit operation, whether in a table update, test, or setting, needs to be saved before it can be deployed. Be sure to select **Save** after making changes and then re-deploy your project for those changes to be reflected in production.
+Every edit operation, whether in a table update, test, or setting, needs to be saved before it can be deployed. Be sure to select **Save** after making changes and then redeploy your project for those changes to be reflected in production.
 
 </details>
 
@@ -76,9 +76,9 @@ Every edit operation, whether in a table update, test, or setting, needs to be s
 
 **Answer**:
 
-#### Multimedia auto-extraction for files and URLs
+#### Multimedia autoextraction for files and URLs
 
-* URLS - limited HTML-to-Markdown conversion capability.
+* Links - limited HTML-to-Markdown conversion capability.
 * Files - not supported
 
 #### Answer text in markdown
@@ -103,7 +103,7 @@ If you have content from multiple languages, be sure to create a separate projec
 <summary><b>I deleted my existing Search service. How can I fix this?</b></summary>
 
 **Answer**:
-If you delete an Azure AI Search index, the operation is final and the index cannot be recovered.
+If you delete an Azure AI Search index, the operation is final and the index can't be recovered.
 
 </details>
 
@@ -119,7 +119,7 @@ In case you deleted the `testkbv2` index in your Search service, you can restore
 <summary><b>Can I use the same Azure AI Search resource for projects using multiple languages?</b></summary>
 
 **Answer**:
-To use multiple language and multiple projects, the user has to create a project for each language and the first project created for the language resource has to select the option **I want to select the language when I create a project in this resource**. This will create a separate Azure search service per language.
+To use multiple language and multiple projects, the user has to create a project for each language and the first project created for the language resource has to select the option **I want to select the language when I create a project in this resource**. This requirement creates a separate Azure search service per language.
 
 </details>
 
@@ -129,7 +129,7 @@ To use multiple language and multiple projects, the user has to create a project
 <summary><b>Do I need to use Bot Framework in order to use custom question answering?</b></summary>
 
 **Answer**:
-No, you do not need to use the [Bot Framework](https://github.com/Microsoft/botbuilder-dotnet) with custom question answering. However, custom question answering is offered as one of several templates in [Azure AI Bot Service](/azure/bot-service/). Bot Service enables rapid intelligent bot development through Microsoft Bot Framework, and it runs in a server-less environment.
+No, you don't need to use the [Bot Framework](https://github.com/Microsoft/botbuilder-dotnet) with custom question answering. However, custom question answering is offered as one of several templates in [Azure AI Bot Service](/azure/bot-service/). Bot Service enables rapid intelligent bot development through Microsoft Bot Framework, and it runs in a server-less environment.
 
 </details>
 

@@ -1,7 +1,7 @@
 ---
 title: "Quickstart: Use cURL & REST to manage project - custom question answering"
 description: This quickstart shows you how to create, publish, and query your project using the REST APIs.
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.topic: include
 author: laujan
 ms.author: lajanuar
@@ -13,7 +13,7 @@ ms.author: lajanuar
 * Custom question answering requires a [Language resource](https://portal.azure.com/?quickstart=true#create/Microsoft.CognitiveServicesTextAnalytics) with the custom question answering feature enabled to generate an API key and endpoint.
     * After your Language resource deploys, select **Go to resource**. You need the key and endpoint from the resource you create to connect to the API. Paste your key and endpoint into the code later in the quickstart.
 * Create a Language resource with [Azure CLI](../../../multi-service-resource.md?pivots=azcli) and provide the following properties: `--api-properties qnaAzureSearchEndpointId=/subscriptions/<azure-subscription-id>/resourceGroups/<resource-group-name>/providers/Microsoft.Search/searchServices/<azure-search-service-name> qnaAzureSearchEndpointKey=<azure-search-service-auth-key>`
-* An existing project to query. If you have not setup a project, you can follow the instructions in the [**Language Studio quickstart**](../quickstart/sdk.md). Or add a project that uses this [Surface User Guide URL](https://download.microsoft.com/download/7/B/1/7B10C82E-F520-4080-8516-5CF0D803EEE0/surface-book-user-guide-EN.pdf) as a data source.
+* An existing project to query. If you have not setup a project, you can follow the instructions in the [**Foundry quickstart**](../quickstart/sdk.md). Or add a project that uses this [Surface User Guide URL](https://download.microsoft.com/download/7/B/1/7B10C82E-F520-4080-8516-5CF0D803EEE0/surface-book-user-guide-EN.pdf) as a data source.
 
 
 
@@ -31,10 +31,10 @@ To [query a custom question answering project](/rest/api/questionanswering/quest
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `Endpoint`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`|
-| `API-Key` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys always for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `Endpoint`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`|
+| `API-Key` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys always for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `Project` | The name of your custom question answering project.|
-| `Deployment`             | There are two possible values: `test`, and `production`. `production` is dependent on you deploying your project from **Language Studio** > **question answering** > **Deploy project**.|
+| `Deployment`             | There are two possible values: `test`, and `production`.|
 
 The cURL command is executed from a BASH shell. Edit this command with your own resource name, resource key, and JSON values and size of JSON.
 

@@ -4,7 +4,7 @@ description: This quickstart shows how to get started with the custom question a
 author: laujan
 ms.author: lajanuar
 ms.topic: include
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ---
 Use this quickstart for the custom question answering client library for .NET to:
 
@@ -26,7 +26,7 @@ Use this quickstart for the custom question answering client library for .NET to
 * Custom question answering requires a [Language resource](https://portal.azure.com/?quickstart=true#create/Microsoft.CognitiveServicesTextAnalytics) with the custom question answering feature enabled to generate an API key and endpoint. 
     * After your Language resource deploys, select **Go to resource**. You need the key and endpoint from the resource you create to connect to the API. Paste your key and endpoint into the code later in the quickstart.
 * Create a Language resource with [Azure CLI](../../../multi-service-resource.md?pivots=azcli) and provide the following properties: `--api-properties qnaAzureSearchEndpointId=/subscriptions/<azure-subscription-id>/resourceGroups/<resource-group-name>/providers/Microsoft.Search/searchServices/<azure-search-service-name> qnaAzureSearchEndpointKey=<azure-search-service-auth-key>`
-* An existing project to query. If you don't have a project, you can follow the instructions in the [**Language Studio quickstart**](../quickstart/sdk.md). Or add a project that uses this [Surface User Guide URL](https://download.microsoft.com/download/7/B/1/7B10C82E-F520-4080-8516-5CF0D803EEE0/surface-book-user-guide-EN.pdf) as a data source.
+* An existing project to query. If you don't have a project, you can follow the instructions in the [**Microsoft Foundry quickstart**](../quickstart/sdk.md). Or add a project that uses this [Surface User Guide URL](https://download.microsoft.com/download/7/B/1/7B10C82E-F520-4080-8516-5CF0D803EEE0/surface-book-user-guide-EN.pdf) as a data source.
 
 
 
@@ -78,10 +78,10 @@ You need to update the code and provide your own values for the following variab
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `endpoint`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`|
-| `credential` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys always for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `endpoint`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`|
+| `credential` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys always for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `projectName` | The name of your custom question answering project.|
-| `deploymentName`             | There are two possible values: `test`, and `production`. `production` is dependent on you deployed your project from **Language Studio** > **question answering** > **Deploy project**.|
+| `deploymentName`             | There are two possible values: `test`, and `production`.|
 
 > [!IMPORTANT]
 > Remember to remove the key from your code when you're done, and never post it publicly. For production, use a secure way of storing and accessing your credentials like [Azure Key Vault](/azure/key-vault/general/overview). For more information, see [Foundry Tools security](../../../security-features.md).

@@ -4,7 +4,7 @@ description: This quickstart shows how to get started with the custom question a
 ms.topic: include
 author: laujan
 ms.author: lajanuar
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ---
 Use this quickstart for the custom question answering client library for Python to:
 
@@ -25,7 +25,7 @@ Use this quickstart for the custom question answering client library for Python
 * Custom question answering requires a [Language resource](https://portal.azure.com/?quickstart=true#create/Microsoft.CognitiveServicesTextAnalytics) with the custom question answering feature enabled to generate an API key and endpoint.
     * After your Language resource deploys, select **Go to resource**. You need the key and endpoint from the resource you create to connect to the API. Paste your key and endpoint into the code later in the quickstart.
 * Create a Language resource with [Azure CLI](../../../multi-service-resource.md?pivots=azcli) and provide the following properties: `--api-properties qnaAzureSearchEndpointId=/subscriptions/<azure-subscription-id>/resourceGroups/<resource-group-name>/providers/Microsoft.Search/searchServices/<azure-search-service-name> qnaAzureSearchEndpointKey=<azure-search-service-auth-key>`
-* An existing project to query. If you don't have a project, you can follow the instructions in the [**Language Studio quickstart**](../quickstart/sdk.md). Or add a project that uses this [Surface User Guide URL](https://download.microsoft.com/download/7/B/1/7B10C82E-F520-4080-8516-5CF0D803EEE0/surface-book-user-guide-EN.pdf) as a data source.
+* An existing project to query. If you don't have a project, you can follow the instructions in the [**Microsoft Foundry quickstart**](../quickstart/sdk.md). Or add a project that uses this [Surface User Guide URL](https://download.microsoft.com/download/7/B/1/7B10C82E-F520-4080-8516-5CF0D803EEE0/surface-book-user-guide-EN.pdf) as a data source.
 
 
 
@@ -51,8 +51,8 @@ You need to update the code and provide your own values for the following variab
 
 |Variable name | Value |
 |--------------------------|-------------|
-| `endpoint`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`|
-| `credential` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys always for secure key rotation with zero downtime. Alternatively you can find the value in **Language Studio** > **question answering** > **Deploy project** > **Get prediction URL**. The key value is part of the sample request.|
+| `endpoint`               | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. An example endpoint is: `https://southcentralus.cognitiveservices.azure.com/`|
+| `credential` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either Key1 or Key2. Always having two valid keys always for secure key rotation with zero downtime. The key value is part of the sample request.|
 | `knowledge_base_project` | The name of your question answering project.|
 | `deployment`             | There are two possible values: `test`, and `production`. `production`.|
 

@@ -1,95 +1,51 @@
 ---
 title: What is custom question answering?
 titleSuffix: Foundry Tools
-description: Custom question answering is a cloud-based Natural Language Processing (NLP) service that easily creates a natural conversational layer over your data. It can be used to find the most appropriate answer for any given natural language input, from your custom project.
+description: Custom question answering is a cloud-based NLP service that creates conversational layers over your data to deliver accurate answers for natural language queries.
 ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
 recommendations: false
 ms.topic: overview
-ms.date: 11/18/2025
-keywords: "qna maker, low code chat bots, multi-turn conversations"
+ms.date: 12/10/2025 
+keywords: "low code chat bots, multi-turn conversations"
 ms.custom: language-service-question-answering
 ---
 # What is custom question answering?
 
-Custom question answering provides cloud-based Natural Language Processing (NLP) that allows you to create a natural conversational layer over your data. It's used to find appropriate answers from customer input or from a project.
+Custom question answering (CQA) is a cloud-based Natural Language Processing (NLP) service that creates conversational AI applications over your data. Build knowledge bases from FAQs, manuals, and documents to deliver accurate answers through chat bots, virtual assistants, and interactive interfaces.
 
-Custom question answering is commonly used to build conversational client applications, which include social media applications, chat bots, and speech-enabled desktop applications. This offering includes features like enhanced relevance using a deep learning ranker, precise answers, and end-to-end region support.
+## Key capabilities
 
-Custom question answering comprises two capabilities:
+Custom question answering provides enterprise-grade features for building and maintaining conversational AI solutions:
 
-* Custom question answering: Using this capability, users can customize different aspects like edit question and answer pairs extracted from the content source, define synonyms, and metadata, accept question suggestions etc.
-* [QnA Maker](./../../qnamaker/Overview/overview.md): This capability allows users to get a response by querying a text passage without having the need to manage knowledge bases.
+* **Knowledge base creation** - Import content from URLs, files, and documents. The service automatically extracts question-answer pairs from structured and semi-structured sources.
+* **Multi-turn conversations** - Create guided conversation flows with follow-up prompts that navigate users through complex information.
+* **Metadata filtering** - Tag answers by content type, domain, or freshness to deliver contextually relevant responses.
+* **Active learning** - Improve answer quality based on real-world usage patterns and user queries.
+* **Deep learning ranking** - Multi-stage ranking architecture combines Azure AI Search with NLP reranking for optimal answer selection.
 
-This documentation contains the following article types:
+## Architecture and workflow
 
-* The [quickstarts](./quickstart/sdk.md) are step-by-step instructions that let you make calls to the service and get results in a short period of time.
-* The [how-to guides](./how-to/manage-knowledge-base.md) contain instructions for using the service in more specific or customized ways.
-* The [conceptual articles](./concepts/precise-answering.md) provide in-depth explanations of the service's functionality and features.
-* [**Tutorials**](./tutorials/bot-service.md) are longer guides that show you how to use the service as a component in broader business solutions. 
+The service follows a structured pipeline from project creation to production deployment:
 
-## When to use custom question answering
+1. **Create a project** - Build a knowledge base by importing content sources or manually adding question-answer pairs in [Microsoft Foundry (classic)](https://ai.azure.com/).
+1. **Test and refine** - Use the test interface to validate responses and adjust answer quality before deployment.
+1. **Deploy** - Publish your project to create a REST API endpoint accessible by client applications.
+1. **Integrate** - Client applications send queries and receive JSON responses with answers, confidence scores, and follow-up prompts.
 
-* **When you have static information** - Use custom question answering when you have static information in your project. This project is custom to your needs, which you built with documents such as PDFs and URLs.
-* **When you want to provide the same answer to a request, question, or command** - when different users submit the same question, the same answer is returned.
-* **When you want to filter static information based on meta-information** - add [metadata](./tutorials/multiple-domains.md) tags to provide added filtering options relevant to your client application's users and the information. Common metadata information includes [chit-chat](./how-to/chit-chat.md), content type or format, content purpose, and content freshness. <!--TODO: Fix Link-->
-* **When you want to manage a bot conversation that includes static information** - your project takes a user's conversational text or command and answers it. If the answer is part of a predetermined conversation flow, represented in your project with [multi-turn context](./tutorials/guided-conversations.md), the bot can easily provide this flow.
+## Development options
 
-## What is a project?
+Choose from multiple development approaches based on your technical requirements and expertise:
 
-Custom question answering [imports your content](./how-to/manage-knowledge-base.md) into a project full of question and answer pairs. The import process extracts information about the relationship between the parts of your structured and semi-structured content to imply relationships between the question and answer pairs. You can edit these question and answer pairs or add new pairs.
-
-The content of the question and answer pair includes:
-* All the alternate forms of the question
-* Metadata tags used to filter answer choices during the search
-* Follow-up prompts to continue the search refinement
-
-After you publish your project, a client application sends a user's question to your endpoint. Your custom question answering service processes the question and responds with the best answer.
-
-## Create a chat bot programmatically
-
-Once a custom question answering project is published, a client application sends a question to your project endpoint and receives the results as a JSON response. A common client application for custom question answering is a chat bot.
-
-![Ask a bot a question and get answer from project content](../../qnamaker/media/qnamaker-overview-learnabout/bot-chat-with-qnamaker.png)
-
-|Step|Action|
-|:--|:--|
-|1|The client application sends the user's _question_ (text in their own words) to your project endpoint, *How do I programmatically update my project?*|
-|2|Custom question answering uses the trained project to provide the correct answer and any follow-up prompts that can be used to refine the search for the best answer. Custom question answering returns a JSON-formatted response.|
-|3|The client application uses the JSON response to make decisions about how to continue the conversation. These decisions can include showing the top answer and presenting more choices to refine the search for the best answer. |
-|||
-
-## Build low code chat bots
-
-The [Language Studio](https://language.cognitive.azure.com/) portal provides the complete project authoring experience. You can import documents, in their current form, to your project. These documents (such as an FAQ, product manual, spreadsheet, or web page) are converted into question and answer pairs. Each pair is analyzed for follow-up prompts and connected to other pairs. The final _markdown_ format supports rich presentation including images and links.
-
-Once your project is edited, publish the project to a working [Azure Web App bot](https://azure.microsoft.com/services/bot-service/) without writing any code. Test your bot in the [Azure portal](https://portal.azure.com) or download it and continue development.
-
-## High quality responses with layered ranking
-
-The custom question answering system uses a layered ranking approach. The data is stored in Azure search, which also serves as the first ranking layer. The top results from Azure search are then passed through custom question answering's NLP reranking model to produce the final results and confidence score.
-
-## Multi-turn conversations
-
-Custom question answering provides multi-turn prompts and active learning to help you improve your basic question and answer pairs.
-
-**Multi-turn prompts** give you the opportunity to connect question and answer pairs. This connection allows the client application to provide a top answer and provides more questions to refine the search for a final answer.
-
-After the project receives questions from users at the published endpoint, custom question answering applies **active learning** to these real-world questions to suggest changes to your project to improve the quality.
-
-## Development lifecycle
-
-Custom question answering provides authoring, training, and publishing along with collaboration permissions to integrate into the full development life cycle.
-
-> [!div class="mx-imgBorder"]
-> ![Conceptual image of development cycle](../../qnamaker/media/qnamaker-overview-learnabout/development-cycle.png)
-
-## Complete a quickstart
-
-We offer quickstarts in most popular programming languages, each designed to teach you basic design patterns, and have you running code in less than 10 minutes.
-
-* [Get started with the custom question answering client library](./quickstart/sdk.md)
+* **Microsoft Foundry (classic)** - Low-code authoring with automatic QA extraction, markdown support, and [chit-chat](./how-to/chit-chat.md) integration. Deploy directly to [Azure Bot Service](https://azure.microsoft.com/services/bot-service/).
+* **REST APIs** - Programmatic access for custom integrations and automated workflows. See the [Azure Language REST API reference](/rest/api/language/) for endpoint documentation.
+* **Client libraries** - SDK packages for .NET and Python enable programmatic project management and query integration:
+  * [.NET (C#) packages](https://www.nuget.org/packages/Azure.AI.Language.QuestionAnswering/) - Runtime and authoring SDKs for C# applications
+  * [Python packages](https://pypi.org/project/azure-ai-language-questionanswering/) - Runtime and authoring SDKs for Python applications
 
 ## Next steps
-Custom question answering provides everything you need to build, manage, and deploy your custom project.
+
+* [Quickstart: Create and deploy a CQA project](./quickstart/sdk.md)
+* [Manage knowledge bases](./how-to/manage-knowledge-base.md)
+* [Configure multi-turn conversations](./tutorials/guided-conversations.md)

@@ -5,17 +5,17 @@ ms.service: azure-ai-language
 ms.author: lajanuar
 author: laujan
 ms.topic: reference
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ---
 # Format guidelines for custom question answering
 
 Review these formatting guidelines to get the best results for your content.
 
 ## Formatting considerations
 
-After importing a file or URL, custom question answering converts and stores your content in the [markdown format](https://en.wikipedia.org/wiki/Markdown). The conversion process adds new lines in the text, such as `\n\n`. A knowledge of the markdown format helps you to understand the converted content and manage your project content.
+After you import a file or URL, custom question answering converts and stores your content in the [markdown format](https://en.wikipedia.org/wiki/Markdown). The conversion process adds new lines in the text, such as `\n\n`. A knowledge of the markdown format helps you to understand the converted content and manage your project content.
 
-If you add or edit your content directly in your project, use **markdown formatting** to create rich text content or change the markdown format content that is already in the answer. Custom question answering supports much of the markdown format to bring rich text capabilities to your content. However, the client application, such as a chat bot may not support the same set of markdown formats. It is important to test the client application's display of answers.
+If you add or edit your content directly in your project, use **markdown formatting** to create rich text content or change the markdown format content that is already in the answer. Custom question answering supports much of the markdown format to bring rich text capabilities to your content. However, the client application, such as a chat bot may not support the same set of markdown formats. It's important to test the client application's display of answers.
 
 ## Basic document formatting
 
@@ -33,7 +33,7 @@ Custom question answering identifies sections and subsections and relationships
 
 A manual is typically guidance material that accompanies a product. It helps the user to set up, use, maintain, and troubleshoot the product. When custom question answering processes a manual, it extracts the headings and subheadings as questions and the subsequent content as answers. See an example [here](https://download.microsoft.com/download/2/9/B/29B20383-302C-4517-A006-B0186F04BE28/surface-pro-4-user-guide-EN.pdf).
 
-Below is an example of a manual with an index page, and hierarchical content
+To follow is an example of a manual with an index page, and hierarchical content
 
 > [!div class="mx-imgBorder"]
 > ![Product Manual example for a project](../../../qnamaker/media/qnamaker-concepts-datasources/product-manual.png)
@@ -43,31 +43,31 @@ Below is an example of a manual with an index page, and hierarchical content
 
 ### Brochures, guidelines, papers, and other files
 
-Many other types of documents can also be processed to generate question answer pairs, provided they have a clear structure and layout. These include: Brochures, guidelines, reports, white papers, scientific papers, policies, books, etc. See an example [here](https://qnamakerstore.blob.core.windows.net/qnamakerdata/docs/Manage%20Azure%20Blob%20Storage.docx).
+Many other types of documents can also be processed to generate question answer pairs, provided they have a clear structure and layout. These documents include: Brochures, guidelines, reports, white papers, scientific papers, policies, books, etc. See an example [here](https://qnamakerstore.blob.core.windows.net/qnamakerdata/docs/Manage%20Azure%20Blob%20Storage.docx).
 
-Below is an example of a semi-structured doc, without an index:
+To follow is an example of a semi-structured doc, without an index:
 
 > [!div class="mx-imgBorder"]
 > ![Azure Blob storage semi-structured Doc](../../../qnamaker/media/qnamaker-concepts-datasources/semi-structured-doc.png)
 
 ### Unstructured document support
 
-Custom question answering now supports unstructured documents. A  document that does not have its content organized in a well-defined hierarchical manner, is missing a set structure or has its content free flowing can be considered as an unstructured document.
+Custom question answering now supports unstructured documents. A  document that doesn't have its content organized in a hierarchical manner, is missing a set structure or has its content free flowing can be considered as an unstructured document.
 
-Below is an example of an unstructured PDF document:
+To follow is an example of an unstructured PDF document:
 
 > [!div class="mx-imgBorder"]
 > ![Unstructured  document example for a project](../../../qnamaker/media/qnamaker-concepts-datasources/unstructured-qna-pdf.png)
 
 > [!NOTE]
-> QnA pairs are not extracted in the "Edit sources" tab for unstructured sources.
+> QnA pairs aren't extracted in the "Edit sources" tab for unstructured sources.
 
 > [!IMPORTANT]
 > Support for unstructured file/content is available only in custom question answering.
 
 ### Structured custom question answering document
 
-The format for structured question-answers in DOC files, is in the form of alternating questions and answers per line, one question per line followed by its answer in the following line, as shown below:
+The format for structured question-answers in DOC files is in the form of alternating questions and answers per line. It's one question per line followed by its answer in the following line, as shown:
 
 ```text
 Question1
@@ -79,27 +79,27 @@ Question2
 Answer2
 ```
 
-Below is an example of a structured custom question answering word document:
+To follow is an example of a structured custom question answering word document:
 
 > [!div class="mx-imgBorder"]
 > ![Structured custom question answering document example for a project](../../../qnamaker/media/qnamaker-concepts-datasources/structured-qna-doc.png)
 
 ### Structured *TXT*, *TSV* and *XLS* Files
 
-Custom question answering in the form of structured *.txt*, *.tsv* or *.xls* files can also be uploaded to custom question answering to create or augment a project.  These can either be plain text, or can have content in RTF or HTML. Question answer pairs have an optional metadata field that can be used to group question answer pairs into categories.
+Custom question answering in the form of structured *.txt*, *.tsv* or *.xls* files can also be uploaded to custom question answering to create or augment a project. These files can either be plain text, or can have content in RTF or HTML. Question answer pairs have an optional metadata field that can be used to group question answer pairs into categories.
 
-| Question  | Answer  | Metadata (1 key: 1 value) |
+| Question  | Answer  | Metadata (one key: One value) |
 |-----------|---------|-------------------------|
 | Question1 | Answer1 | <code>Key1:Value1 &#124; Key2:Value2</code> |
 | Question2 | Answer2 |      `Key:Value`           |
 
-Any additional columns in the source file are ignored.
+Any other columns in the source file are ignored.
 
 ### Structured data format through import
 
-Importing a project replaces the content of the existing project. Import requires a structured .tsv file that contains data source information. This information helps group the question-answer pairs and attribute them to a particular data source. Question answer pairs have an optional metadata field that can be used to group question answer pairs into categories. The import format needs to be similar to the exported knowledgebase format.
+Importing a project replaces the content of the existing project. Import requires a structured .tsv file that contains data source information. This information helps group the question-answer pairs and attributes them to a particular data source. Question answer pairs have an optional metadata field that can be used to group question answer pairs into categories. The import format needs to be similar to the exported knowledgebase format.
 
-| Question  | Answer  | Source| Metadata (1 key: 1 value) | QnaId |
+| Question  | Answer  | Source| Metadata (one key: one value) | QnaId |
 |-----------|---------|----|---------------------|------|
 | Question1 | Answer1 | Url1 | <code>Key1:Value1 &#124; Key2:Value2</code> | QnaId 1 |
 | Question2 | Answer2 | Editorial|    `Key:Value`       | QnaId 2 |
@@ -108,9 +108,9 @@ Importing a project replaces the content of the existing project. Import require
 
 ### Multi-turn document formatting
 
-* Use headings and subheadings to denote hierarchy. For example, You can h1 to denote the parent question answer and h2 to denote the question answer that should be taken as prompt. Use small heading size to denote subsequent hierarchy. Do not use style, color, or some other mechanism to imply structure in your document, custom question answering will not extract the multi-turn prompts.
+* Use headings and subheadings to denote hierarchy. For example, You can h1 to denote the parent question answer and h2 to denote the question answer that should be taken as prompt. Use small heading size to denote subsequent hierarchy. Don't use style, color, or some other mechanism to imply structure in your document, custom question answering doesn't extract the multi-turn prompts.
 * First character of heading must be capitalized.
-* Do not end a heading with a question mark, `?`.
+* Don't end a heading with a question mark, `?`.
 
 **Sample documents**:<br>[Surface Pro (docx)](https://github.com/Azure-Samples/cognitive-services-sample-data-files/blob/master/qna-maker/data-source-formats/multi-turn.docx)<br>[Contoso Benefits (docx)](https://github.com/Azure-Samples/cognitive-services-sample-data-files/blob/master/qna-maker/data-source-formats/Multiturn-ContosoBenefits.docx)<br>[Contoso Benefits (pdf)](https://github.com/Azure-Samples/cognitive-services-sample-data-files/blob/master/qna-maker/data-source-formats/Multiturn-ContosoBenefits.pdf)
 
@@ -120,42 +120,40 @@ Custom question answering can support FAQ web pages in three different forms:
 
 * Plain FAQ pages
 * FAQ pages with links
-* FAQ pages with a Topics Homepage
+* FAQ pages with a `Topics` Homepage
 
 ### Plain FAQ pages
 
-This is the most common type of FAQ page, in which the answers immediately follow the questions in the same page.
+This type is the most common type of FAQ page, in which the answers immediately follow the questions in the same page.
 
 ### FAQ pages with links
 
 In this type of FAQ page, questions are aggregated together and are linked to answers that are either in different sections of the same page, or in different pages.
 
-Below is an example of an FAQ page with links in sections that are on the same page:
+To follow is an example of an FAQ page with links in sections that are on the same page:
 
 > [!div class="mx-imgBorder"]
 > ![Section Link FAQ page example for a project](../../../qnamaker/media/qnamaker-concepts-datasources/sectionlink-faq.png)
 
-### Parent Topics page links to child answers pages
+### Parent `Topics` page links to child answers pages
 
-This type of FAQ has a Topics page where each topic is linked to a corresponding set of questions and answers on a different page. Question answer crawls all the linked pages to extract the corresponding questions & answers.
+This type of FAQ has a `Topics` page where each subject is linked to a corresponding set of questions and answers on a different page. Question answer crawls all the linked pages to extract the corresponding questions & answers.
 
-Below is an example of a Topics page with links to FAQ sections in different pages.
+To follow is an example of a `Topics` page with links to FAQ sections in different pages.
 
 > [!div class="mx-imgBorder"]
 > ![Deep link FAQ page example for a project](../../../qnamaker/media/qnamaker-concepts-datasources/topics-faq.png)
 
 ### Support URLs
 
-Custom question answering can process semi-structured support web pages, such as web articles that would describe how to perform a given task, how to diagnose and resolve a given problem, and what are the best practices for a given process. Extraction works best on content that has a clear structure with hierarchical headings.
+Custom question answering works with semi-structured support web pages. These web pages include articles that explain how to do a task, how to solve a problem, or what best practices to follow. Extraction works best when the content has a clear structure with headings.
 
 > [!NOTE]
-> Extraction for support articles is a new feature and is in early stages. It works best for simple pages, that are well structured, and do not contain complex headers/footers.
+> Extraction for support articles is a new feature and is in early stages. It works best for simple pages that are well structured, and don't contain complex headers/footers.
 
 ## Import and export project
 
-**TSV and XLS files**, from exported projects, can only be used by importing the files from the **Settings** page in Language Studio. They cannot be used as data sources during project creation or from the **+ Add file** or **+ Add URL** feature on the **Settings** page.
-
-When you import the project through these **TSV and XLS files**, the question answer pairs get added to the editorial source and not the sources from which the question and answers were extracted in the exported project.
+To migrate your Azure Language Studio project to your Microsoft Foundry project, link your existing Azure Language resource as a **`Connected Resource`** within your Foundry project's **`Management Center`**. For more information, *see* [Connect Foundry Tools to a Foundry project](/azure/ai-services/connect-services-ai-foundry-portal#connect-foundry-tools-after-you-create-a-project)
 
 ## Next steps
 

@@ -5,7 +5,7 @@ ms.service: azure-ai-language
 ms.author: lajanuar
 author: laujan
 ms.topic: reference
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ---
 # Markdown format supported in answer text
 
@@ -25,8 +25,8 @@ Following is the list of markdown formats that you can use in your answer text.
 
 |Purpose|Format|Example markdown|
 |--|--|--|
-A new line between 2 sentences.|`\n\n`|`How can I create a bot with \n\n custom question answering?`|
-|Headers from h1 to h6, the number of `#` denotes which header. 1 `#` is the h1.|`\n# text \n## text \n### text \n####text \n#####text` |`## Creating a bot \n ...text.... \n### Important news\n ...text... \n### Related Information\n ....text...`<br><br>`\n# my h1 \n## my h2\n### my h3 \n#### my h4 \n##### my h5`|
+A new line between two sentences.|`\n\n`|`How can I create a bot with \n\n custom question answering?`|
+|Headers from h1 to h6, the number of `#` denotes which header. One `#` is the h1.|`\n# text \n## text \n### text \n####text \n#####text` |`## Creating a bot \n ...text.... \n### Important news\n ...text... \n### Related Information\n ....text...`<br><br>`\n# my h1 \n## my h2\n### my h3 \n#### my h4 \n##### my h5`|
 |Italics |`*text*`|`How do I create a bot with *custom question answering*?`|
 |Strong (bold)|`**text**`|`How do I create a bot with **custom question answering***?`|
 |URL for link|`[text](https://www.my.com)`|`How do I create a bot with [custom question answering](https://language.cognitive.azure.com/)?`|
@@ -37,7 +37,7 @@ A new line between 2 sentences.|`\n\n`|`How can I create a bot with \n\n custom
 |Italics URL for link|`[*text*](https://www.my.com)`|`How do I create a bot with [*custom question answering*](https://language.cognitive.azure.com/)?`|
 |Escape markdown symbols|`\*text\*`|`How do I create a bot with \*custom question answering*\*?`|
 |Ordered list|`\n 1. item1 \n 1. item2`|`This is an ordered list: \n 1. List item 1 \n 1. List item 2`<br>The preceding example uses automatic numbering built into markdown.<br>`This is an ordered list: \n 1. List item 1 \n 2. List item 2`<br>The preceding example uses explicit numbering.|
-|Unordered list|`\n * item1 \n * item2`<br>or<br>`\n - item1 \n - item2`|`This is an unordered list: \n * List item 1 \n * List item 2`|
+|Unordered list|`\n * item1 \n * item2`<br>`or`<br>`\n - item1 \n - item2`|`This is an unordered list: \n * List item 1 \n * List item 2`|
 |Nested lists|`\n * Parent1 \n\t * Child1 \n\t * Child2 \n * Parent2`<br><br>`\n * Parent1 \n\t 1. Child1 \n\t * Child2 \n 1. Parent2`<br><br>You can nest ordered and unordered lists together. The tab, `\t`, indicates the indentation level of the child element.|`This is an unordered list: \n * List item 1 \n\t * Child1 \n\t * Child2 \n * List item 2`<br><br>`This is an ordered nested list: \n 1. Parent1 \n\t 1. Child1 \n\t 1. Child2 \n 1. Parent2`|
 
 * Custom question answering doesn't process the image in any way. It's the client application's role to render the image.

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.author: lajanuar
 ms.custom:
   - language-service-summarization
@@ -39,7 +39,7 @@ For easier navigation, here are links to the corresponding sections for each ser
 ## Features
 
 > [!TIP]
-> If you want to start using these features, you can follow the [quickstart article](../quickstart.md) to get started. You can also make example requests using [Language Studio](../../language-studio.md) without needing to write code.
+> If you want to start using these features, you can follow the [quickstart article](../quickstart.md) to get started. You can also make example requests using [Microsoft Foundry](https://ai.azure.com/)) without needing to write code.
 
 The extractive summarization API uses natural language processing techniques to locate key sentences in an unstructured text document. These sentences collectively convey the main idea of the document.
 

@@ -2,7 +2,7 @@
 author: laujan
 ms.author: lajanuar
 manager: nitinme
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.service: azure-ai-language
 ms.topic: include
 ms.custom:
@@ -26,7 +26,7 @@ ms.custom:
 
 Use this quickstart to create a text summarization application with the client library for .NET. In the following example, you'll create a C# application that can summarize documents or text-based customer service conversations.
 
-[!INCLUDE [Use Language Studio](../use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../use-microsoft-foundry.md)]
 
 ## Prerequisites
 
@@ -225,21 +225,21 @@ namespace Example
                             {
                                 new
                                 {
-                                    text = "Hello, you’re chatting with Rene. How may I help you?",
+                                    text = "Hello, you're chatting with Rene. How may I help you?",
                                     id = "1",
                                     role = "Agent",
                                     participantId = "Agent",
                                 },
                                 new
                                 {
-                                    text = "Hi, I tried to set up wifi connection for Smart Brew 300 coffee machine, but it didn’t work.",
+                                    text = "Hi, I tried to set up wifi connection for Smart Brew 300 coffee machine, but it didn't work.",
                                     id = "2",
                                     role = "Customer",
                                     participantId = "Customer",
                                 },
                                 new
                                 {
-                                    text = "I’m sorry to hear that. Let’s see what we can do to fix this issue. Could you please try the following steps for me? First, could you push the wifi connection button, hold for 3 seconds, then let me know if the power light is slowly blinking on and off every second?",
+                                    text = "I'm sorry to hear that. Let's see what we can do to fix this issue. Could you please try the following steps for me? First, could you push the wifi connection button, hold for 3 seconds, then let me know if the power light is slowly blinking on and off every second?",
                                     id = "3",
                                     role = "Agent",
                                     participantId = "Agent",
@@ -267,7 +267,7 @@ namespace Example
                                 },
                                 new
                                 {
-                                    text = "I’m very sorry to hear that. Let me see if there’s another way to fix the issue. Please hold on for a minute.",
+                                    text = "I'm very sorry to hear that. Let me see if there's another way to fix the issue. Please hold on for a minute.",
                                     id = "7",
                                     role = "Agent",
                                     participantId = "Agent",

@@ -2,7 +2,7 @@
 author: laujan
 ms.author: lajanuar
 manager: nitinme
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.service: azure-ai-language
 ms.topic: include
 ms.custom:
@@ -14,7 +14,7 @@ ms.custom:
 
 Use this quickstart to create a text summarization application with the client library for Java. In the following example, you'll create a Java application that can summarize documents.
 
-[!INCLUDE [Use Language Studio](../use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../use-microsoft-foundry.md)]
 
 ## Prerequisites
 
@@ -138,8 +138,8 @@ public class Example {
 
 ```console
 Extractive Summarization action results:
-	Extracted summary sentences:
-		 Sentence text: The extractive summarization feature uses natural language processing techniques to locate key sentences in an unstructured text document., length: 138, offset: 0, rank score: 1.000000.
-		 Sentence text: This feature is provided as an API for developers., length: 50, offset: 206, rank score: 0.510000.
-		 Sentence text: Extractive summarization supports several languages., length: 52, offset: 378, rank score: 0.410000.
+    Extracted summary sentences:
+         Sentence text: The extractive summarization feature uses natural language processing techniques to locate key sentences in an unstructured text document., length: 138, offset: 0, rank score: 1.000000.
+         Sentence text: This feature is provided as an API for developers., length: 50, offset: 206, rank score: 0.510000.
+         Sentence text: Extractive summarization supports several languages., length: 52, offset: 378, rank score: 0.410000.
 ```

@@ -2,7 +2,7 @@
 author: laujan
 ms.author: lajanuar
 manager: nitinme
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.service: azure-ai-language
 ms.topic: include
 ms.custom:
@@ -14,7 +14,7 @@ ms.custom:
 
 Use this quickstart to create a text summarization application with the client library for Node.js. In the following example, you create a JavaScript application that can summarize documents.
 
-[!INCLUDE [Use Language Studio](../use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../use-microsoft-foundry.md)]
 
 ## Prerequisites
 
@@ -84,16 +84,16 @@ const apiKey = process.env.LANGUAGE_KEY;
 
 const documents = [
   `
-           Windows 365 was in the works before COVID-19 sent companies around the world on a scramble to secure solutions to support employees suddenly forced to work from home, but “what really put the firecracker behind it was the pandemic, it accelerated everything,” McKelvey said. She explained that customers were asking, “’How do we create an experience for people that makes them still feel connected to the company without the physical presence of being there?”
+           Windows 365 was in the works before COVID-19 sent companies around the world on a scramble to secure solutions to support employees suddenly forced to work from home, but "what really put the firecracker behind it was the pandemic, it accelerated everything," McKelvey said. She explained that customers were asking, "'How do we create an experience for people that makes them still feel connected to the company without the physical presence of being there?"
            In this new world of Windows 365, remote workers flip the lid on their laptop, bootup the family workstation or clip a keyboard onto a tablet, launch a native app or modern web browser and login to their Windows 365 account. From there, their Cloud PC appears with their background, apps, settings and content just as they left it when they last were last there – in the office, at home or a coffee shop.
-           “And then, when you’re done, you’re done. You won’t have any issues around security because you’re not saving anything on your device,” McKelvey said, noting that all the data is stored in the cloud.
-           The ability to login to a Cloud PC from anywhere on any device is part of Microsoft’s larger strategy around tailoring products such as Microsoft Teams and Microsoft 365 for the post-pandemic hybrid workforce of the future, she added. It enables employees accustomed to working from home to continue working from home; it enables companies to hire interns from halfway around the world; it allows startups to scale without requiring IT expertise.
-           “I think this will be interesting for those organizations who, for whatever reason, have shied away from virtualization. This is giving them an opportunity to try it in a way that their regular, everyday endpoint admin could manage,” McKelvey said.
+           "And then, when you're done, you're done. You won't have any issues around security because you're not saving anything on your device," McKelvey said, noting that all the data is stored in the cloud.
+           The ability to login to a Cloud PC from anywhere on any device is part of Microsoft's larger strategy around tailoring products such as Microsoft Teams and Microsoft 365 for the post-pandemic hybrid workforce of the future, she added. It enables employees accustomed to working from home to continue working from home; it enables companies to hire interns from halfway around the world; it allows startups to scale without requiring IT expertise.
+           "I think this will be interesting for those organizations who, for whatever reason, have shied away from virtualization. This is giving them an opportunity to try it in a way that their regular, everyday endpoint admin could manage," McKelvey said.
            The simplicity of Windows 365 won over Dean Wells, the corporate chief information officer for the Government of Nunavut. His team previously attempted to deploy a traditional virtual desktop infrastructure and found it inefficient and unsustainable given the limitations of low-bandwidth satellite internet and the constant need for IT staff to manage the network and infrastructure.
-           We didn’t run it for very long,” he said. “It didn’t turn out the way we had hoped. So, we actually had terminated the project and rolled back out to just regular PCs.”
-           He re-evaluated this decision after the Government of Nunavut was hit by a ransomware attack in November 2019 that took down everything from the phone system to the government’s servers. Microsoft helped rebuild the system, moving the government to Teams, SharePoint, OneDrive and Microsoft 365. Manchester’s team recruited the Government of Nunavut to pilot Windows 365. Wells was intrigued, especially by the ability to manage the elastic workforce securely and seamlessly.
-           “The impact that I believe we are finding, and the impact that we’re going to find going forward, is being able to access specialists from outside the territory and organizations outside the territory to come in and help us with our projects, being able to get people on staff with us to help us deliver the day-to-day expertise that we need to run the government,” he said.
-           “Being able to improve healthcare, being able to improve education, economic development is going to improve the quality of life in the communities.”`,
+           We didn't run it for very long," he said. "It didn't turn out the way we had hoped. So, we actually had terminated the project and rolled back out to just regular PCs."
+           He re-evaluated this decision after the Government of Nunavut was hit by a ransomware attack in November 2019 that took down everything from the phone system to the government's servers. Microsoft helped rebuild the system, moving the government to Teams, SharePoint, OneDrive and Microsoft 365. Manchester's team recruited the Government of Nunavut to pilot Windows 365. Wells was intrigued, especially by the ability to manage the elastic workforce securely and seamlessly.
+           "The impact that I believe we are finding, and the impact that we're going to find going forward, is being able to access specialists from outside the territory and organizations outside the territory to come in and help us with our projects, being able to get people on staff with us to help us deliver the day-to-day expertise that we need to run the government," he said.
+           "Being able to improve healthcare, being able to improve education, economic development is going to improve the quality of life in the communities."`,
 ];
 
 async function main() {

@@ -1,7 +1,7 @@
 ---
 author: laujan
 ms.author: lajanuar
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.service: azure-ai-language
 ms.topic: include
 ms.custom:
@@ -26,7 +26,7 @@ ms.custom:
 
 Use this quickstart to create a text summarization application with the client library for Python. In the following example, you'll create a Python application that can summarize documents or text-based customer service conversations.
 
-[!INCLUDE [Use Language Studio](../use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../use-microsoft-foundry.md)]
 
 ## Prerequisites
 
@@ -161,19 +161,19 @@ with client:
                     {
                         "conversationItems": [
                             {
-                                "text": "Hello, you’re chatting with Rene. How may I help you?",
+                                "text": "Hello, you're chatting with Rene. How may I help you?",
                                 "id": "1",
                                 "role": "Agent",
                                 "participantId": "Agent_1",
                             },
                             {
-                                "text": "Hi, I tried to set up wifi connection for Smart Brew 300 coffee machine, but it didn’t work.",
+                                "text": "Hi, I tried to set up wifi connection for Smart Brew 300 coffee machine, but it didn't work.",
                                 "id": "2",
                                 "role": "Customer",
                                 "participantId": "Customer_1",
                             },
                             {
-                                "text": "I’m sorry to hear that. Let’s see what we can do to fix this issue. Could you please try the following steps for me? First, could you push the wifi connection button, hold for 3 seconds, then let me know if the power light is slowly blinking on and off every second?",
+                                "text": "I'm sorry to hear that. Let's see what we can do to fix this issue. Could you please try the following steps for me? First, could you push the wifi connection button, hold for 3 seconds, then let me know if the power light is slowly blinking on and off every second?",
                                 "id": "3",
                                 "role": "Agent",
                                 "participantId": "Agent_1",
@@ -197,7 +197,7 @@ with client:
                                 "participantId": "Customer_1",
                             },
                             {
-                                "text": "I’m very sorry to hear that. Let me see if there’s another way to fix the issue. Please hold on for a minute.",
+                                "text": "I'm very sorry to hear that. Let me see if there's another way to fix the issue. Please hold on for a minute.",
                                 "id": "7",
                                 "role": "Agent",
                                 "participantId": "Agent_1",

@@ -3,7 +3,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: include
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.author: lajanuar
 ---
 # [Text summarization](#tab/text-summarization)
@@ -14,15 +14,15 @@ ms.author: lajanuar
 
 ---
 
-Use this quickstart to send text summarization requests using the [REST API](/rest/api/language/analyze-documents/analyze-documents-submit-job/analyze-documents-submit-job?view=rest-language-analyze-documents-2024-11-15-preview&preserve-view=true&tabs=HTTP). In the following example, you will use cURL to summarize documents or text-based customer service conversations.
+Use this quickstart to send text summarization requests using the [REST API](/rest/api/language/analyze-documents/analyze-documents-submit-job/analyze-documents-submit-job?view=rest-language-analyze-documents-2024-11-15-preview&preserve-view=true&tabs=HTTP). In the following example, you use cURL to summarize documents or text-based customer service conversations.
 
-[!INCLUDE [Use Language Studio](../use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../use-microsoft-foundry.md)]
 
 ## Prerequisites
 
 * The current version of [cURL](https://curl.haxx.se/).
 * Once you have your Azure subscription, <[create a Foundry resource](../../../../../ai-services/multi-service-resource.md?pivots=azportal#create-your-first-resource).
-    * You will need the key and endpoint from the resource you create to connect your application to the API. You'll paste your key and endpoint into the code below later in the quickstart.
+    * You need the key and endpoint from the resource you create to connect your application to the API. You paste your key and endpoint into the code later in the quickstart.
     * You can use the free pricing tier (`Free F0`) to try the service, and upgrade later to a paid tier for production.
 
 
@@ -36,11 +36,11 @@ Use this quickstart to send text summarization requests using the [REST API](/re
 ## Example request
 
 > [!NOTE]
-> * The following BASH exaples use the `\` line continuation character. If your console or terminal uses a different line continuation character, use that character.
+> * The following BASH examples use the `\` line continuation character. If your console or terminal uses a different line continuation character, use that character.
 > * You can find language specific samples on [GitHub](https://github.com/Azure-Samples/cognitive-services-quickstart-code).
 To call the API, you need the following information:
 
-Choose the type of summarization you would like to perform, and select one of the tabs below to see an example API call:
+Choose the type of summarization you would like to perform, and select one of the tabs and see an example API call:
 
 | Feature | Description |
 |---------|-------------|
@@ -62,9 +62,9 @@ The following cURL commands are executed from a BASH shell. Edit these commands
 
 ### Text extractive summarization example
 
-The following example will get you started with text extractive summarization:
+The following example gets you started with text extractive summarization:
 
-1. Copy the command below into a text editor. The BASH example uses the `\` line continuation character. If your console or terminal uses a different line continuation character, use that character instead.
+1. Copy the command into a text editor. The BASH example uses the `\` line continuation character. If your console or terminal uses a different line continuation character, use that character instead.
 
 ```bash
 curl -i -X POST $LANGUAGE_ENDPOINT/language/analyze-text/jobs?api-version=2024-11-15-preview \
@@ -100,7 +100,7 @@ curl -i -X POST $LANGUAGE_ENDPOINT/language/analyze-text/jobs?api-version=2024-1
 
 3. Paste the command from the text editor into the command prompt window, then run the command.
 
-4. Get the `operation-location` from the response header. The value will look similar to the following URL:
+4. Get the `operation-location` from the response header. The value looks similar to the following URL:
 
 ```http
 https://<your-language-resource-endpoint>/language/analyze-text/jobs/12345678-1234-1234-1234-12345678?api-version=2024-11-15-preview
@@ -194,9 +194,9 @@ curl -X GET $LANGUAGE_ENDPOINT/language/analyze-text/jobs/<my-job-id>?api-versio
 
 ## Conversation issue and resolution summarization
 
-The following example will get you started with conversation issue and resolution summarization:
+The following example gets you started with conversation issue and resolution summarization:
 
-1. Copy the command below into a text editor. The BASH example uses the `\` line continuation character. If your console or terminal uses a different line continuation character, use that character instead.
+1. Copy the command into a text editor. The BASH example uses the `\` line continuation character. If your console or terminal uses a different line continuation character, use that character instead.
 
 ```bash
 curl -i -X POST $LANGUAGE_ENDPOINT/language/analyze-conversations/jobs?api-version=2024-11-15-preview \
@@ -279,13 +279,13 @@ curl -i -X POST $LANGUAGE_ENDPOINT/language/analyze-conversations/jobs?api-versi
 }
 '
 ```
-Only the `resolution` aspect supports sentenceCount. If you do not specify the `sentenceCount` parameter, the model will determine the summary's length. Note that `sentenceCount` is just the approximation of sentence count of output summary, range 1 to 7.
+Only the `resolution` aspect supports sentenceCount. If you don't specify the `sentenceCount` parameter, the model determines the summary's length. That `sentenceCount` is just the approximation of sentence count of output summary, range 1 to 7.
 
 2. Open a command prompt window (for example: BASH).
 
 3. Paste the command from the text editor into the command prompt window, then run the command.
 
-4. Get the `operation-location` from the response header. The value will look similar to the following URL:
+4. Get the `operation-location` from the response header. The value looks similar to the following URL:
 
 ```http
 https://<your-language-resource-endpoint>/language/analyze-conversations/jobs/12345678-1234-1234-1234-12345678?api-version=2024-11-15-preview

@@ -5,9 +5,9 @@
  author: laujan
  ms.service: azure-ai-language
  ms.topic: include
- ms.date: 11/05/2025
+ ms.date: 12/15/2025
  ms.author: lajanuar
 ms.custom: include, build-2024, ignite-2024
 ---
 > [!TIP]
-> You can use [**Microsoft Foundry**](../../../../ai-foundry/what-is-azure-ai-foundry.md) to try summarization without needing to write code. 
+> You can use [**Microsoft Foundry**](https://ai.azure.com/) to try summarization without needing to write code. 

@@ -7,7 +7,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: overview
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.author: lajanuar
 ms.custom: language-service-health
 ---
@@ -18,7 +18,7 @@ ms.custom: language-service-health
 Text Analytics for health is one of the prebuilt features offered by [Azure Language in Foundry Tools](../overview.md). Text Analytics for health uses machine learning to identify and label medical information in unstructured text such as doctor's notes, clinical documents, and electronic health records. It extracts key data from sources like discharge summaries to support healthcare analysis.
 
 > [!TIP]
-> Try out Text Analytics for health [in Microsoft Foundry portal](https://ai.azure.com/explore/language). There you can [utilize a currently existing Language Studio resource or create a new Foundry resource](../../../ai-services/connect-services-ai-foundry-portal.md) in order to use this service.
+> Try out Text Analytics for health [in Microsoft Foundry portal](https://ai.azure.com/). There you can [utilize a currently existing Language Studio resource or create a new Foundry resource](../../../ai-services/connect-services-ai-foundry-portal.md) in order to use this service.
 
 This documentation contains the following types of articles:
 * The [**quickstart article**](quickstart.md) provides a short tutorial that guides you with making your first request to the service.

@@ -7,7 +7,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: quickstart
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.author: lajanuar
 ms.devlang: csharp
 # ms.devlang: csharp, java, javascript, python
@@ -19,7 +19,7 @@ zone_pivot_groups: programming-languages-text-analytics
 
 This article contains Text Analytics for health quickstarts that help with using the supported client libraries, C#, Java, NodeJS, and Python and the REST API.
 
-[!INCLUDE [Use Language Studio](../includes/use-language-studio.md)]
+[!INCLUDE [Use Microsoft Foundry](../includes/use-microsoft-foundry.md)]
 ::: zone pivot="programming-language-csharp"
 
 [!INCLUDE [C# quickstart](includes/quickstarts/csharp-sdk.md)]