@@ -5,7 +5,7 @@ description: Learn about how to deploy your custom language projects to multiple
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 12/05/2025
 ms.author: lajanuar
 ms.custom: language-service-clu, ignite-2024
@@ -43,7 +43,7 @@ The same request body to each of those different URLs serves the exact same resp
 
 ## Validations and requirements
 
-Assigning deployment resources requires Microsoft Entra authentication. Microsoft Entra ID is used to confirm that you have access to the resources that you want to assign to your project for multiregion deployment. In Language Studio, you can automatically [enable Microsoft Entra authentication](https://aka.ms/rbac-language) by assigning yourself the Azure Cognitive Services Language Owner role to your original resource. To programmatically use Microsoft Entra authentication, learn more from the [Foundry Tools documentation](../../../authentication.md?source=docs&tabs=powershell&tryIt=true#authenticate-with-azure-active-directory).
+Assigning deployment resources requires Microsoft Entra authentication. Microsoft Entra ID is used to confirm that you have access to the resources that you want to assign to your project for multiregion deployment. In Microsoft Foundry, you can automatically [enable Microsoft Entra authentication](https://aka.ms/rbac-language) by assigning yourself the Azure Cognitive Services Language Owner role to your original resource. To programmatically use Microsoft Entra authentication, learn more from the [Foundry Tools documentation](../../../authentication.md?source=docs&tabs=powershell&tryIt=true#authenticate-with-azure-active-directory).
 
 Your project name and resource are used as its main identifiers. A Language resource can only have a specific project name in each resource. Any other projects with the same name can't be deployed to that resource.
 

@@ -22,7 +22,7 @@ ms.reviewer: haelhamm
 
 Building your project typically happens in increments. You may add, remove, or edit intents, entities, labels, and data at each stage. Every time you train, a snapshot of your current project state is taken to produce a model. That model saves the snapshot to be loaded back at any time. Every model acts as its own version of the project.
 
-For example, if your project has 10 intents and/or entities, with 50 training documents or utterances, it can be trained to create a model named **v1**. Afterwards, you might make changes to the project to alter the numbers of training data. The project can be trained again to create a new model named **v2**. If you don't like the changes you made in **v2** and would like to continue from where you left off in model **v1**, then you would just need to load the model data from **v1** back into the project. Loading a model's data is possible through both Azure Language Studio and API. Once complete, the project has the original amount and types of training data.
+For example, if your project has 10 intents and/or entities, with 50 training documents or utterances, it can be trained to create a model named **v1**. Afterwards, you might make changes to the project to alter the numbers of training data. The project can be trained again to create a new model named **v2**. If you don't like the changes you made in **v2** and would like to continue from where you left off in model **v1**, then you would just need to load the model data from **v1** back into the project. Loading a model's data is possible through both Microsoft Foundry and API. Once complete, the project has the original amount and types of training data.
 
 If the project data isn't saved in a trained model, it can be lost. For example, if you loaded model **v1**, your project now has the data that was used to train it. If you then made changes, didn't train, and loaded model **v2**, you would lose those changes as they weren't saved to any specific snapshot.
 

@@ -5,7 +5,7 @@ description: Learn about how to integrate Azure Language service SDK and REST AP
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 11/18/2025
 ms.author: lajanuar
 ---
@@ -40,7 +40,7 @@ The Language provides three namespaces for using the available features. Dependi
 The `Azure.AI.TextAnalytics` namespace enables you to use the following Language features. Use the following links for articles to help you send API requests using the SDK.
 
 * [Custom named entity recognition](../custom-named-entity-recognition/how-to/call-api.md?tabs=client)
-* [Custom text classification](../custom-text-classification/how-to/call-api.md?tabs=client-libraries#send-a-text-classification-request-to-your-model)
+* [Custom text classification](../custom-text-classification/how-to/call-api.md#send-a-text-classification-request-to-your-model-rest-api)
 * [Document summarization](../summarization/quickstart.md)
 * [Entity linking](../entity-linking/quickstart.md)
 * [Key phrase extraction](../key-phrase-extraction/quickstart.md)
@@ -107,7 +107,7 @@ The conversation analysis authoring API enables you to author custom models and
 * [Conversational language understanding](../conversational-language-understanding/quickstart.md?pivots=rest-api)
 * [Orchestration workflow](../orchestration-workflow/quickstart.md?pivots=rest-api)
 
-For more information, *see* the [reference documentation](/rest/api/language/2023-04-01/conversational-analysis-authoring).
+For more information, *see* the [reference documentation](/rest/api/language/).
 
 ### Conversation analysis runtime API
 
@@ -128,7 +128,7 @@ The text analysis authoring API enables you to author custom models and create/m
 * [Custom named entity recognition](../custom-named-entity-recognition/quickstart.md?pivots=rest-api)
 * [Custom text classification](../custom-text-classification/quickstart.md?pivots=rest-api)
 
-For more information, *see* the [reference documentation](/rest/api/language/2023-04-01/text-analysis-authoring).
+For more information, *see* the [reference documentation](/rest/api/language/).
 ### Text analysis runtime API
 
 The text analysis runtime API enables you to send requests to custom models you create for the following features:

@@ -5,18 +5,18 @@ description: Learn about the data formats accepted by custom NER.
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 11/18/2025
 ms.author: lajanuar
 ms.custom: language-service-custom-ner
 ---
 # Accepted custom NER data formats
 
-If you're trying to [import your data](../how-to/create-project.md#import-project) into custom NER, it has to follow a specific format. If you don't have data to import, you can [create your project](../how-to/create-project.md) and use [Microsoft Foundry](https://ai.azure.com/) to label your documents.
+If you're trying to [import your data](../how-to/create-project.md#import-project-rest-api) into custom NER, it has to follow a specific format. If you don't have data to import, you can [create your project](../how-to/create-project.md) and use [Microsoft Foundry](https://ai.azure.com/) to label your documents.
 
 ## Labels file format
 
-Your Labels file should be in `json` format for use in [importing](../how-to/create-project.md#import-project) your labels into a project.
+Your Labels file should be in `json` format for use in [importing](../how-to/create-project.md#import-project-rest-api) your labels into a project.
 
 ```json
 {
@@ -108,5 +108,5 @@ Your Labels file should be in `json` format for use in [importing](../how-to/cre
 
 
 ## Next steps
-* You can import your labeled data into your project directly. Learn how to [import project](../how-to/create-project.md#import-project)
+* You can import your labeled data into your project directly. Learn how to [import project](../how-to/create-project.md#import-project-rest-api)
 * See the [how-to article](../how-to/tag-data.md)  more information about labeling your data. When you're done labeling your data, you can [train your model](../how-to/train-model.md).  

@@ -42,8 +42,6 @@ You can create a resource in the following ways:
 
 [!INCLUDE [create a new resource from the Azure portal](../includes/resource-creation-azure-portal.md)]
 
-[!INCLUDE [create a new resource from Language Studio](../includes/language-studio/resource-creation-language-studio.md)]
-
 [!INCLUDE [create a new resource with Azure PowerShell](../includes/resource-creation-powershell.md)]
 
 
@@ -55,58 +53,26 @@ You can create a resource in the following ways:
 
 [!INCLUDE [use an existing resource](../includes/use-pre-existing-resource.md)]
 
-## Create a custom named entity recognition project
-
-Once your resource and storage container are configured, create a new custom NER project. A project is a work area for building your custom AI models based on your data. Only you can access your project along with others who have access to the Azure resource being used. If you labeled data, you can use it to get started by [importing a project](#import-project).
-
-### [Language Studio](#tab/language-studio)
+## Create a custom named entity recognition project (REST API)
 
-[!INCLUDE [Language Studio project creation](../includes/language-studio/create-project.md)]
-
-### [REST APIs](#tab/rest-api)
+Once your resource and storage container are configured, create a new custom NER project. A project is a work area for building your custom AI models based on your data. Only you can access your project along with others who have access to the Azure resource being used. If you labeled data, you can use it to get started by [importing a project](#import-project-rest-api).
 
 [!INCLUDE [REST APIs project creation](../includes/rest-api/create-project.md)]
 
----
-
-## Import project
+## Import project (REST API)
 
 If you already labeled data, you can use it to get started with the service. Make sure that your labeled data follows the [accepted data formats](../concepts/data-formats.md).
 
-### [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Import project](../includes/language-studio/import-project.md)]
-
-### [REST APIs](#tab/rest-api)
-
 [!INCLUDE [Import project](../includes/rest-api/import-project.md)]
 
----
-
-## Get project details
-
-### [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Language Studio project details](../includes/language-studio/project-details.md)]
-
-### [REST APIs](#tab/rest-api)
+## Get project details (REST API)
 
 [!INCLUDE [REST APIs project details](../includes/rest-api/project-details.md)]
 
----
-
-## Delete project
-
-### [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Delete project using Language studio](../includes/language-studio/delete-project.md)]
-
-### [REST APIs](#tab/rest-api)
+## Delete project (REST API)
 
 [!INCLUDE [Delete project using the REST API](../includes/rest-api/delete-project.md)]
 
----
-
 ## Next steps
 
 * You should have an idea of the [project schema](design-schema.md) you use to label your data.

@@ -64,7 +64,7 @@ You can upload an annotated dataset, or you can upload an unannotated one and la
  
 ## Test set
 
-When defining the testing set, make sure to include example documents that aren't present in the training set. Defining the testing set is an important step to calculate the [model performance](view-model-evaluation.md#model-details). Also, make sure that the testing set include documents that represent all entities used in your project.
+When defining the testing set, make sure to include example documents that aren't present in the training set. Defining the testing set is an important step to calculating the [model performance](view-model-evaluation.md#model-details-rest-api). Also, make sure that the testing set includes documents that represent all entities used in your project.
 
 ## Next steps
 

@@ -12,7 +12,7 @@ ms.custom: language-service-custom-ner
 ---
 # Label your data in Azure Language in Foundry Tools Studio
 
-Before training your model, you need to label your documents with the custom entities you want to extract. Data labeling is a crucial step in development lifecycle. You can create the entity types you want to extract from your data and label these entities within your documents. This data is used in the next step when training your model so that your model can learn from the labeled data. If you already labeled data, you can directly [import](create-project.md#import-project) it into your project, but you need to make sure that your data follows the [accepted data format](../concepts/data-formats.md). See [create project](create-project.md#import-project) to learn more about importing labeled data into your project.
+Before training your model, you need to label your documents with the custom entities you want to extract. Data labeling is a crucial step in development lifecycle. You can create the entity types you want to extract from your data and label these entities within your documents. This data is used in the next step when training your model so that your model can learn from the labeled data. If you already labeled data, you can directly [import](create-project.md#import-project-rest-api) it into your project, but you need to make sure that your data follows the [accepted data format](../concepts/data-formats.md). See [create project](create-project.md#import-project-rest-api) to learn more about importing labeled data into your project.
 
 Before creating a custom NER model, you first need to label your data. If your data isn't labeled already, you can label it in the [Language Studio](https://aka.ms/languageStudio). Labeled data informs the model how to interpret text, and is used for training and evaluation.
 

@@ -44,38 +44,27 @@ Custom NER supports two methods for data splitting:
 
 * **Use a manual split of training and testing data**: This method enables users to define which labeled documents should belong to which set. This step is only enabled if you added documents to your testing set during [data labeling](tag-data.md).
 
-## Train model
+## Train model (REST API)
 
-# [Language studio](#tab/Language-studio)
-
-[!INCLUDE [Train model](../includes/language-studio/train-model.md)]
-
-# [REST APIs](#tab/REST-APIs)
+Once you have labeled your data and configured your data split settings, you can start training your custom NER model using the REST API. The training process involves submitting a training job request and monitoring its progress until completion. This section provides the API calls needed to initiate training and check the status of your training job.
 
 ### Start training job
 
 [!INCLUDE [train model](../includes/rest-api/train-model.md)]
 
-### Get training job status
+### Get training job status (REST API)
 
 Training can take some time, depending on the size of your training data and complexity of your schema. You can use the following request to keep polling the status of the training job until successful completion.
 
  [!INCLUDE [get training model status](../includes/rest-api/get-training-status.md)]
 
----
-
-### Cancel training job
 
-# [Language Studio](#tab/language-studio)
+### Cancel training job (REST API)
 
-[!INCLUDE [Cancel training](../includes/language-studio/cancel-training.md)]
-
-# [REST APIs](#tab/rest-api)
+If you need to stop a training job that's currently in progress, you can cancel it using the REST API. Canceling a training job is useful when you discover an issue with your data or configuration and want to make corrections before restarting the training process.
 
 [!INCLUDE [Cancel training](../includes/rest-api/cancel-training.md)]
 
----
-
 ## Next steps
 
 After training is completed, you'll be able to view [model performance](view-model-evaluation.md) to optionally improve your model if needed. Once you're satisfied with your model, you can deploy it, making it available to use for [extracting entities](call-api.md) from text.

@@ -12,7 +12,7 @@ ms.custom: language-service-custom-ner
 ---
 # View the custom NER model's evaluation and details
 
-After your model has finished training, you can view the model performance and see the extracted entities for the documents in the test set. 
+After your model finishes training, you can view the model performance and see the extracted entities for the documents in the test set. 
 
 > [!NOTE]
 > Using the **Automatically split the testing set from training data** option may result in different model evaluation result every time you [train a new model](train-model.md), as the test set is selected randomly from the data. To make sure that the evaluation is calculated on the same test set every time you train a model, make sure to use the **Use a manual split of training and testing data** option when starting a training job and define your **Test** documents when [labeling data](tag-data.md).
@@ -26,45 +26,21 @@ Before viewing model evaluation, you need:
 * [Labeled data](tag-data.md)
 * A [successfully trained model](train-model.md)
 
-See the [project development lifecycle](../overview.md#project-development-lifecycle) for more information.
+For more information, *see* the [project development lifecycle](../overview.md#project-development-lifecycle).
 
-## Model details
-
-### [Language studio](#tab/language-studio)
-
-[!INCLUDE [View model evaluation using Language Studio](../includes/language-studio/model-evaluation.md)]
-
-### [REST APIs](#tab/rest-api)
+## Model details (REST API)
 
 [!INCLUDE [Model evaluation](../includes/rest-api/model-evaluation.md)]
 
----
-
-## Load or export model data
-
-### [Language studio](#tab/Language-studio)
 
-[!INCLUDE [Load export model](../../conversational-language-understanding/includes/language-studio/load-export-model.md)]
+## Load or export model data (REST API)
 
+[!INCLUDE [Load export model](../includes/rest-api/load-export-model.md)]
 
-### [REST APIs](#tab/REST-APIs)
-
-[!INCLUDE [Load export model](../../custom-text-classification/includes/rest-api/load-export-model.md)]
-
----
-
-## Delete model
-
-### [Language studio](#tab/language-studio)
-
-[!INCLUDE [Delete model](../includes/language-studio/delete-model.md)]
-
-### [REST APIs](#tab/rest-api)
+## Delete model (REST API)
 
 [!INCLUDE [Delete model](../includes/rest-api/delete-model.md)]
 
----
-
 ## Next steps
 
 * [Deploy your model](deploy-model.md)

@@ -1,9 +0,0 @@
----
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-To cancel a training job from within [Language Studio](https://aka.ms/languageStudio), go to the **Training jobs** page. Select the training job you want to cancel and select **Cancel** from the top menu. 

@@ -1,36 +0,0 @@
----
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-1. Sign into the [Language Studio](https://aka.ms/languageStudio). A window appears to let you select your subscription and Language resource. Select Azure Language resource you created in the previous step. 
-
-2. Under the **Extract information** section of Language Studio, select **Custom named entity recognition**.
-
-    :::image type="content" source="../../media/select-custom-ner.png" alt-text="A screenshot showing the location of custom named entity recognition (NER) in Azure Language Studio landing page." lightbox="../../media/select-custom-ner.png":::
-
-3. Select **Create new project** from the top menu in your projects page. Creating a project lets you tag data, train, evaluate, improve, and deploy your models. 
-
-    :::image type="content" source="../../media/create-project.png" alt-text="A screenshot of the project creation page." lightbox="../../media/create-project.png":::
-
-4.  After you select, **Create new project**, a window appears to let you connect your storage account. If you already connected a storage account, the connected storage accounted appears in the window. If not, choose your storage account from the dropdown that appears and select **Connect storage account**; this sets the required roles for your storage account. This step can return an error if you aren't assigned as **owner** on the storage account.
-
-    >[!NOTE]
-    > * You only need to do this step once for each new resource you use. 
-    > * This process is irreversible, if you connect a storage account to your Language resource you can't disconnect it later.
-    > * You can only connect your Language resource to one storage account.
-    
-    :::image type="content" source="../../media/connect-storage.png" alt-text="A screenshot showing the storage connection screen." lightbox="../../media/connect-storage.png":::
-
-5. Enter the project information, including a name, description, and the language of the files in your project. If you're using the [example dataset](https://go.microsoft.com/fwlink/?linkid=2175226), select **English**. You can't change the name of your project later. Select **Next**
-
-    > [!TIP]
-    > Your dataset doesn't have to be entirely in the same language. You can have multiple documents, each with different supported languages. If your dataset contains documents of different languages or if you expect text from different languages during runtime, select **enable multi-lingual dataset** option when you enter the basic information for your project. This option can be enabled later from the **Project settings** page.
-
-6. Select the container where you uploaded your dataset. 
-If you already labeled data make sure it follows the [supported format](../../concepts/data-formats.md) and select **Yes, my files are already labeled and I have formatted JSON labels file** and select the labels file from the drop-down menu. Select **Next**.
-
-7. Review the data you entered and select **Create Project**.

@@ -1,10 +0,0 @@
----
-titleSuffix: Foundry Tools
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-To delete a deployment from within [Language Studio](https://aka.ms/laguageStudio), go to the **Deploying a model** page. Select the deployment you want to delete and select **Delete deployment** from the top menu. 

@@ -1,15 +0,0 @@
----
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-To delete your model from within the [Language Studio](https://aka.ms/LanguageStudio):
-
-1. Select **Model performance** from the left side menu.
-
-2. Select the **model name** you want to delete and select **Delete** from the top menu.
-
-3. In the window that appears, select **OK** to delete the model. 

@@ -1,10 +0,0 @@
----
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
-ms.custom: language-service-custom-classification
----
-When you don't need your project anymore, you can delete your project using [Language Studio](https://aka.ms/custom-extraction). Select **Custom named entity recognition (NER)** from the top, select the project you want to delete, and then select **Delete** from the top menu.

@@ -1,26 +0,0 @@
----
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-To deploy your model from within the [Language Studio](https://aka.ms/LanguageStudio):
-
-1. Select **Deploying a model** from the left side menu.
-
-2. Select **Add deployment** to start a new deployment job.
-
-    :::image type="content" source="../../media/deploy-model.png" alt-text="A screenshot showing the deployment button" lightbox="../../media/deploy-model.png":::
-
-3. Select **Create new deployment** to create a new deployment and assign a trained model from the dropdown. You can also **Overwrite an existing deployment** by selecting this option and select the trained model you want to assign to it from the dropdown.
-
-    > [!NOTE]
-    > Overwriting an existing deployment doesn't require changes to your [prediction API](https://aka.ms/ct-runtime-swagger) call but the results you get are based on the newly assigned model.
-    
-   :::image type="content" source="../../media/add-deployment.png" alt-text="A screenshot showing the deployment screen" lightbox="../../media/add-deployment.png":::
-     
-4. Select **Deploy** to start the deployment job.
-
-5. After deployment is successful, an expiration date will appear next to it. [Deployment expiration](../../../concepts/model-lifecycle.md#expiration-timeline) is when your deployed model will be unavailable to be used for prediction, which typically happens **twelve** months after a training configuration expires.

@@ -1,42 +0,0 @@
----
-titleSuffix: Foundry Tools
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-1. Sign into the [Language Studio](https://aka.ms/languageStudio). A window appears to let you select your subscription and Language resource. Select your Language resource. 
-
-2. Under the **Extract information** section of Language Studio, select **Custom named entity recognition**.
-
-    :::image type="content" source="../../media/select-custom-ner.png" alt-text="A screenshot showing the location of the custom `NER` feature in Azure Language Studio landing page." lightbox="../../media/select-custom-ner.png":::
-        
-
-3. Select **Create new project** from the top menu in your projects page. Creating a project lets you tag data, train, evaluate, improve, and deploy your models. 
-
-    :::image type="content" source="../../media/create-project.png" alt-text="A screenshot of the project creation page." lightbox="../../media/create-project.png":::
-
-
-4.  After you select **Create new project**, a screen will appear to let you connect your storage account. If you can't find your storage account, make sure you created a resource using the recommended steps. If you've already connected a storage account to your Language resource, you can see your storage account connected.
-
-    >[!NOTE]
-    > * You only need to do this step once for each new language resource you use. 
-    > * This process is irreversible, if you connect a storage account to your Language resource you can't disconnect it later.
-    > * You can only connect your Language resource to one storage account.
-
-    :::image type="content" source="../../media/connect-storage.png" alt-text="A screenshot of the storage connection screen for new projects." lightbox="../../media/connect-storage.png":::
-
-4. Enter the project information, including a name, description, and the language of the files in your project. You can't change the name of your project later. Select **Next**.
-       
-    >[!TIP]
-    > Your dataset doesn't have to be entirely in the same language. You can have multiple documents, each with different supported languages. If your dataset contains documents of different languages or if you expect text from different languages during runtime, select **enable multi-lingual dataset** option when you enter the basic information for your project. This option can be enabled later from the **Project settings** page.
-
-5. Select the container where you uploaded your dataset. 
-
-7. Select **Yes, my files are already labeled and I have formatted JSON labels file** and select the labels file from the drop-down menu to import your JSON labels file. Make sure it follows the [supported format](../../concepts/data-formats.md).
-
-8.   Select **Next**.
-
-9. Review the data you entered and select **Create Project**.

@@ -1,82 +0,0 @@
----
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-1. Go to your project page in [Language Studio](https://aka.ms/languageStudio).
-
-2. Select **Model performance** from the menu on the left side of the screen.
-
-3. On this page, you can only view the successfully trained models, F1 score for each model and [model expiration date](../../../concepts/model-lifecycle.md). You can select the model name for more details about its performance.
-
-> [!NOTE]
-> Entities that aren't labeled or predicted in the test set aren't part of the displayed results.
-
-### [Overview](#tab/overview)
-
-* In this tab you can view the model's details such as: F1 score, precision, recall, date, and time for the training job, total training time, and number of training and testing documents included in this training job.
-
-    :::image type="content" source="../../media/overview.png" alt-text="A screenshot that shows the overview page for model evaluation." lightbox="../../media/overview.png":::
-
-* You can also see [guidance](../../concepts/evaluation-metrics.md#guidance) on how to improve the model. When you select *view details*, a side panel opens to give more guidance on how to improve the model. In this example, *BorrowerAddress* and *BorrowerName* entities are confused with *$none* entity. By selecting the confused entities, you're taken to the [data labeling](../../how-to/tag-data.md) page to label more data with the correct entity.
-
-    :::image type="content" source="../../media/overview-guidance.png" alt-text="A screenshot that shows the guidance page for model evaluation." lightbox="../../media/overview-guidance.png":::
-
-    Learn more about model guidance and confusion matrix in [model performance](../../concepts/evaluation-metrics.md) concepts.
-
-### [Entity type performance](#tab/entity-performance)
-
-* This view is a snapshot of how your model performed during testing. The metrics here are static and tied to your model, so they don't update until you train again.
-
-* You can see for each entity, precision, recall, F1 score, number of training and testing labels.
-
-
-    :::image type="content" source="../../media/entity-type-performace.png" alt-text="A screenshot of entity performance." lightbox="../../media/entity-type-performace.png":::
-
-### [Test set details](#tab/test-set)
-
-* Here you can see the documents included in the **test set** and the result entity type for each document. You can use the *Show mismatches only* toggle to show only documents with mismatches, or unselect the toggle to view all document in the test set.
-
-* For each document, you can view: labeled text, its respective labeled entity type and what entity it was predicted with. Also, you can see whether it's a [true positive](../../concepts/evaluation-metrics.md), [false positive](../../concepts/evaluation-metrics.md), or [false negative](../../concepts/evaluation-metrics.md).
-
-    :::image type="content" source="../../media/test-set.png" alt-text="A screenshot of test set details." lightbox="../../media/test-set.png":::
-
-
-### [Dataset distribution](#tab/dataset-distribution)
-
-This snapshot shows how entities are distributed across your training and testing sets. This data is static and tied to your model, so it doesn't update until you train again.
-
-* You can view the dataset distribution in *graph* or *table* view.
-
-**Graph view**
-
-* *Documents with at least one label*: This view shows for each entity, the number of occurrences for this entity across the training and testing sets.
-
-* *Total instances throughout documents*: This view shows for each entity, the labeled occurrences across training and testing sets.
-
-  :::image type="content" source="../../media/dataset-graph.png" alt-text="A screenshot showing distribution in graph view." lightbox="../../media/dataset-graph.png":::
-
-**Table view**
-
-For each *entity*, you can view: tags per entity in training set; tagged documents in training set; tags per entity in testing set; tagged documents in testing set; tags per entity total; and tagged documents total.
-
-  :::image type="content" source="../../media/dataset-table.png" alt-text="A screenshot showing distribution in table view." lightbox="../../media/dataset-table.png":::
-
-### [Confusion matrix](#tab/confusion-matrix)
-
-A [confusion matrix](../../concepts/evaluation-metrics.md#confusion-matrix) is an N x N matrix used for evaluating the performance of a classification model, where N is the number of target entities. The matrix compares the actual target values with those values predicted by the machine learning model to show how well the extraction model is performing and what kinds of errors it's making.
-
-You can view the confusion matrix in *normalized* or *raw count* view.
-
-  :::image type="content" source="../../media/confusion.png" alt-text="A screenshot of a confusion matrix in Language Studio." lightbox="../../media/confusion.png":::
-
-* All values: Shows the confusion matrix for all entities.
-
-* Only errors: Shows the confusion matrix for entities with errors only.
-
-* Only matches: Shows the confusion matrix for entities with correct predictions only.
-
----

@@ -1,20 +0,0 @@
----
-titleSuffix: Foundry Tools
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-1. Go to your **project settings** page in [Language Studio](https://aka.ms/languageStudio).
-
-2. You can see project details.
-
-3. On this page, you can update project description and enable/disable Multi-lingual dataset in project settings.
-
-4. You can also view the connected storage account and container to your Language resource.
-
-5. You can also retrieve your primary resource key from this page.
-
-    :::image type="content" source="../../media/project-details.png" alt-text="A screenshot of the project settings page in Language Studio." lightbox="../../media/project-details.png":::

@@ -1,28 +0,0 @@
----
-titleSuffix: Foundry Tools
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-### Create a new Language resource from Language Studio
-
-If it's your first time logging in, you'll see a window in [Language Studio](https://aka.ms/languageStudio) that lets you choose an existing Language resource or create a new one. You can also create a resource by clicking the settings icon in the top-right corner, selecting **Resources**, then clicking **Create a new resource**.
-
-Create a Language resource with following details.
-
-|Instance detail  |Required value  |
-|---------|---------|
-|Azure subscription| **Your Azure subscription**|
-|Azure resource group| **Your Azure resource group**|
-|Azure resource name| **Your Azure resource name**|
-|Location | The [region](../../service-limits.md#regional-availability) of your Language resource.      |
-|Pricing tier     | The [pricing tier](../../service-limits.md#language-resource-limits) of your Language resource.        |
-
-> [!IMPORTANT]
-> * Make sure to enable **Managed Identity** when you create a Language resource. 
-> * Read and confirm Responsible AI notice
-
-To use custom named entity recognition, you need to [create an Azure storage account](/azure/storage/common/storage-account-create) if you don't have one already. 

@@ -1,14 +0,0 @@
----
-titleSuffix: Foundry Tools
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-To swap deployments from within [Language Studio](https://aka.ms/laguageStudio):
-
-1. In the **Deploying a model** page, select the two deployments you want to swap and select **Swap deployments** from the top menu. 
-
-2. From the window that appears, select the names of the deployments you want to swap.

@@ -1,28 +0,0 @@
----
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: include
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-To start training your model from within the [Language Studio](https://aka.ms/LanguageStudio):
-
-1. Select **Training jobs** from the left side menu.
-
-2. Select **Start a training job** from the top menu.
-
-3. Select **Train a new model** and type in the model name in the text box. You can also **overwrite an existing model** by selecting this option and choosing the model you want to overwrite from the dropdown menu. Overwriting a trained model is irreversible, but it doesn't affect your deployed models until you deploy the new model.
-
-    :::image type="content" source="../../media/train-model.png" alt-text="Create a new training job" lightbox="../../media/train-model.png":::
-    
-4. Select data splitting method. You can choose **Automatically splitting the testing set from training data** where the system splits your labeled data between the training and testing sets, according to the specified percentages. Or you can **Use a manual split of training and testing data**, this option is only enabled if you added documents to your testing set during [data labeling](../../how-to/tag-data.md). See [How to train a model](../../how-to/train-model.md#data-splitting) for information about data splitting.
-
-4. Select the **Train** button.
-
-5. If you select the Training Job ID from the list, a side pane appears where you can check the **Training progress**, **Job status**, and other details for this job.
-
-    > [!NOTE]
-    > * Only successfully completed training jobs generate models.
-    > * Training can take some time between a couple of minutes and several hours based on the size of your labeled data.
-    > * You can only have one training job running at a time. You can't start other training job within the same project until the running job is completed.

@@ -0,0 +1,81 @@
+---
+author: laujan
+manager: nitinme
+ms.service: azure-ai-language
+ms.topic: include
+ms.date: 11/18/2025
+ms.author: lajanuar
+
+---
+### Load model data 
+
+Create a **POST** request using the following URL, headers, and JSON body to load your model data to your project.
+
+### Request URL
+
+Use the following URL when creating your API request. Replace the placeholder values with your own values. 
+
+```rest
+{ENDPOINT}/language/authoring/analyze-text/projects/{PROJECT-NAME}/models/{MODEL-NAME}:load-snapshot?stringIndexType=Utf16CodeUnit&api-version={API-VERSION}
+```
+
+|Placeholder  |Value  | Example |
+|---------|---------|---------|
+|`{ENDPOINT}`     | The endpoint for authenticating your API request.   | `https://<your-custom-subdomain>.cognitiveservices.azure.com` |
+|`{PROJECT-NAME}`     | The name for your project. This value is case-sensitive.   | `EmailApp` |
+|`{API-VERSION}`     | The version of the API you're calling. | `2022-10-01-preview` |
+|`{MODEL-NAME}`       | The name of your model. This value is case-sensitive. | `v1` |
+
+### Headers
+
+Use the following header to authenticate your request. 
+
+|Key|Value|
+|--|--|
+|`Ocp-Apim-Subscription-Key`| The key to your resource. Used for authenticating your API requests.|
+
+
+Once you send your API request, you receive a `202` response indicating success. In the response headers, extract the `operation-location` value formatted like this: 
+
+```rest
+{ENDPOINT}/language/authoring/analyze-text/projects/{PROJECT-NAME}/models/{MODEL-NAME}/jobs/{JOB-ID}?api-version={API-VERSION}
+``` 
+
+`JOB-ID` is used to identify your request, since this operation is asynchronous. Use this URL to get the status of your model data loading, using the same authentication method.
+
+
+### Export model data
+
+Create a **POST** request using the following URL, headers, and JSON body to export your model data.
+
+### Request URL
+
+Use the following URL when creating your API request. Replace the placeholder values with your own values. 
+
+```rest
+{ENDPOINT}/language/authoring/analyze-text/projects/{PROJECT-NAME}/:export?stringIndexType=Utf16CodeUnit&api-version={API-VERSION}&trainedModelLabel={MODEL-NAME}
+```
+
+|Placeholder  |Value  | Example |
+|---------|---------|---------|
+|`{ENDPOINT}`     | The endpoint for authenticating your API request.   | `https://<your-custom-subdomain>.cognitiveservices.azure.com` |
+|`{PROJECT-NAME}`     | The name for your project. This value is case-sensitive.   | `EmailApp` |
+|`{API-VERSION}`     | The version of the API you're calling. | `2022-10-01-preview` |
+|`{MODEL-NAME}`       | The name of your model. This value is case-sensitive. | `v1` |
+
+### Headers
+
+Use the following header to authenticate your request. 
+
+|Key|Value|
+|--|--|
+|`Ocp-Apim-Subscription-Key`| The key to your resource. Used for authenticating your API requests.|
+
+
+Once you send your API request, you receive a `202` response indicating success. In the response headers, extract the `operation-location` value formatted like this: 
+
+```rest
+{ENDPOINT}/language/authoring/analyze-text/projects/{PROJECT-NAME}/jobs/{JOB-ID}?api-version={API-VERSION}
+``` 
+
+`JOB-ID` is used to identify your request, since this operation is asynchronous. Use this URL to get the exported project JSON, using the same authentication method.

@@ -6,18 +6,18 @@ description: Learn about the data formats accepted by custom text classification
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
-ms.topic: conceptual
-ms.date: 11/18/2025
+ms.topic: concept-article
+ms.date: 12/15/2025
 ms.author: lajanuar
 ms.custom: language-service-custom-classification
 ---
 # Accepted data formats
 
-If you're trying to import your data into custom text classification, it has to follow a specific format. If you don't have data to import, you can [create your project](../how-to/create-project.md) and use Language Studio to [label your documents](../how-to/tag-data.md).
+If you're trying to import your data into custom text classification, it has to follow a specific format. If you don't have data to import, you can [create your project](../how-to/create-project.md) and use Microsoft Foundry to [label your documents](../how-to/tag-data.md).
 
 ## Labels file format
 
-Your Labels file should be in the `json` format to enable you to [import](../how-to/create-project.md#import-a-custom-text-classification-project) your labels into a project.
+Your Labels file should be in the `json` format to enable you to [import](../how-to/create-project.md#import-a-custom-text-classification-project-rest-api) your labels into a project.
 
 # [Multi label classification](#tab/multi-classification)
 
@@ -135,5 +135,5 @@ Your Labels file should be in the `json` format to enable you to [import](../how
 
 ## Next steps
 
-* You can import your labeled data into your project directly. See [How to create a project](../how-to/create-project.md#import-a-custom-text-classification-project) to learn more about importing projects.
+* You can import your labeled data into your project directly. See [How to create a project](../how-to/create-project.md#import-a-custom-text-classification-project-rest-api) to learn more about importing projects.
 * See the [how-to article](../how-to/tag-data.md) more information about labeling your data. When you're done labeling your data, you can [train your model](../how-to/train-model.md).  

@@ -6,7 +6,7 @@ description: Learn about evaluation metrics in custom text classification.
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 11/18/2025
 ms.author: lajanuar
 ms.custom: language-service-custom-classification
@@ -151,5 +151,4 @@ Similarly,
 
 ## Next steps
 
-* [View a model's performance in Language Studio](../how-to/view-model-evaluation.md)
 * [Train a model](../how-to/train-model.md)

@@ -7,7 +7,7 @@ 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-custom-classification
 ---

@@ -43,7 +43,7 @@ When you're ready to start [using your model to make predictions](#how-do-i-use-
 
 ## What is the recommended CI/CD process?
 
-You can train multiple models on the same dataset within the same project. After you train your model successfully, you can [view its evaluation](how-to/view-model-evaluation.md). You can [deploy and test](quickstart.md#deploy-your-model) your model within [Language studio](https://aka.ms/languageStudio). You can add or remove tags from your data and train a **new** model and test it as well. View [service limits](service-limits.md)to learn about maximum number of trained models with the same project. When you [tag your data](how-to/tag-data.md#label-your-data), you can determine how your dataset is split into training and testing sets.
+You can train multiple models on the same dataset within the same project. After you train your model successfully, you can [view its evaluation](how-to/view-model-evaluation.md). You can [deploy and test](quickstart.md#deploy-your-model) your model within [Microsoft Foundry](https://ai.azure.com/). You can add or remove tags from your data and train a **new** model and test it as well. View [service limits](service-limits.md)to learn about maximum number of trained models with the same project. When you [tag your data](how-to/tag-data.md#label-your-data), you can determine how your dataset is split into training and testing sets.
 
 ## Does a low or high model score guarantee bad or good performance in production?
 

@@ -6,7 +6,7 @@ description: Learn about definitions used in custom text classification.
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
-ms.topic: conceptual
+ms.topic: glossary
 ms.date: 11/18/2025
 ms.author: lajanuar
 ms.custom: language-service-custom-classification

@@ -16,81 +16,60 @@ ms.custom: language-service-clu
 # Send text classification requests to your model
 
 After you successfully deploy a model, you can query the deployment to classify text based on the model you assigned to the deployment.
-You can query the deployment programmatically [Prediction API](/rest/api/language/analyze-text/analyze-text/analyze-text?view=rest-language-analyze-text-2025-11-01&tabs=HTTP&preserve-view=true) or through the client libraries (Azure SDK). 
+You can query the deployment programmatically [Prediction API](/rest/api/language/analyze-text/analyze-text/analyze-text?view=rest-language-analyze-text-2025-11-01&tabs=HTTP&preserve-view=true) or through the client libraries (Azure SDK).
 
-## Test deployed model
-
-You can use Language Studio to submit the custom text classification task and visualize the results. 
-
-[!INCLUDE [Test model](../../includes/custom/language-studio/test-model.md)]
-
-
-:::image type="content" source="../media/test-model-results.png" alt-text="A screenshot showing model test results for a single label classification project." lightbox="../media/test-model-results.png":::
-
-
-## Send a text classification request to your model
-
-> [!TIP]
-> You can [test your model in Language Studio](../quickstart.md?pivots=language-studio#test-your-model) by sending sample text to classify it.
-
-# [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Get prediction URL](../../includes/custom/language-studio/get-prediction-url.md)]
-
-
-# [REST API](#tab/rest-api)
+## Send a text classification request to your model (REST API)
 
 First you need to get your resource key and endpoint:
 
 [!INCLUDE [Get keys and endpoint Azure portal](../../includes/key-endpoint-page-azure-portal.md)]
 
-
-
 ### Submit a custom text classification task
 
 [!INCLUDE [submit a text classification task using the REST API](../includes/rest-api/submit-task.md)]
 
 
-### Get task results
+### Get task results (Azure SDK)
 
 [!INCLUDE [get custom NER task results](../includes/rest-api/get-results.md)]
 
-# [Client libraries (Azure SDK)](#tab/client-libraries)
 
 First you need to get your resource key and endpoint:
 
+
+
 [!INCLUDE [Get keys and endpoint Azure portal](../includes/get-keys-endpoint-azure.md)]
 
-3. Download and install the client library package for your language of choice:
-    
+1. Download and install the client library package for your language of choice:
+
     |Language  |Package version  |
     |---------|---------|
     |.NET     | [5.2.0-beta.3](https://www.nuget.org/packages/Azure.AI.TextAnalytics/5.2.0-beta.3)        |
     |Java     | [5.2.0-beta.3](https://mvnrepository.com/artifact/com.azure/azure-ai-textanalytics/5.2.0-beta.3)        |
     |JavaScript     |  [6.0.0-beta.1](https://www.npmjs.com/package/@azure/ai-text-analytics/v/6.0.0-beta.1)       |
     |Python     | [5.2.0b4](https://pypi.org/project/azure-ai-textanalytics/5.2.0b4/)         |
-    
-4. After you install the client library, use the following samples on GitHub to start calling the API.
-    
+
+1. After you install the client library, use the following samples on GitHub to start calling the API.
+
     Single label classification:
     * [C#](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/textanalytics/Azure.AI.TextAnalytics/samples/Sample9_SingleLabelClassify.md)
     * [Java](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/textanalytics/azure-ai-textanalytics/src/samples/java/com/azure/ai/textanalytics/lro/SingleLabelClassifyDocument.java)
     * [JavaScript](https://github.com/Azure/azure-sdk-for-js/blob/%40azure/ai-text-analytics_6.0.0-beta.1/sdk/textanalytics/ai-text-analytics/samples/v5/javascript/customText.js)
     * [Python](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/textanalytics/azure-ai-textanalytics/samples/sample_single_label_classify.py)
-    
+
     Multi label classification:
     * [C#](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/textanalytics/Azure.AI.TextAnalytics/samples/Sample10_MultiLabelClassify.md)
     * [Java](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/textanalytics/azure-ai-textanalytics/src/samples/java/com/azure/ai/textanalytics/lro/MultiLabelClassifyDocument.java)
     * [JavaScript](https://github.com/Azure/azure-sdk-for-js/blob/%40azure/ai-text-analytics_6.0.0-beta.1/sdk/textanalytics/ai-text-analytics/samples/v5/javascript/customText.js)
     * [Python](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/textanalytics/azure-ai-textanalytics/samples/sample_multi_label_classify.py)
 
-5. See the following reference documentation on the client, and return object:
-    
+1. See the following reference documentation on the client, and return object:
+
     * [C#](/dotnet/api/azure.ai.textanalytics?view=azure-dotnet-preview&preserve-view=true)
     * [Java](/java/api/overview/azure/ai-textanalytics-readme?view=azure-java-preview&preserve-view=true)
     * [JavaScript](/javascript/api/overview/azure/ai-text-analytics-readme?view=azure-node-preview&preserve-view=true)
     * [Python](/python/api/azure-ai-textanalytics/azure.ai.textanalytics?view=azure-python-preview&preserve-view=true)
----
+
 
 ## Next steps
 

@@ -7,7 +7,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/18/2025
+ms.date: 12/18/2025
 ms.author: lajanuar
 ms.custom: language-service-custom-classification, references_regions
 ---
@@ -41,10 +41,6 @@ You also need an Azure storage account where to upload your `.txt` documents tha
 
 [!INCLUDE [create a new resource from the Azure portal](../includes/resource-creation-azure-portal.md)]
 
-### [Using Language Studio](#tab/language-studio)
-
-[!INCLUDE [create a new resource from Language Studio](../includes/language-studio/resource-creation-language-studio.md)]
-
 ### [Using Azure PowerShell](#tab/azure-powershell)
 
 [!INCLUDE [create a new resource with Azure PowerShell](../includes/resource-creation-powershell.md)]
@@ -60,58 +56,29 @@ You also need an Azure storage account where to upload your `.txt` documents tha
 [!INCLUDE [use an existing resource](../includes/use-pre-existing-resource.md)]
 
 
-## Create a custom text classification project
-
-Once your resource and storage container are configured, create a new custom text classification project. A project is a work area for building your custom AI models based on your data. Your project is only accessible by you and others who have access to the Azure resource being used. If you labeled data, you can [import it](#import-a-custom-text-classification-project) to get started.
-
-### [Language Studio](#tab/studio)
-
-[!INCLUDE [Language Studio project creation](../includes/language-studio/create-project.md)]
+## Create a custom text classification project (REST API)
 
+Once your resource and storage container are configured, create a new custom text classification project. A project is a work area for building your custom AI models based on your data. Your project is only accessible by you and others who have access to the Azure resource being used. If you labeled data, you can [import it](#import-a-custom-text-classification-project-rest-api) to get started.
 
-### [REST APIs](#tab/apis)
 
 [!INCLUDE [REST APIs project creation](../includes/rest-api/create-project.md)]
 
----
 
-## Import a custom text classification project
+## Import a custom text classification project (REST API)
 
 If you already labeled data, you can use it to get started with the service. Make sure that your labeled data follows the [accepted data formats](../concepts/data-formats.md).
 
-### [Language Studio](#tab/studio)
-
-[!INCLUDE [Import project](../includes/language-studio/import-project.md)]
-
-### [REST APIs](#tab/apis)
-
 [!INCLUDE [Import project](../includes/rest-api/import-project.md)]
 
----
-
-## Get project details
-
-### [Language Studio](#tab/studio)
-
-[!INCLUDE [Language Studio project details](../includes/language-studio/project-details.md)]
-
-### [REST APIs](#tab/apis)
+## Get project details (REST API)
 
 [!INCLUDE [REST API project details](../includes/rest-api/project-details.md)]
 
----
+## Delete project (REST API)
 
-## Delete project
-
-### [Language Studio](#tab/studio)
-
-[!INCLUDE [Delete project using Language Studio](../includes/language-studio/delete-project.md)]
-
-### [REST APIs](#tab/apis)
 
 [!INCLUDE [Delete project using the REST API](../includes/rest-api/delete-project.md)]
 
----
 
 ## Next steps
 

@@ -7,7 +7,7 @@ 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-custom-classification
 ---
@@ -24,16 +24,10 @@ Once you're satisfied with how your model performs, it's ready to be deployed; a
 
 See the [project development lifecycle](../overview.md#project-development-lifecycle).
 
-## Deploy model
+## Deploy model (REST API)
 
 After you review your model's performance and decided it can be used in your environment, you need to assign it to a deployment to be able to query it. Assigning the model to a deployment makes it available for use through the [prediction API](https://aka.ms/ct-runtime-swagger). We recommend that you create a deployment named `production` to which you assign the best model you built so far and use it in your system. You can create another deployment called `staging` to which you can assign the model you're currently working on to be able to test it. You can have a maximum on 10 deployments in your project.
 
-# [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Deploy a model using Language Studio](../includes/language-studio/deploy-model.md)]
-
-# [REST APIs](#tab/rest-api)
-
 ### Submit deployment job
 
 [!INCLUDE [deploy model](../includes/rest-api/deploy-model.md)]
@@ -42,63 +36,28 @@ After you review your model's performance and decided it can be used in your env
 
 [!INCLUDE [get deployment status](../includes/rest-api/get-deployment-status.md)]
 
----
-
-## Swap deployments
+## Swap deployments (REST API)
 
 You can swap deployments after testing a model assigned to one deployment, and want to assign it to another. Swapping deployments involves taking the model assigned to the first deployment, and assigning it to the second deployment. Then taking the model assigned to second deployment and assign it to the first deployment. This step could be used to swap your `production` and `staging` deployments when you want to take the model assigned to `staging` and assign it to `production`.
 
-# [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Swap deployments](../includes/language-studio/swap-deployment.md)]
-
-# [REST APIs](#tab/rest-api)
-
 [!INCLUDE [Swap deployments](../includes/rest-api/swap-deployment.md)]
 
----
-
-
-## Delete deployment
-
-# [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Delete deployment](../includes/language-studio/delete-deployment.md)]
-
-# [REST APIs](#tab/rest-api)
+## Delete deployment (REST API)
 
 [!INCLUDE [Delete deployment](../includes/rest-api/delete-deployment.md)]
 
----
-
-## Assign deployment resources
+## Assign deployment resources (REST API)
 
 You can [deploy your project to multiple regions](../../concepts/custom-features/multi-region-deployment.md) by assigning different Language resources that exist in different regions.
 
-# [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Assign resource](../../conversational-language-understanding/includes/language-studio/assign-resources.md)]
-
-# [REST APIs](#tab/rest-api)
-
 [!INCLUDE [Assign resource](../includes/rest-api/assign-resources.md)]
 
----
-
-## Unassign deployment resources
+## Unassign deployment resources (REST API)
 
 When you unassign or remove a deployment resource from a project, you also delete all the deployments previously deployed to that resource region.
 
-# [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Unassign resource](../../conversational-language-understanding/includes/language-studio/unassign-resources.md)]
-
-# [REST APIs](#tab/rest-api)
-
 [!INCLUDE [Unassign resource](../includes/rest-api/unassign-resources.md)]
 
----
-
 ## Next steps
 
 * Use [prediction API to query your model](call-api.md)

@@ -13,15 +13,15 @@ ms.custom: language-service-custom-classification
 ---
 # How to prepare data and define a text classification schema
 
-In order to create a custom text classification model, you will need quality data to train it. This article covers how you should select and prepare your data, along with defining a schema. Defining the schema is the first step in [project development lifecycle](../overview.md#project-development-lifecycle), and it defines the classes that you need your model to classify your text into at runtime.
+In order to create a custom text classification model, you need quality data to train it. This article covers how you should select and prepare your data, along with defining a schema. Defining the schema is the first step in [project development lifecycle](../overview.md#project-development-lifecycle), and it defines the classes that you need your model to classify your text into at runtime.
 
 ## Schema design
 
 The schema defines the classes that you need your model to classify your text into at runtime.
 
 * **Review and identify**: Review documents in your dataset to be familiar with their structure and content, then identify how you want to classify your data. 
 
-    For example, if you're classifying support tickets, you might need the following classes: *login issue*, *hardware issue*, *connectivity issue*, and *new equipment request*.
+    For example, if you're classifying support tickets, you might need the following classes: *Sign in issue*, *hardware issue*, *connectivity issue*, and *new equipment request*.
 
 * **Avoid ambiguity in classes**: Ambiguity arises when the classes you specify share similar meaning to one another. The more ambiguous your schema is, the more labeled data you might need to differentiate between different classes.
 
@@ -34,7 +34,7 @@ The schema defines the classes that you need your model to classify your text in
 
 The quality of data you train your model with affects model performance greatly.
 
-* Use real-life data that reflects your domain's problem space to effectively train your model. You can use synthetic data to accelerate the initial model training process, but it will likely differ from your real-life data and make your model less effective when used.
+* Use real-life data that reflects your domain's problem space to effectively train your model. You can use synthetic data to accelerate the initial model training process, but it likely differs from your real-life data and make your model less effective when used.
 
 * Balance your data distribution as much as possible without deviating far from the distribution in real-life.
 
@@ -54,14 +54,12 @@ As a prerequisite for creating a custom text classification project, your traini
 * [Create and upload documents from Azure](/azure/storage/blobs/storage-quickstart-blobs-portal#create-a-container)
 * [Create and upload documents using Azure Storage Explorer](/azure/vs-azure-tools-storage-explorer-blobs)
 
-You can only use `.txt`. documents for custom text. If your data is in other format, you can use [CLUtils parse command](https://github.com/microsoft/CognitiveServicesLanguageUtilities/blob/main/CustomTextAnalytics.CLUtils/Solution/CogSLanguageUtilities.ViewLayer.CliCommands/Commands/ParseCommand/README.md) to change your file format.
-
- You can upload an annotated dataset, or you can upload an unannotated one and [label your data](../how-to/tag-data.md) in Language studio. 
+You can only use `.txt` documents for custom text. If your data is in other format, you can use [CLUtils parse command](https://github.com/microsoft/CognitiveServicesLanguageUtilities/blob/main/CustomTextAnalytics.CLUtils/Solution/CogSLanguageUtilities.ViewLayer.CliCommands/Commands/ParseCommand/README.md) to change your file format.
 
 ## Test set
 
-When defining the testing set, make sure to include example documents that are not present in the training set. Defining the testing set is an important step to calculate the [model performance](view-model-evaluation.md#model-details). Also, make sure that the testing set include documents that represent all classes used in your project.
+When defining the testing set, make sure to include example documents that aren't present in the training set. Defining the testing set is an important step to calculate the [model performance](view-model-evaluation.md#model-details-rest-api). Also, make sure that the testing set includes documents that represent all classes used in your project.
 
 ## Next steps
 
-If you haven't already, create a custom text classification project. If it's your first time using custom text classification, consider following the [quickstart](../quickstart.md) to create an example project. You can also see the [project requirements](../how-to/create-project.md) for more details on what you need to create a project.
+If you haven't already, create a custom text classification project. If it's your first time using custom text classification, consider following the [quickstart](../quickstart.md) to create an example project. For more information, *see* [project requirements](../how-to/create-project.md).
\ No newline at end of file

@@ -7,15 +7,15 @@ 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-custom-classification
 ---
 # Label text data for training your model 
 
 Before training your model, you need to label your documents with the classes you want to categorize them into. Data labeling  is a crucial step in development lifecycle; in this step you can create the classes you want to categorize your data into and label your documents with these classes. This data is used in the next step when training your model so that your model can learn from the labeled data. If you already labeled your data, you can directly [import](create-project.md) it into your project but you need to make sure that your data follows the [accepted data format](../concepts/data-formats.md).
 
-Before creating a custom text classification model, you need to have labeled data first. If your data isn't labeled already, you can label it in the [Language Studio](https://aka.ms/languageStudio). Labeled data informs the model how to interpret text, and is used for training and evaluation.
+Before creating a custom text classification model, you need to have labeled data first. If your data isn't labeled already, you can label it in the [Microsoft Foundry](https://ai.azure.com/). Labeled data informs the model how to interpret text, and is used for training and evaluation.
 
 ## Prerequisites
 
@@ -28,7 +28,7 @@ See the [project development lifecycle](../overview.md#project-development-lifec
 
 ## Data labeling guidelines
 
-After [preparing your data, designing your schema](design-schema.md) and [creating your project](create-project.md), you need to label your data. Labeling your data is important so your model knows which documents will be associated with the classes you need. When you label your data in [Language Studio](https://aka.ms/languageStudio) (or import labeled data), these labels are stored in the JSON file in your storage container that you've connected to this project. 
+After [preparing your data, designing your schema](design-schema.md) and [creating your project](create-project.md), you need to label your data. Labeling your data is important so your model knows which documents will be associated with the classes you need. When you label your data or import labeled data, these labels are stored in the JSON file in your storage container that you've connected to this project. 
 
 As you label your data, keep in mind:
 
@@ -40,7 +40,7 @@ As you label your data, keep in mind:
 
 Use the following steps to label your data:
 
-1. Go to your project page in [Language Studio](https://aka.ms/languageStudio).
+1. Go to your project page in [Microsoft Foundry](https://ai.azure.com/).
 
 2. From the left side menu, select **Data labeling**. You can find a list of all documents in your storage container. See the image below.
 

@@ -48,13 +48,8 @@ Custom text classification supports two methods for data splitting:
 
 * **Use a manual split of training and testing data**: This method enables users to define which labeled documents should belong to which set. This step is only enabled if you added documents to your testing set during [data labeling](tag-data.md).
 
-## Train model
+## Train model with REST API
 
-# [Language studio](#tab/Language-studio)
-
-[!INCLUDE [Train model](../includes/language-studio/train-model.md)]
-
-# [REST APIs](#tab/REST-APIs)
 
 ### Start training job
 
@@ -66,19 +61,11 @@ Training could take sometime depending on the size of your training data and com
 
  [!INCLUDE [get training model status](../includes/rest-api/get-training-status.md)]
 
----
-
-### Cancel training job
 
-# [Language Studio](#tab/language-studio)
-
-[!INCLUDE [Cancel training](../includes/language-studio/cancel-training.md)]
-
-# [REST APIs](#tab/rest-api)
+### Cancel training job with REST API
 
 [!INCLUDE [Cancel training](../includes/rest-api/cancel-training.md)]
 
----
 
 ## Next steps
 

@@ -7,7 +7,7 @@ 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-custom-classification
 ---
@@ -29,13 +29,7 @@ Before viewing model evaluation you need:
 
 See the [project development lifecycle](../overview.md#project-development-lifecycle).
 
-## Model details
-
-### [Language studio](#tab/language-studio)
-
-[!INCLUDE [View model details](../includes/language-studio/model-evaluation.md)]
-
-### [REST APIs](#tab/rest-api)
+## Model details (REST API)
 
 ### Single label classification
 [!INCLUDE [Model evaluation](../includes/rest-api/model-evaluation-single-label.md)]
@@ -44,35 +38,16 @@ See the [project development lifecycle](../overview.md#project-development-lifec
 
 [!INCLUDE [Model evaluation](../includes/rest-api/model-evaluation-multi-label.md)]
 
----
-
-## Load or export model data
-
-### [Language studio](#tab/Language-studio)
-
-[!INCLUDE [Load export model](../../conversational-language-understanding/includes/language-studio/load-export-model.md)]
-
 
-### [REST APIs](#tab/REST-APIs)
+## Load or export model data (REST API)
 
 [!INCLUDE [Load export model](../includes/rest-api/load-export-model.md)]
 
----
-
-## Delete model
-
-### [Language studio](#tab/language-studio)
-
-[!INCLUDE [Delete model](../includes/language-studio/delete-model.md)]
 
-
-### [REST APIs](#tab/rest-api)
+## Delete model (REST API)
 
 [!INCLUDE [Delete model](../includes/rest-api/delete-model.md)]
 
-
----
-
 ## Next steps
 
 As you review your how your model performs, learn about the [evaluation metrics](../concepts/evaluation-metrics.md) that are used. Once you know whether your model performance needs to improve, you can begin improving the model.

@@ -13,7 +13,7 @@ After you create an Azure storage account and connected it to your Language reso
 
 1. [Download the sample dataset for multi label classification projects](https://github.com/Azure-Samples/cognitive-services-sample-data-files/raw/master/language-service/Custom%20text%20classification/Custom%20multi%20classification%20-%20movies%20summary.zip).
 
-2. Open the .zip file, and extract the folder containing the documents. 
+1. Open the .zip file, and extract the folder containing the documents. 
 
 The provided sample dataset contains about 200 documents,  each of which is a summary for a movie. Each document belongs to one or more of the following classes: 
 * "Mystery"
@@ -26,7 +26,7 @@ The provided sample dataset contains about 200 documents,  each of which is a su
 
 1. [Download the sample dataset for single label classification projects](https://github.com/Azure-Samples/cognitive-services-sample-data-files/raw/master/language-service/Custom%20text%20classification/Custom%20single%20classification%20-%20WebOfScience.zip). 
 
-2. Open the .zip file, and extract the folder containing the documents. 
+1. Open the .zip file, and extract the folder containing the documents. 
 
 The provided sample dataset contains about 210 documents, each of which is an abstract of a scientific paper. Each document is labeled with only one class of the following classes: 
 * "Computer_science"
@@ -39,14 +39,16 @@ The provided sample dataset contains about 210 documents, each of which is an ab
 
 ---
 
-2. In the [Azure portal](https://portal.azure.com), navigate to the storage account you created, and select it by selecting **Storage accounts** and typing your storage account name into **Filter for any field**.
+### Azure portal
+
+1. In the [Azure portal](https://portal.azure.com), navigate to the storage account you created, and select it by selecting **Storage accounts** and typing your storage account name into **Filter for any field**.
 
     if your resource group doesn't show up, make sure the **Subscription equals** filter is set to **All**.
 
-3. In your storage account, select **Containers** from the left menu, located below **Data storage**. On the screen that appears, select **+ Container**. Give the container the name **example-data** and leave the default **Public access level**.
+1. In your storage account, select **Containers** from the left menu, located below **Data storage**. On the screen that appears, select **+ Container**. Give the container the name **example-data** and leave the default **Public access level**.
 
     :::image type="content" source="../../media/storage-screen.png" alt-text="A screenshot showing the main page for a storage account." lightbox="../../media/storage-screen.png":::
 
-4. After your container is created, select it. Then select **Upload** button to select the `.txt` and `.json` files you downloaded earlier. 
+1. After your container is created, select it. Then select **Upload** button to select the `.txt` and `.json` files you downloaded earlier. 
 
     :::image type="content" source="../../media/file-upload-screen.png" alt-text="A screenshot showing the button for uploading files to the storage account." lightbox="../../media/file-upload-screen.png":::

@@ -23,26 +23,26 @@ Before you can use custom text classification, you'll need to create a Language
 > If you have a [pre-existing resource](../../how-to/create-project.md#using-a-preexisting-language-resource) that you'd like to use, you need to connect it to storage account.
 
 [!INCLUDE [create a new resource from the Azure portal](../resource-creation-azure-portal.md)]
-    
+
 
 
 ## Upload sample data to blob container
 
 [!INCLUDE [Uploading sample data for custom tex classification](blob-storage-upload.md)]
-    
+
 
 
 ### Get your resource keys and endpoint
 
 [!INCLUDE [Get keys and endpoint Azure portal](../get-keys-endpoint-azure.md)]
-    
+
 
 
 ## Create a custom text classification project
 
 Once your resource and storage container are configured, create a new custom text classification project. A project is a work area for building your custom ML models based on your data. Your project can only be accessed by you and others who have access to Azure Language resource being used.
 
-### Trigger import project job 
+### Trigger import project job
 
 [!INCLUDE [Import a project using the REST API](../rest-api/import-project.md)]
 
@@ -60,7 +60,7 @@ Typically after you create a project, you go ahead and start [tagging the docume
 
 ### Start training your model
 
-After your project has been imported, you can start training your model. 
+After your project has been imported, you can start training your model.
 
 [!INCLUDE [train model](../rest-api/train-model.md)]
 

@@ -1,11 +1,11 @@
 ---
-#services: cognitive-services
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: include
 ms.date: 11/18/2025
 ms.author: lajanuar
+
 ---
 ### Load model data 
 

@@ -20,23 +20,11 @@ To use custom text classification, you'll need to [create an Azure storage accou
 
 ## Enable identity management for your resource
 
-# [Azure portal](#tab/azure-portal)
-
 Your Language resource must have identity management, to enable it using [Azure portal](https://portal.azure.com/):
 
 1. Go to your Language resource
-2. From left hand menu, under **Resource Management** section, select **Identity**
-3. From **System assigned** tab, make sure to set **Status** to **On**
-
-# [Language Studio](#tab/language-studio)
-
-Your Language resource must have identity management, to enable it using [Language Studio](https://aka.ms/languageStudio):
-
-1. Select the settings icon in the top right corner of the screen
-2. Select **Resources**
-3. Select the check box **Managed Identity** for your Azure Language in Foundry Tools resource.
-
----
+1. From left hand menu, under **Resource Management** section, select **Identity**
+1. From **System assigned** tab, make sure to set **Status** to **On**
 
 ### Enable custom text classification feature
 

@@ -6,8 +6,8 @@ description: Learn about which languages are supported by custom text classifica
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
-ms.topic: conceptual
-ms.date: 11/18/2025
+ms.topic: concept-article
+ms.date: 12/15/2025
 ms.author: lajanuar
 ms.custom: language-service-custom-classification
 ---
@@ -22,7 +22,7 @@ With custom text classification, you can train a model in one language and use t
 You can train your project entirely with English documents, and query it in: French, German, Mandarin, Japanese, Korean, and others. Custom text classification
 makes it easy for you to scale your projects to multiple languages by using multilingual technology to train your models.
 
-Whenever you identify that a particular language is not performing as well as other languages, you can add more documents for that language in your project. In the [data labeling](how-to/tag-data.md) page in Language Studio, you can select the language of the document you're adding. When you introduce more documents for that language to the model, it is introduced to more of the syntax of that language, and learns to predict it better.
+Whenever you identify that a particular language is not performing as well as other languages, you can add more documents for that language in your project. When you introduce more documents for that language to the model, it is introduced to more of the syntax of that language, and learns to predict it better.
 
 You aren't expected to add the same number of documents for every language. You should build the majority of your project in one language, and only add a few documents in languages you observe aren't performing well. If you create a project that is primarily in English, and start testing it in French, German, and Spanish, you might observe that German doesn't perform as well as the other two languages. In that case, consider adding 5% of your original English documents in German, train a new model and test in German again. You should see better results for German queries. The more labeled documents you add, the more likely the results are going to get better. 
 

@@ -7,15 +7,15 @@ 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-custom-classification
 ---
 # What is custom text classification?
 
 Custom text classification is one of the custom features offered by [Azure Language in Foundry Tools](../overview.md). It's a cloud-based API service that applies machine-learning intelligence to enable you to build custom models for text classification tasks. 
 
-Custom text classification enables users to build custom AI models to classify text into custom classes predefined by the user. By creating a custom text classification project, developers can iteratively label data, train, evaluate, and improve model performance before making it available for consumption. The quality of the labeled data greatly impacts model performance. 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). 
+Custom text classification enables users to build custom AI models to classify text into custom classes predefined by the user. By creating a custom text classification project, developers can iteratively label data, train, evaluate, and improve model performance before making it available for consumption. The quality of the labeled data greatly impacts model performance. To simplify building and customizing your model, the service offers a unified platform for building, managing, and deploying AI solutions 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). 
 
 Custom text classification supports two types of projects: 
 

@@ -7,12 +7,11 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: quickstart
-ms.date: 12/05/2025
+ms.date: 12/15/2025
 ms.author: lajanuar
 ms.custom: language-service-custom-classification, mode-other
-zone_pivot_groups: usage-custom-language-features
 ---
-# Quickstart: Custom text classification
+# Quickstart: Custom text classification REST API
 
 Use this article to get started with creating a custom text classification project where you can train custom models for text classification. A model is AI software trained to do a certain task. For this system, the models classify text, and are trained by learning from tagged data.
 
@@ -24,18 +23,8 @@ Custom text classification supports two types of projects:
 In this quickstart, you can use the sample datasets provided to build a multi label classification to classify movie scripts into one or more categories. Alternatively, you can use single label classification dataset to classify abstracts of scientific papers into one of the defined domains.
 
 
-::: zone pivot="language-studio"
-
-[!INCLUDE [Language Studio quickstart](includes/quickstarts/language-studio.md)]
-
-::: zone-end
-
-::: zone pivot="rest-api"
-
 [!INCLUDE [REST API quickstart](includes/quickstarts/rest-api.md)]
 
-::: zone-end
-
 ## Next steps
 
 After you create a custom text classification model, you can:

@@ -7,7 +7,7 @@ author: laujan
 manager: nitinme
 ms.date: 11/18/2025
 ms.service: azure-ai-language
-ms.topic: conceptual
+ms.topic: limits-and-quotas
 ms.author: lajanuar
 ms.custom: language-service-custom-classification, references_regions
 ---

@@ -7,7 +7,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: tutorial
-ms.date: 11/18/2025
+ms.date: 12/15/2025
 ms.author: lajanuar
 ---
 # Tutorial: Triage incoming emails with Power Automate

@@ -1,130 +0,0 @@
----
-title: Use Azure Machine Learning labeling in Language Studio
-description: Learn how to label your data in Azure Machine Learning, and import it for use in Azure Language service.
-titleSuffix: Foundry Tools
-author: laujan
-manager: nitinme
-ms.service: azure-ai-language
-ms.topic: how-to
-ms.date: 11/18/2025
-ms.author: lajanuar
----
-# Use Azure Machine Learning labeling in Language Studio
-
-Labeling data is an important part of preparing your dataset. Using the labeling experience in Azure Machine Learning, you can experience easier collaboration, more flexibility, and the ability to [outsource labeling tasks](/azure/machine-learning/how-to-outsource-data-labeling) to external labeling vendors from the [Azure Marketplace](https://azuremarketplace.microsoft.com/marketplace/consulting-services?search=AzureMLVend). You can use Azure Machine Learning labeling for:
-* [custom text classification](../custom-text-classification/overview.md)
-* [custom named entity recognition](../custom-named-entity-recognition/overview.md)
-
-## Prerequisites
-
-Before you can connect your labeling project to Azure Machine Learning, you need:
-* A successfully created Language Studio project with a configured Azure blob storage account.
-* Text data that is uploaded to your storage account.
-* At least:
-    * One entity label for custom named entity recognition, or
-    * Two class labels for custom text classification projects.
-* An [Azure Machine Learning workspace](/azure/machine-learning/how-to-manage-workspace) that is [connected](/azure/machine-learning/v1/how-to-connect-data-ui?tabs=credential#create-datastores) to the same Azure blob storage account that your Language Studio account using.
-
-## Limitations
-
-* Connecting your labeling project to Azure Machine Learning is a one-to-one connection. If you disconnect your project, you can't connect your project back to the same Azure Machine Learning project
-* You can't label in Azure Language Studio and Azure Machine Learning simultaneously. The labeling experience is enabled in one studio at a time.
-* The testing and training files in the labeling experience you switch away from is ignored when training your model.
-* Only Azure Machine Learning's JSONL file format can be imported into Language Studio.
-* Projects with the multi-lingual option enabled can't be connected to Azure Machine Learning, and not all languages are supported.
-    * Language support is provided by the Azure Machine Learning [TextDNNLanguages Class](/python/api/azureml-automl-core/azureml.automl.core.constants.textdnnlanguages?view=azure-ml-py&preserve-view=true&branch=main#azureml-automl-core-constants-textdnnlanguages-supported).
-* The Azure Machine Learning workspace you're connecting to must be assigned to the same Azure Storage account that Language Studio is connected to. Be sure that the Azure Machine Learning workspace has the storage blob data reader permission on the storage account. The workspace needs to link to the storage account during the [creation process in the Azure portal](https://portal.azure.com/#create/Microsoft.MachineLearningServices).
-* Switching between the two labeling experiences isn't instantaneous. It may take time to successfully complete the operation.
-
-## Import your Azure Machine Learning labels into Language Studio
-
-Language Studio supports the JSONL file format used by Azure Machine Learning. If you've been labeling data on Azure Machine Learning, you can import your up-to-date labels in a new custom project to utilize the features of both studios.
-
-1.    Start by creating a new project for custom text classification or custom named entity recognition.
-
-1. In the **Create a project** screen that appears, follow the prompts to connect your storage account, and enter the basic information about your project. Be sure that the Azure resource you're using doesn't have another storage account already connected.
-
-1. In the **Choose container** section, choose the option indicating that you already have a correctly formatted file. Then select your most recent Azure Machine Learning labels file.
-
-    :::image type="content" source="./media/select-label-file.png" alt-text="A screenshot showing the selection for a label file in Language Studio." lightbox="./media/select-label-file.png":::
-
-## Connect to Azure Machine Learning
-
-Before you connect to Azure Machine Learning, you need an Azure Machine Learning account with a pricing plan that can accommodate the compute needs of your project. See the [prerequisites section](#prerequisites) to make sure that you successfully completed all the requirements to start connecting your Language Studio project to Azure Machine Learning.
-
-1. Use the [Azure portal](https://portal.azure.com) to navigate to the Azure Blob Storage account connected to your language resource.
-1. Ensure that the *Storage Blob Data Contributor* role is assigned to your AML workspace within the role assignments for your Azure Blob Storage account.
-1. Navigate to your project in [Language Studio](https://language.azure.com/). From the left pane of your project, select **Data labeling**.
-1. Select **use Azure Machine Learning to label** in either the **Data labeling** description, or under the **Activity pane**.
-
-    :::image type="content" source="./media/azure-machine-learning-selection.png" alt-text="A screenshot showing the location of the Azure Machine Learning link." lightbox="./media/azure-machine-learning-selection.png":::
-
-1. Select **Connect to Azure Machine Learning** to start the connection process.
-
-    :::image type="content" source="./media/activity-pane.png" alt-text="A screenshot showing the Azure Machine Learning connection button in Language Studio." lightbox="./media/activity-pane.png":::
-
-1. In the window that appears, follow the prompts. Select the Azure Machine Learning workspace you created previously under the same Azure subscription. Enter a name for the new Azure Machine Learning project that is created to enable labeling in Azure Machine Learning.
-
-    >[!TIP]
-    > Make sure your workspace is linked to the same Azure Blob Storage account and Language resource before continuing. You can create a new workspace and [link to your storage account using the Azure portal](https://portal.azure.com/#create/Microsoft.MachineLearningServices). Ensure that the storage account is properly linked to the workspace.
-
-1. (Optional) Turn on the vendor labeling toggle to use labeling vendor companies. Before choosing the vendor labeling companies, contact the vendor labeling companies on the [Azure Marketplace](https://azuremarketplace.microsoft.com/marketplace/consulting-services?search=AzureMLVend) to finalize a contract with them. For more information about working with vendor companies, see [How to outsource data labeling](/azure/machine-learning/how-to-outsource-data-labeling).
-
-  * You can also leave labeling instructions for the human labelers that help you in the labeling process.
-  * These instructions can help them understand the task by leaving clear definitions of the labels and including examples for better results.
-
-1. Review the settings for your connection to Azure Machine Learning and make changes if needed.
-
-    > [!IMPORTANT]
-    > Finalizing the connection **is permanent**. Attempting to disconnect your established connection at any point in time can permanently disable your Language Studio project from connecting to the same Azure Machine Learning project.
-
-1. After the connection is initiated, your ability to label data in Language Studio will be disabled for a few minutes to prepare the new connection.
-
-## Switch to labeling with Azure Machine Learning from Language Studio
-
-Once the connection is established, you can switch to Azure Machine Learning through the **Activity pane** in Language Studio at any time.
-
-:::image type="content" source="./media/switch-labeling-activity.png" alt-text="A screenshot showing the button to switch to labeling using Azure Machine Learning." lightbox="./media/switch-labeling-activity.png":::
-
-When you switch, your ability to label data in Language Studio is disabled, and you're able to label data in Azure Machine Learning. You can switch back to labeling in Language Studio at any time through Azure Machine Learning.
-
-For information on how to label the text, see [Azure Machine Learning how to label](/azure/machine-learning/how-to-label-data#label-text). For information about managing and tracking the text labeling project, *see* [Azure Machine Learning set up and manage a text labeling project](/azure/machine-learning/how-to-create-text-labeling-projects).
-
-## Train your model using labels from Azure Machine Learning
-
-When you switch to labeling using Azure Machine Learning, you can still train, evaluate, and deploy your model in Language Studio. To train your model using updated labels from Azure Machine Learning:
-
-1. Select **Training jobs** from the navigation menu on the left of Azure Language studio screen for your project.
-
-1. Select **Import latest labels from Azure Machine Learning** from the **Choose label origin** section in the training page. This step synchronizes the labels from Azure Machine Learning before starting the training job.
-
-    :::image type="content" source="./media/azure-machine-learning-label-origin.png" alt-text="A screenshot showing the selector for using labels from Azure Machine Learning." lightbox="./media/azure-machine-learning-label-origin.png":::
-
-## Switch to labeling with Language Studio from Azure Machine Learning
-
-After you switch to labeling with Azure Machine Learning, You can switch back to labeling with Language Studio project at any time.
-
-> [!NOTE]
-> * Only users with the [correct roles](/azure/machine-learning/how-to-add-users) in Azure Machine Learning have the ability to switch labeling.
-> * When you switch to using Language Studio, labeling on Azure Machine Learning is disabled.
-
-To switch back to labeling with Language Studio:
-
-1. Navigate to your project in Azure Machine Learning and select **Data labeling** from the left pane.
-1. Select the **Language Studio** tab and select **Switch to Language Studio**.
-
-    :::image type="content" source="./media/azure-machine-learning-studio.png" alt-text="A screenshot showing the selector for using labels from Language Studio." lightbox="./media/azure-machine-learning-studio.png":::
-
-3. The process takes a few minutes to complete, and your ability to label in Azure Machine Learning is disabled until switched back from Language Studio.
-
-## Disconnecting from Azure Machine Learning
-
-Disconnecting your project from Azure Machine Learning is a permanent, irreversible process and can't be undone. You can no longer be able to access your labels in Azure Machine Learning, and you won't be able to reconnect the Azure Machine Learning project to any Language Studio project in the future. To disconnect from Azure Machine Learning:
-
-1. Ensure that any updated labels you want to maintain are synchronized with Azure Machine Learning by switching the labeling experience back to Azure Language Studio.
-1. Select **Project settings** from the navigation menu on the left in Language Studio.
-1. Select the **Disconnect from Azure Machine Learning** button from the **Manage Azure Machine Learning connections** section.
-
-## Next steps
-Learn more about labeling your data for [Custom Text Classification](../custom-text-classification/how-to/tag-data.md) and [Custom Named Entity Recognition](../custom-named-entity-recognition/how-to/tag-data.md).
-

@@ -1,86 +0,0 @@
----
-title: "Tutorial: Create an FAQ bot with custom question answering and Azure AI Bot Service"
-description: In this tutorial, create a no code FAQ Bot with custom question answering and Azure AI Bot Service.
-ms.service: azure-ai-language
-ms.topic: tutorial
-author: laujan
-ms.author: lajanuar
-ms.date: 11/18/2025
-ms.custom:
-  - language-service-question-answering
-  - cogserv-non-critical-language
-  - sfi-image-nochange
----
-# Tutorial: Create an FAQ bot
-
-Create an FAQ Bot with custom question answering and Azure [Bot Service](https://azure.microsoft.com/services/bot-service/) with no code.
-
-In this tutorial, you learn how to:
-
-<!-- green checkmark -->
-> [!div class="checklist"]
-> * Link a custom question answering project to an Azure AI Bot Service
-> * Deploy a Bot
-> * Chat with the Bot in web chat
-> * Enable the Bot in supported channels
-
-## Create and publish a project
-
-Follow the [getting started article](../how-to/create-test-deploy.md). Once the project has been successfully deployed, you will be ready to start this article.
-
-## Create a bot
-
-After deploying your project, you can create a bot from the **Deploy project** page:
-
-* You can create several bots quickly, all pointing to the same project for different regions or pricing plans for the individual bots.
-
-* When you make changes to the project and redeploy, you don't need to take further action with the bot. It's already configured to work with the project, and works with all future changes to the project. Every time you publish a project, all the bots connected to it are automatically updated.
-
-1. In [Language Studio](https://language.azure.com/), on the custom question answering **Deploy project** page, select the **Create a bot** button.
-
-    > [!div class="mx-imgBorder"]
-    > ![Screenshot of UI with option to create a bot in Azure.](../media/bot-service/create-bot-in-azure.png)
-
-1. A new browser tab opens for the Azure portal, with the Azure AI Bot Service's creation page. Configure the Azure AI Bot Service and hit the **Create** button.
-
-    |Setting |Value|
-    |----------|---------|
-    | Bot handle| Unique identifier for your bot. This value needs to be distinct from your App name |
-    | Subscription | Select your subscription |
-    | Resource group | Select an existing resource group or create a new one |
-    | Location | Select your desired location |
-    | Pricing tier | Choose pricing tier |
-    |App name | App service name for your bot |
-    |SDK language | C# or Node.js. Once the bot is created, you can download the code to your local development environment and continue the development process. |
-    | Language Resource Key  | This key is automatically populated deployed custom question answering project |
-    | App service plan/Location | This value is automatically populated, do not change this value |
-
-1. After the bot is created, open the **Bot service** resource.
-1. Under **Settings**, select **Test in Web Chat**.
-
-    > [!div class="mx-imgBorder"]
-    > ![Screenshot of Azure AI Bot Service UI button that reads "Test web chat".](../media/bot-service/test-in-web-chat.png)
-
-1. At the chat prompt of **Type your message**, enter:
-
-    `How do I setup my surface book?`
-
-    The chat bot responds with an answer from your project.
-
-    > [!div class="mx-imgBorder"]
-    > ![Screenshot of bot test chat response containing a question and bot generated answer.](../media/bot-service/bot-chat.png)
-
-## Integrate the bot with channels
-
-Select **Channels** in the Bot service resource that you create. You can activate the Bot in additional [supported channels](/azure/bot-service/bot-service-manage-channels).
-
-   >[!div class="mx-imgBorder"]
-   >![Screenshot of integration with teams with product icons.](../media/bot-service/channels.png)
-
-## Clean up resources
-
-If you're not going to continue to use this application, delete the associate custom question answering and bot service resources.
-
-## Next steps
-
-Advance to the next article to learn how to customize your FAQ bot with multi-turn prompts.

@@ -1,90 +0,0 @@
----
-title: Add guided conversations with multi-turn prompts
-description: In this tutorial, learn how to make guided conversations with multi-turn prompts.
-ms.service: azure-ai-language
-ms.topic: tutorial
-author: laujan
-ms.author: lajanuar
-ms.date: 11/18/2025
-ms.custom: language-service-question-answering
----
-# Add guided conversations with multi-turn prompts
-
-In this tutorial, you learn how to:
-
-> [!div class="checklist"]
-> * Add new question and answer pairs to your existing project
-> * Add follow-up prompts to create guided conversations
-> * Test your multi-turn prompts
-
-## Prerequisites
-
- In this tutorial, we use [Surface Pen FAQ](https://support.microsoft.com/surface/how-to-use-your-surface-pen-8a403519-cd1f-15b2-c9df-faa5aa924e98) to create a project.
-
-If you have never created a custom question answering project before we recommend starting with the [getting started](../how-to/create-test-deploy.md) article, which will take you step-by-step through the process.
-
-## View question answer pair context
-
-For this example, let's assume that users are asking for additional details about the Surface Pen product, particularly how to troubleshoot their Surface Pen, but they are not getting the correct answers. So, we add more prompts to support additional scenarios and guide the users to the correct answers using multi-turn prompts.
-
-Multi-turn prompts that are associated with question and answer pairs, can be viewed by selecting **Show columns** > **Context**. By default this should already be enabled on the **Edit project** page in Azure Language Studio custom question answering interface.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of show columns UI with context highlighted in red]( ../media/guided-conversations/context.png) ]( ../media/guided-conversations/context.png#lightbox)
-
-This displays the context tree where all follow-up prompts linked to a QnA pair are shown: 
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of Surface Pen FAQ page with answers to common questions]( ../media/guided-conversations/surface-source.png) ]( ../media/guided-conversations/surface-source.png#lightbox)
-
-## Add question pair with follow-up prompts
-
-To help users solve issues with their Surface Pen, we add follow-up prompts:
-
-- Add a new question pair with two follow-up prompts
-- Add a follow-up prompt to one of the newly added prompts
-
-1. Add a new QnA pair with two follow-up prompts **Check compatibility** and **Check Pen Settings**
-Using the editor, we add a new QnA pair with a follow-up prompt by selecting **Add question pair**
-
-    > [!div class="mx-imgBorder"]
-    > ![Screenshot of UI with "Add question pair" highlighted in a red box]( ../media/guided-conversations/add-question.png)
-    
-    A new row in **Editorial** is created where we enter the question answer pair as shown below:
-    
-    |Field|Value|
-    |-----|----|
-    |Questions | Fix problems with Surface |
-    |Answers and prompts | Here are some things to try first if your Surface Pen won't write, open apps, or connect to Bluetooth.|
-    
-2. We then add a follow-up prompt to the newly created question pair by choosing **Add follow-up prompts**. Fill the details for the prompt as shown:
-    
-    > [!div class="mx-imgBorder"]
-    > [ ![Screenshot of UI with "add a follow-up prompt" highlighted in a red box]( ../media/guided-conversations/add-prompts.png) ]( ../media/guided-conversations/add-prompts.png#lightbox)
-    
-    We provide **Check Compatibility** as the "Display text" for the prompt and try to link it to a QnA. Since, no related QnA pair is available to link to the prompt, when we search “Check your Surface Pen Compatibility”, we create a new question pair by selecting **Create link to new pair** and select **Done**. Then select **Save changes**.
-    
-    > [!div class="mx-imgBorder"]
-    > [ ![Screenshot of a question and answer about checking your surface pen compatibility]( ../media/guided-conversations/compatability-check.png) ]( ../media/guided-conversations/compatability-check.png#lightbox)
-    
-3. Similarly, we add another prompt **Check Pen Settings** to help the user troubleshoot the Surface Pen and add question pair to it.
-    
-    > [!div class="mx-imgBorder"]
-    > [ ![Screenshot of a question and answer about checking your surface pen settings]( ../media/guided-conversations/pen-settings.png) ]( ../media/guided-conversations/check-pen-settings.png#lightbox)
-
-4. Add another follow-up prompt to the newly created prompt. We now add “Replace Pen tips’ as a follow-up prompt to the previously created prompt “Check Pen Settings”.
-
-    > [!div class="mx-imgBorder"]
-    > [ ![Screenshot of a question and answer about creating a follow-up prompt for replacing pen tips]( ../media/guided-conversations/replace-pen.png) ]( ../media/guided-conversations/replace-pen.png#lightbox)
-    
-5. Finally, save the changes and test these prompts in the **Test** pane:
-    
-    > [!div class="mx-imgBorder"]
-    > [ ![Screenshot of question answer UI with save changes highlighted in a red box]( ../media/guided-conversations/save-changes.png) ]( ../media/guided-conversations/save-changes.png#lightbox)
-    
-    For a user query **Issues with Surface Pen**, the system returns an answer and presents the newly added prompts to the user. The user then selects one of the prompts **Check Pen Settings** and the related answer is returned to the user with another prompt **Replace Pen Tips**, which when selected further provides the user with more information. So, multi-turn is used to help and guide the user to the desired answer.
-    
-    > [!div class="mx-imgBorder"]
-    > [ ![Screenshot of chat test UI]( ../media/guided-conversations/test.png) ]( ../media/guided-conversations/test.png#lightbox)
-
-## Next steps

@@ -1,86 +0,0 @@
----
-title: Create projects in multiple languages - custom question answering
-description: In this tutorial, learn how to create projects with multiple languages.
-ms.service: azure-ai-language
-ms.topic: tutorial
-author: laujan
-ms.author: lajanuar
-ms.date: 11/18/2025
-ms.custom: language-service-question-answering
----
-# Create projects in multiple languages
-
-In this tutorial, you learn how to:
-
-<!-- green checkmark -->
-> [!div class="checklist"]
-> * Create a project that supports English
-> * Create a project that supports German
-
-This tutorial walks you through the process of creating projects in multiple languages. We use the [Surface Pen FAQ](https://support.microsoft.com/surface/how-to-use-your-surface-pen-8a403519-cd1f-15b2-c9df-faa5aa924e98) URL to create projects in German and English. We then deploy the project and use the custom question answering REST API to query and get answers to FAQs in the desired language.
-
-## Create project in German
-
-To be able to create a project in more than one language, the multiple language setting must be set at the creation of the first project that is associated with the language resource.
-
-> [!div class="mx-imgBorder"]
-> [![Screenshot of UI for create project with I want to select the language when I create a project in this resource selected.](../media/multiple-languages/multiple-languages.png)](../media/multiple-languages/multiple-languages.png#lightbox)
-
-1. From the [Language Studio](https://aka.ms/languageStudio) home page, select open custom question answering. Select **Create new project** > **I want to select the language when I create a project in this resource** > **Next**.
-
-2. Fill out enter basic information page and select **Next** > **Create project**.
-
-    |Setting| Value|
-    |---|----|
-    |Name | Unique name for your project|
-    |Description | Unique description to help identify the project |
-    |Source language | For this tutorial, select German |
-    |Default answer | Default answer when no answer is returned |
-
-    > [!div class="mx-imgBorder"]
-    > [![Screenshot of UI for create project with the German language selected.](../media/multiple-languages/choose-german.png)](../media/multiple-languages/choose-german.png#lightbox)
-
-3. **Add source** > **URLs** > **Add url** > **Add all**.
-
-    |Setting| Value |
-    |----|------|
-    | Url Name | Surface Pen German |
-    | URL | https://support.microsoft.com/de-de/surface/how-to-use-your-surface-pen-8a403519-cd1f-15b2-c9df-faa5aa924e98 |
-    | Classify file structure | Autodetect |
-    
-    Custom question answering reads the document and extracts question answer pairs from the source URL to create the project in the German language. If you select the link to the source, the project page opens where we can edit the contents.
-    
-    > [!div class="mx-imgBorder"]
-    > [![Screenshot of UI with German questions and answers](../media/multiple-languages/german-language.png)](../media/multiple-languages/german-language.png#lightbox)
-    
-## Create project in English
-
-We now repeat the above steps from before but this time we select English and an English URL as a source.
-
-1. From the [Language Studio](https://aka.ms/languageStudio), open the custom question answering page > **Create new project**.
-
-1. Fill out enter basic information page and select **Next** > **Create project**.
-
-    |Setting| Value|
-    |---|----|
-    |Name | Unique name for your project|
-    |Description | Unique description to help identify the project |
-    |Source language | For this tutorial, select English |
-    |Default answer | Default answer when no answer is returned |
-
-1. **Add source** > **URLs** > **Add url** > **Add all**.
-
-    |Setting| Value |
-    |-----|-----|
-    | Url Name | Surface Pen German |
-    | URL | https://support.microsoft.com/en-us/surface/how-to-use-your-surface-pen-8a403519-cd1f-15b2-c9df-faa5aa924e98 |
-    | Classify file structure | Autodetect |
-
-## Deploy and query project
-
-We're now ready to deploy the two projects and query them in the desired language using the custom question answering REST API. Once a project is deployed, the following page is shown which provides details to query the project.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of UI with English questions and answers](../media/multiple-languages/get-prediction-url.png) ](../media/multiple-languages/get-prediction-url.png#lightbox)
-
-The language for the incoming user query can be detected with the [Language Detection API](../../language-detection/how-to/call-api.md) and the user can call the appropriate endpoint and project depending on the detected language.

@@ -1,214 +0,0 @@
----
-title: "Tutorial: Add your custom question answering project to Power Virtual Agents"
-description: In this tutorial, you will learn how to add your custom question answering project to Power Virtual Agents.
-ms.service: azure-ai-language
-ms.topic: tutorial
-author: laujan
-ms.author: lajanuar
-ms.date: 11/18/2025
-ms.custom: language-service-question-answering
----
-# Add your custom question answering project to Power Virtual Agents
-
-Create and extend a [Power Virtual Agents](https://powervirtualagents.microsoft.com/) bot to provide answers from your project. 
-
-> [!NOTE]
-> The integration demonstrated in this tutorial is in preview and is not intended for deployment to production environments. 
-
-In this tutorial, you learn how to: 
-> [!div class="checklist"]
-> * Create a Power Virtual Agents bot 
-> * Create a system fallback topic
-> * Add custom question answering as an action to a topic as a Power Automate flow
-> * Create a Power Automate solution
-> * Add a Power Automate flow to your solution
-> * Publish Power Virtual Agents
-> * Test Power Virtual Agents, and receive an answer from your custom question answering project
-
-> [!NOTE]
-> The QnA Maker service is being retired on the 31st of March, 2025. A newer version of the question and answering capability is now available as part of [Azure Language in Foundry Tools](../../index.yml). For custom question answering capabilities within Azure Language, see [custom question answering](../overview.md). Starting 1st October, 2022 you won’t be able to create new QnA Maker resources. For information on migrating existing QnA Maker knowledge bases to custom question answering, consult the [migration guide](../how-to/migrate-qnamaker.md).
-
-## Create and publish a project
-1. Follow the [quickstart](../quickstart/sdk.md?pivots=studio) to create a custom question answering project. Once you have deployed your project.
-2. After deploying your project from Language Studio, select “Get Prediction URL”. 
-3. Get your Site URL from the hostname of Prediction URL and your Account key which would be the Ocp-Apim-Subscription-Key.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of how to obtain the prediction URL and subscription key displayed.]( ../media/power-virtual-agents/get-prediction-url.png) ]( ../media/power-virtual-agents/get-prediction-url.png#lightbox)
-
-4. Create a custom question answering connector: Follow the [connector documentation](/connectors/languagequestionansw/) to create a connection to question answering.
-5. Use this tutorial to create a Bot with Power Virtual Agents instead of creating a bot from Language Studio.
-
-## Create a bot in Power Virtual Agents
-[Power Virtual Agents](https://powervirtualagents.microsoft.com/) allows teams to create powerful bots by using a guided, no-code graphical interface. You don't need data scientists or developers.
-
-Create a bot by following the steps in [Create and delete Power Virtual Agents bots](/power-virtual-agents/authoring-first-bot).
-
-## Create the system fallback topic
-In Power Virtual Agents, you create a bot with a series of topics (subject areas), in order to answer user questions by performing actions.
-
-Although the bot can connect to your project from any topic, this tutorial uses the system fallback topic. The fallback topic is used when the bot can't find an answer. The bot passes the user's text to custom question answering Query knowledgebase API, receives the answer from your project, and displays it to the user as a message.
-
-Create a fallback topic by following the steps in [Configure the system fallback topic in Power Virtual Agents](/power-virtual-agents/authoring-system-fallback-topic).
-
-## Use the authoring canvas to add an action
-Use the Power Virtual Agents authoring canvas to connect the fallback topic to your project. The topic starts with the unrecognized user text. Add an action that passes that text to custom question answering, and then shows the answer as a message. The last step of displaying an answer is handled as a [separate step](../../../QnAMaker/Tutorials/integrate-with-power-virtual-assistant-fallback-topic.md), later in this tutorial.
-
-This section creates the fallback topic conversation flow.
-
-The new fallback action might already have conversation flow elements. Delete the **Escalate** item by selecting the **Options** menu.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of how to delete existing conversation flow elements.]( ../media/power-virtual-agents/delete-action.png) ]( ../media/power-virtual-agents/delete-action.png#lightbox)
-
-Below the *Message* node, select the (**+**) icon, then select **Call an action**.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of how select the Call an action feature.]( ../media/power-virtual-agents/trigger-action-for-power-automate.png) ]( ../media/power-virtual-agents/trigger-action-for-power-automate.png#lightbox)
-
-Select **Create a flow**. This takes you to the Power Automate portal.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of where to find the Create a flow action.]( ../media/power-virtual-agents/create-flow.png) ]( ../media/power-virtual-agents/create-flow.png#lightbox)
-
-Power Automate opens a new template as shown below.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the default Power Automate template.]( ../media/power-virtual-agents/power-automate-actions.png) ]( ../media/power-virtual-agents/power-automate-actions.png#lightbox)
-**Do not use the template shown above.**
-
-Instead you need to follow the steps below that creates a Power Automate flow. This flow:
-- Takes the incoming user text as a question, and sends it to custom question answering.
-- Returns the top response back to your bot.
-
-select **Create** in the left panel, then click "OK" to leave the page.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the Create action in the left panel and a confirmation message for navigating away from the page.]( ../media/power-virtual-agents/power-automate-create-new.png) ]( ../media/power-virtual-agents/power-automate-create-new.png#lightbox)
-
-Select "Instant Cloud flow"
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the Instant cloud flow selection box.]( ../media/power-virtual-agents/create-instant-cloud-flow.png) ]( ../media/power-virtual-agents/create-instant-cloud-flow.png#lightbox)
-
-For testing this connector, you can select “When PowerVirtual Agents calls a flow” and select **Create**.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the When Power Virtual Agents calls a flow selection in the Choose how to trigger this flow list.]( ../media/power-virtual-agents/create-trigger.png) ]( ../media/power-virtual-agents/create-trigger.png#lightbox)
-
-Select "New Step" and search for "Power Virtual Agents". Choose "Add an input" and select text. Next, provide the keyword and the value.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the Add an input option.]( ../media/power-virtual-agents/flow-step-1.png) ]( ../media/power-virtual-agents/flow-step-1.png#lightbox)
-
-Select "New Step" and search "Language - custom question answering" and choose "Generate answer from Project" from the three actions.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the Generate answer from Project selection in the Action list.]( ../media/power-virtual-agents/flow-step-2.png) ]( ../media/power-virtual-agents/flow-step-2.png#lightbox)
-
-This option helps in answering the specified question using your project. Type in the project name, deployment name and API version and select the question from the previous step.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of fields for the Generate answer from Project action.]( ../media/power-virtual-agents/flow-step-3.png) ]( ../media/power-virtual-agents/flow-step-3.png#lightbox)
-
-Select "New Step" and search for "Initialize variable". Choose a name for your variable, and select the "String" type.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the Initialize variable action fields.]( ../media/power-virtual-agents/flow-step-4.png) ]( ../media/power-virtual-agents/flow-step-4.png#lightbox)
-
-Select "New Step" again, and search for "Apply to each", then select the output from the previous steps and add an action of "Set variable" and select the connector action.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the Set variable action within the Apply to each step.]( ../media/power-virtual-agents/flow-step-5.png) ]( ../media/power-virtual-agents/flow-step-5.png#lightbox)
-
-Select "New Step" and search for "Return value(s) to Power Virtual Agents" and type in a keyword, then choose the previous variable name in the answer.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the Return value(s) to Power Virtual Agents step, containing the previous variable.]( ../media/power-virtual-agents/flow-step-6.png) ]( ../media/power-virtual-agents/flow-step-6.png#lightbox)
-
-The list of completed steps should look like this.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the full list of completed steps within Power Virtual Agents.]( ../media/power-virtual-agents/flow-step-7.png) ]( ../media/power-virtual-agents/flow-step-7.png#lightbox)
-
-Select **Save** to save the flow.
-
-## Create a solution and add the flow
-
-For the bot to find and connect to the flow, the flow must be included in a Power Automate solution.
-
-1. While still in the Power Automate portal, select Solutions from the left-side navigation.
-2. Select **+ New solution**.
-3. Enter a display name. The list of solutions includes every solution in your organization or school. Choose a naming convention that helps you filter to just your solutions. For example, you might prefix your email to your solution name: jondoe-power-virtual-agent-question-answering-fallback.
-4. Select your publisher from the list of choices.
-5. Accept the default values for the name and version.
-6. Select **Create** to finish the process.
-
-**Add your flow to the solution**
-
-1. In the list of solutions, select the solution you just created. It should be at the top of the list. If it isn't, search by your email name, which is part of the solution name.
-2. In the solution, select **+ Add existing**, and then select Flow from the list.
-3. Find your flow from the **Outside solutions** list, and then select Add to finish the process. If there are many flows, look at the **Modified** column to find the most recent flow.
-
-## Add your solution's flow to Power Virtual Agents
-
-1. Return to the browser tab with your bot in Power Virtual Agents. The authoring canvas should still be open.
-2. To insert a new step in the flow, above the **Message** action box, select the plus (+) icon. Then select **Call an action**.
-3. From the **Flow** pop-up window, select the new flow named **Generate answers using Question Answering Project...**. The new action appears in the flow.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the Call an action using the Generate answers using Question Answering Project flow.]( ../media/power-virtual-agents/flow-step-8.png) ]( ../media/power-virtual-agents/flow-step-8.png#lightbox)
-
-4. To correctly set the input variable to the QnA Maker action, select **Select a variable**, then select **bot.UnrecognizedTriggerPhrase**.
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the selected bot.UnrecognizedTriggerPhrase variable within the action call.]( ../media/power-virtual-agents/flow-step-9.png) ]( ../media/power-virtual-agents/flow-step-9.png#lightbox)
-
-5. To correctly set the output variable to the custom Question Answering action, in the **Message** action, select **UnrecognizedTriggerPhrase**, then select the icon to insert a variable, {x}, then select **FinalAnswer**.
-6. From the context toolbar, select **Save**, to save the authoring canvas details for the topic.
-
-Here's what the final bot canvas looks like:
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the completed bot canvas.]( ../media/power-virtual-agents/flow-step-10.png) ]( ../media/power-virtual-agents/flow-step-10.png#lightbox)
-
-## Test the bot
-
-As you design your bot in Power Virtual Agents, you can use the [Test bot pane](/power-virtual-agents/authoring-test-bot) to see how the bot leads a customer through the bot conversation.
-
-1. In the test pane, toggle **Track between topics**. This allows you to watch the progression between topics, as well as within a single topic.
-2. Test the bot by entering the user text in the following order. The authoring canvas reports the successful steps with a green check mark.
-
-|**Question order**|**Test questions**                                                 |**Purpose**                                                                                                                           |
-|------------------|-------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------|
-|1                 |Hello                                                              |Begin conversation                                                                                                                          |
-|2                 |Store hours                                                        |Sample topic. This is configured for you without any additional work on your part.                                                                                                                            |
-|3                 |Yes                                                                |In reply to "Did that answer your question?"                                                                                                                                     |
-|4                 |Excellent                                                          |In reply to "Please rate your experience."                                                                                                                                     |
-|5                 |Yes                                                                |In reply to "Can I help with anything else?"                                                                                                                                     |
-|6                 |How can I improve the throughput performance for query predictions?|This question triggers the fallback action, which sends the text to your project to answer. Then the answer is shown. the green check marks for the individual actions indicate success for each action.|
-
-> [!div class="mx-imgBorder"]
-> [ ![Screenshot of the completd test bot running alongside the tutorial flow.]( ../media/power-virtual-agents/flow-step-11.png) ]( ../media/power-virtual-agents/flow-step-11.png#lightbox)
-
-## Publish your bot
-
-To make the bot available to all members of your organization, you need to publish it.
-
-Publish your bot by following the steps in [Publish your bot](/power-virtual-agents/publication-fundamentals-publish-channels).
-
-## Share your bot
-
-To make your bot available to others, you first need to publish it to a channel. For this tutorial we'll use the demo website.
-
-Configure the demo website by following the steps in [Configure a chatbot for a live or demo website](/power-virtual-agents/publication-connect-bot-to-web-channels).
-
-Then you can share your website URL with your school or organization members.
-
-## Clean up resources
-
-When you're done with the project, remove the QnA Maker resources in the Azure portal.
-
-## See also
-
-* [Tutorial: Create an FAQ bot](../tutorials/bot-service.md)

@@ -226,22 +226,12 @@ items:
         href: conversational-language-understanding/concepts/app-architecture.md
     - name: Tutorials
       items:
-      - name: Create an FAQ Bot
-        href: question-answering/tutorials/bot-service.md
-        displayName: bot framework, chatbot
-      - name: Guided conversations
-        href: question-answering/tutorials/guided-conversations.md
       - name: Active learning
         href: question-answering/tutorials/active-learning.md
       - name: Adding synonyms
         href: question-answering/tutorials/adding-synonyms.md
-      - name: Multiple languages
-        href: question-answering/tutorials/multiple-languages.md
       - name: Multiple domains
         href: question-answering/tutorials/multiple-domains.md
-      - name: Add your custom question answering project to Microsoft Copilot Studios
-        href: question-answering/tutorials/power-virtual-agents.md
-        displayName: power virtual agents, pva integration, chatbot, virtual assistant
     - name: Reference
       items:
       - name: General
@@ -290,12 +280,6 @@ items:
       - name: Label data
         href: custom-text-classification/how-to/tag-data.md
         displayName: tag data, annotate text, training data
-      - name: Auto label your data (preview)
-        href: custom-text-classification/how-to/use-autolabeling.md
-        displayName: automatic annotation, smart labeling, ai assisted labeling
-      - name: Label data with Azure Machine Learning
-        href: custom/azure-machine-learning-labeling.md
-        displayName: azure ml labeling, aml annotation
       - name: Train a model
         href: custom-text-classification/how-to/train-model.md
         displayName: training, classifier, build model