@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.author: lajanuar
 ---
 
@@ -51,7 +51,7 @@ These custom roles only apply to Language resources.
 
 ### Cognitive Services Language Reader
 
-A user that should only be validating and reviewing the Language apps, typically a tester to ensure the application is performing well before deploying the project. They may want to review the application’s assets to notify the app developers of any changes that need to be made, but do not have direct access to make them. Readers will have access to view the evaluation results.
+A user that should only be validating and reviewing the Language apps, typically a tester to ensure the application is performing well before deploying the project. They might want to review the application’s assets to notify the app developers of any changes that need to be made, but do not have direct access to make them. Readers will have access to view the evaluation results.
 
 
 :::row:::
@@ -85,7 +85,7 @@ A user that should only be validating and reviewing the Language apps, typically
 
 ### Cognitive Services Language Writer
 
-A user that is responsible for building and modifying an application, as a collaborator in a larger team. The collaborator can modify the Language apps in any way, train those changes, and validate/test those changes in the portal. However, this user shouldn’t have access to deploying this application to the runtime, as they may accidentally reflect their changes in production. They also shouldn’t be able to delete the application or alter its prediction resources and endpoint settings (assigning or unassigning prediction resources, making the endpoint public). This restricts this role from altering an application currently being used in production. They may also create new applications under this resource, but with the restrictions mentioned.
+A user that is responsible for building and modifying an application, as a collaborator in a larger team. The collaborator can modify the Language apps in any way, train those changes, and validate/test those changes in the portal. However, this user shouldn’t have access to deploying this application to the runtime, as they might accidentally reflect their changes in production. They also shouldn’t be able to delete the application or alter its prediction resources and endpoint settings (assigning or unassigning prediction resources, making the endpoint public). This restricts this role from altering an application currently being used in production. They might also create new applications under this resource, but with the restrictions mentioned.
 
 :::row:::
     :::column span="":::
@@ -104,7 +104,7 @@ A user that is responsible for building and modifying an application, as a colla
     :::column-end:::
     :::column span="":::
       * All APIs under Language reader
-      * All POST, PUT and PATCH APIs under:
+      * All POST, PUT, and PATCH APIs under:
          * [Language conversational language understanding APIs](/rest/api/language/2023-04-01/conversational-analysis-authoring)
          * [Language text analysis APIs](/rest/api/language/2023-04-01/text-analysis-authoring)
          * [question answering projects](/rest/api/questionanswering/question-answering-projects)

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.author: lajanuar
 ---
 

@@ -0,0 +1,126 @@
+---
+title: Configure the conversational language understanding  service for fine-tune models
+description: This article details Azure AI resource configurations for conversational language understanding fine-tune models.
+ms.service: azure-ai-language
+ms.topic: how-to
+author: laujan
+ms.author: lajanuar
+ms.date: 06/25/2025
+ms.custom: language-service-question-answering
+---
+
+# Configure your environment for Azure AI resources and permissions
+
+In this guide, we walk you through configuring your Azure AI resources and permissions for conversational language understanding (CLU) projects. We present two options:
+
+* [**Option 1: Configure an Azure AI Foundry resource**](#option-1-configure-an-azure-ai-foundry-resource). Azure AI Foundry offers a unified environment for building generative AI applications and using Azure AI services. All essential tools are together in one environment for all stages of AI app development.
+
+* [**Option 2: Configure Azure Language and Azure OpenAI resources**](#option-2-configure-azure-language-resource-and-azure-openai-resources). Azure OpenAI allows users to access OpenAI's language models within the Azure platform, providing security, regulatory compliance, and integration with other Azure services.
+
+Completing these setups is essential for fully integrating your environment with Azure AI Services. You only need to perform this setup once—afterward, you have seamless access to advanced, AI-powered conversational language understanding capabilities.
+
+In addition, we show you how to assign the correct roles and permissions within the Azure portal. These steps help you get started quickly and effectively with Azure AI Language.
+
+## Prerequisites
+
+Before you can set up your resources, you need:
+
+* **An active Azure subscription**. If you don't have one, you can [create one for free](https://azure.microsoft.com/free/cognitive-services).
+* **Requisite permissions**. Make sure the person establishing the account and project is assigned as the Azure AI Account Owner role at the subscription level. Alternatively, having either the **Contributor** or **Cognitive Services Contributor** role at the subscription scope also meets this requirement. For more information, *see* [Role based access control (RBAC)](../../../openai/how-to/role-based-access-control.md#cognitive-services-contributor).
+* An [Azure AI Foundry multi-service resource](../../../multi-service-resource.md) or an [Azure AI Language resource](https://portal.azure.com/?Microsoft_Azure_PIMCommon=true#create/Microsoft.CognitiveServicesTextAnalytics).
+
+* An [Azure OpenAI resource](https://portal.azure.com/#create/Microsoft.CognitiveServicesOpenAI) (optional but required for [option 2](#option-2-configure-azure-language-resource-and-azure-openai-resources))
+
+> [!NOTE]
+>
+> We highly recommend that you use an Azure AI Foundry resource in the AI Foundry; however, you can also follow these instructions using a Language resource.
+
+## Option 1: Configure an Azure AI Foundry resource
+
+Azure AI Foundry offers a unified platform for building, managing, and deploying AI solutions with a wide array of models and tools. With this integration, you gain access to features like **Quick Deploy** for rapid model **fine-tuning** and **suggest utterances** to expand your training data with generative AI. New features are continually added, making Azure AI Foundry the recommended choice for scalable CLU solutions.
+
+1. Navigate to the [Azure portal](https://azure.microsoft.com/#home).
+
+1. Go to your Azure AI Foundry resource (select **All resources** to locate your resource).
+
+1. Next, select **Access Control (IAM)** on the left panel, then select **Add role assignment**.
+
+   :::image type="content" source="../media/configure-resources/add-role-assignment.png" alt-text="Screenshot of add role assignment selector in the Azure portal.":::
+
+1. Search and select the **Cognitive Services User** role. Select **Next**.
+
+   :::image type="content" source="../media/configure-resources/cognitive-services-user.png" alt-text="Screenshot of Cognitive Services User from the job function roles list in the Azure portal.":::
+
+1. Navigate to the **Members** tab and then select **Managed Identity**.
+
+   :::image type="content" source="../media/configure-resources/managed-identity.png" alt-text="Screenshot of assign member access selector in the Azure portal.":::
+
+1. Select **Select members**, then in the right panel, search for and choose your Azure AI Foundry resource (the one you're using for this project), and choose **Select**.
+
+1. Finally, select **Review + assign** to confirm your selection.
+
+1. Your resources are now set up properly. Continue with setting up the fine-tuning task and continue customizing your CLU project.
+
+## Option 2: Configure Azure Language resource and Azure OpenAI resources
+
+Azure OpenAI is a cloud-based solution that brings the advanced capabilities of OpenAI's language models to the Azure platform. With this service, you can easily incorporate natural language processing features into your applications without extensive AI or machine learning expertise. 
+
+##### Step 1: Assign the correct role to the Azure OpenAI resource
+
+1. Navigate to the [Azure portal](https://azure.microsoft.com/#home).
+
+1. Go to your Azure OpenAI resource. (select **All resources** to locate your resource).
+
+1. Next, select **Access Control (IAM)** on the left panel, then select **Add role assignment**.
+
+   :::image type="content" source="../media/configure-resources/add-role-assignment.png" alt-text="Screenshot of add role assignment selector in the Azure portal.":::
+
+1. Search and select the **Cognitive Services User** role, then select **Next**.
+
+   :::image type="content" source="../media/configure-resources/cognitive-services-user.png" alt-text="Screenshot of Cognitive Services User from the job function roles list in the Azure portal.":::
+
+1. Navigate to the **Members** tab and then select **Managed Identity**.
+
+   :::image type="content" source="../media/configure-resources/managed-identity.png" alt-text="Screenshot of assign member access selector in the Azure portal.":::
+
+1. Select **Select members**, then in the right panel, search for and choose your Azure AI Foundry resource (the one you're using for this project), and choose **Select**.
+
+1. Finally, select **Review + assign** to confirm your selection.
+
+
+##### Step 2: Configure connections in AI Foundry
+
+Azure AI Foundry offers a unified platform where you can easily build, manage, and deploy AI solutions using a wide range of models and tools. Connections enable authentication and access to both Microsoft and external resources within your Azure AI Foundry projects.
+
+1. Sign into [Azure AI Foundry](https://ai.azure.com/) using your account and required subscription. Then, select the project containing your desired Azure AI Foundry resource.
+
+1. Next, navigate to the **Management Center** in the bottom left corner of the page.
+
+1. Scroll to the **Connected resources** section of the Management center.
+
+    :::image type="content" source="../media/configure-resources/ai-foundry-management-center.png" alt-text="Screenshot of the management center selector in the Azure AI Foundry.":::
+
+
+1. Select the  **+ New connection** button.
+
+   :::image type="content" source="../media/configure-resources/new-connection.png" alt-text="Screenshot of the new connection button in the Azure AI Foundry.":::
+
+
+1. In the new window, select **Azure AI Language** as the resource type, then find your Azure AI Language resource.
+
+1. Select **Add connection** in the corner of your selected Azure AI Language resource.
+
+1. Select **Azure OpenAI** as the resource type, then find your desired Azure OpenAI resource.
+
+1. Ensure **Authentication** is set to **API key**.
+
+1. Select **Add connection**, then select **Close**.
+
+   :::image type="content" source="../media/configure-resources/connect-language-resource.png" alt-text="Screenshot of connect search resource selector in the Azure AI Foundry.":::
+
+1. Your resources are now set up properly. Continue with setting up the fine-tuning task and customizing your CLU project.
+
+## Next Steps
+
+[Create a CLU fine-tuning task](train-model.md#train-your-model)
+

@@ -6,18 +6,18 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.author: lajanuar
 ms.custom: language-service-clu,
 ---
 
 # Deploy a model 
 
-Once you are satisfied with how your model performs, it's ready to be deployed, and query it for predictions from utterances. Deploying a model makes it available for use through the [prediction API](/rest/api/language/2023-04-01/conversation-analysis-runtime/analyze-conversation).
+Once you're satisfied with how your model performs, it's ready to be deployed, and query it for predictions from utterances. Deploying a model makes it available for use through the [prediction API](/rest/api/language/2023-04-01/conversation-analysis-runtime/analyze-conversation).
 
 ## Prerequisites
 
-* A successfully [created project](create-project.md) 
+* A [created project](create-project.md) 
 * [Labeled utterances](tag-utterances.md) and successfully [trained model](train-model.md)
 * Reviewed the [model performance](view-model-evaluation.md) to determine how your model is performing.
 
@@ -45,7 +45,7 @@ After you have reviewed the model's performance and decide it's fit to be used i
 
 ## Swap deployments
 
-After you are done testing a model assigned to one deployment, you might want to assign it to another deployment. Swapping deployments involves:
+After you're done testing a model assigned to one deployment, you might want to assign it to another deployment. Swapping deployments involves:
 * Taking the model assigned to the first deployment, and assigning it to the second deployment. 
 * taking the model assigned to second deployment and assign it to the first deployment. 
 
@@ -89,7 +89,7 @@ You can [deploy your project to multiple regions](../../concepts/custom-features
 
 ## Unassign deployment resources
 
-When unassigning or removing a deployment resource from a project, you will also delete all the deployments that have been deployed to that resource's region.
+When unassigning or removing a deployment resource from a project, you'll also delete all the deployments that have been deployed to the resource's region.
 
 # [Language Studio](#tab/language-studio)
 

@@ -6,68 +6,141 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 04/29/2025
+ms.date: 06/23/2025
 ms.author: lajanuar
 ms.custom: language-service-clu
 ---
 
-# Train your conversational language understanding model
+# Train a conversational language understanding model
 
-After you have completed [labeling your utterances](tag-utterances.md), you can start training a model. Training is the process where the model learns from your [labeled utterances](tag-utterances.md). <!--After training is completed, you will be able to [view model performance](view-model-evaluation.md).-->
+After you complete [labeling your utterances](tag-utterances.md), you can start training a model. Training is the process where the model learns from your [labeled utterances](tag-utterances.md). <!--After training is completed, you will be able to [view model performance](view-model-evaluation.md).-->
 
-To train a model, start a training job. Only successfully completed jobs create a model. Training jobs expire after seven days, after this time you will no longer be able to retrieve the job details. If your training job completed successfully and a model was created, it won't be affected by the job expiring. You can only have one training job running at a time, and you can't start other jobs in the same project. 
+To train a model, start a training job. Only successfully completed jobs create a model. Training jobs expire after seven days, then you can no longer retrieve the job details. If your training job completed successfully and a model was created, the job doesn't expire. You can only have one training job running at a time, and you can't start other jobs in the same fine tuning task.
 
-The training times can be anywhere from a few seconds when dealing with simple projects, up to a couple of hours when you reach the [maximum limit](../service-limits.md) of utterances.
+> [!NOTE]
+>
+> When using the **Quick Deploy** option, Conversational Language Understanding (CLU) automatically creates an instant training job to set up your CLU intent router using your selected `LLM` deployment.
 
-Model evaluation is triggered automatically after training is completed successfully. The evaluation process starts by using the trained model to run predictions on the utterances in the testing set, and compares the predicted results with the provided labels (which establishes a baseline of truth). <!--The results are returned so you can review the [model’s performance](view-model-evaluation.md).-->
+The training times can be anywhere from a few seconds for simple projects, up to several hours when you reach the [maximum limit](../service-limits.md) of utterances.
+
+Model evaluation is triggered automatically after training is completed successfully. The evaluation process starts by using the trained model to run predictions on the utterances in the testing set, and compares the predicted results with the provided labels (which establishes a baseline of truth). <!--The results are returned so you can review the [model's performance](view-model-evaluation.md).-->
 
 ## Prerequisites
 
-* A successfully [created project](create-project.md) with a configured Azure blob storage account
-* [Labeled utterances](tag-utterances.md)
+* **An active Azure subscription**. If you don't have one, you can [create one for free](https://azure.microsoft.com/free/cognitive-services).
+* **Requisite permissions**. Make sure the person establishing the account and project is assigned as the Azure AI Account Owner role at the subscription level. Alternatively, having either the **Contributor** or **Cognitive Services Contributor** role at the subscription scope also meets this requirement. For more information, *see* [Role based access control (RBAC)](../../../openai/how-to/role-based-access-control.md#cognitive-services-contributor)
+* **A project created in the Azure AI Foundry**. For more information, *see* [Create an AI Foundry project](../../../../ai-foundry/how-to/create-projects.md)
+* [**Your labeled utterances**](tag-utterances.md) tagged for your fine tuning task.
+
 
 <!--See the [project development lifecycle](../overview.md#project-development-lifecycle) for more information.-->
 
-[!INCLUDE [Balance training data](../includes/balance-training-data.md)]
+## Balance training data
+
+When it comes to training data, try to keep your schema well-balanced. Including large quantities of one intent and few of another results in a model with bias towards particular intents.
+
+To address this scenario, you might need to down sample your training set. Or you might need to add to it. To down sample, you can:
 
+* Get rid of a certain percentage of the training data randomly.
+* Analyze the dataset and remove overrepresented duplicate entries, which is a more systematic manner.
 
+To add to the training set, in Language Studio, on the **Data labeling** tab, select **Suggest utterances**. Conversational Language Understanding sends a call to [Azure OpenAI](../../../openai/overview.md) to generate similar utterances.
+
+:::image type="content" source="../media/suggest-utterances.png" alt-text="Screenshot that shows an utterance suggestion in Language Studio." lightbox="../media/suggest-utterances.png":::
+
+You should also look for unintentional patterns in the training set. For example, look to see if the training set for a particular intent is all lowercase or starts with a particular phrase. In such cases, the model you train might learn these unintended biases in the training set instead of being able to generalize.
+
+We recommend that you introduce casing and punctuation diversity in the training set. If your model is expected to handle variations, be sure to have a training set that also reflects that diversity. For example, include some utterances in proper casing and some in all lowercase.
 
 ## Data splitting
 
 Before you start the training process, labeled utterances in your project are divided into a training set and a testing set. Each one of them serves a different function.
-The **training set** is used in training the model, this is the set from which the model learns the labeled utterances. 
-The **testing set** is a blind set that isn't introduced to the model during training but only during evaluation. 
+The **training set** is used in training the model, the set from which the model learns the labeled utterances.
+The **testing set** is a blind set that isn't introduced to the model during training but only during evaluation.
 
-After the model is trained successfully, the model can be used to make predictions from the utterances in the testing set. These predictions are used to calculate [evaluation metrics](../concepts/evaluation-metrics.md). 
-It is recommended to make sure that all your intents and entities are adequately represented in both the training and testing set.
+After the model is trained successfully, the model can be used to make predictions from the utterances in the testing set. These predictions are used to calculate [evaluation metrics](../concepts/evaluation-metrics.md).
+We recommend that you make sure that all your intents and entities are adequately represented in both the training and testing set.
 
 Conversational language understanding supports two methods for data splitting:
 
-* **Automatically splitting the testing set from training data**: The system will split your tagged data between the training and testing sets, according to the percentages you choose. The recommended percentage split is 80% for training and 20% for testing. 
+* **Automatically splitting the testing set from training data**: The system splits your tagged data between the training and testing sets, according to the percentages you choose. The recommended percentage split is 80% for training and 20% for testing.
 
  > [!NOTE]
- > If you choose the **Automatically splitting the testing set from training data** option, only the data assigned to training set will be split according to the percentages provided.
+ > If you choose the **Automatically splitting the testing set from training data** option, only the data assigned to a training set is split according to the percentages provided.
 
-* **Use a manual split of training and testing data**: This method enables users to define which utterances should belong to which set. This step is only enabled if you have added utterances to your testing set during [labeling](tag-utterances.md).
+* **Use a manual split of training and testing data**: This method enables users to define which utterances should belong to which set. This step is only enabled if you added utterances to your testing set during [labeling](tag-utterances.md).
 
 ## Training modes
 
-CLU supports two modes for training your models
+Conversational Language Understanding (CLU) supports two modes for training your models
 
-* **Standard training** uses fast machine learning algorithms to train your models relatively quickly. This is currently only available for **English** and is disabled for any project that doesn't use English (US), or English (UK) as its primary language. This training option is free of charge. Standard training allows you to add utterances and test them quickly at no cost. The evaluation scores shown should guide you on where to make changes in your project and add more utterances. Once you’ve iterated a few times and made incremental improvements, you can consider using advanced training to train another version of your model.
+* **Standard training** uses fast machine learning algorithms to quickly train your models. This training level is currently only available for **English** and is disabled for any project that doesn't use English (US), or English (UK) as its primary language. This training option is free of charge. Standard training allows you to add utterances and test them quickly free of charge. The evaluation scores shown should guide you on where to make changes in your project and add more utterances. While standard training is best for testing and updating your model quickly, you should see better model quality when using advanced training. While standard training is best for testing and updating your model quickly, you should see better model quality when using advanced training. Once you iterate a few times and made incremental improvements, you can consider using advanced training to train another version of your model.
 
-* **Advanced training** uses the latest in machine learning technology to customize models with your data. This is expected to show better performance scores for your models and will enable you to use the [multilingual capabilities](../language-support.md#multi-lingual-option) of CLU as well. Advanced training is priced differently. See the [pricing information](https://azure.microsoft.com/pricing/details/cognitive-services/language-service) for details.
+* **Advanced training** uses the latest in machine learning technology to customize models with your data. This training level is expected to show better performance scores for your models and enables you to use the [multilingual capabilities](../language-support.md#multi-lingual-option) of CLU as well. Advanced training is priced differently. See the [pricing information](https://azure.microsoft.com/pricing/details/cognitive-services/language-service) for details.
 
-Use the evaluation scores to guide your decisions. There might be times where a specific example is predicted incorrectly in advanced training as opposed to when you used standard training mode. However, if the overall evaluation results are better using advanced, then it is recommended to use your final model. If that isn’t the case and you are not looking to use any multilingual capabilities, you can continue to use model trained with standard mode.
+Use the evaluation scores to guide your decisions. There may be times where a specific example is predicted incorrectly in advanced training as opposed to when you used standard training mode. However, if the overall evaluation results are better using advanced training, then we recommend that you use that model as your final model. If that isn't the case and you aren't looking to use any multilingual capabilities, you can continue to use model trained with standard mode.
 
 > [!Note]
-> You should expect to see a difference in behaviors in intent confidence scores between the training modes as each algorithm calibrates their scores differently. 
+> You should expect to see a difference in behaviors in intent confidence scores between the training modes as each algorithm calibrates their scores differently.
+
+## Train your model
+
+# [Azure AI Foundry](#tab/ai-foundry)
+
+1. Navigate to the [Azure AI Foundry](https://ai.azure.com/).
+1. If you aren't already signed in, the portal prompts you to do so with your Azure credentials.
+1. Once signed in, you can create or access your existing projects within Azure AI Foundry.
+1. If you're not already at your project for this task, select it.
+1. Select Fine-tuning from the left navigation panel.
+
+   :::image type="content" source="../media/select-fine-tuning.png" alt-text="Screenshot of fine-tuning selector in the Azure AI Foundry.":::
+
+1. Select **the AI Service fine-tuning** tab and then **+ Fine-tune** button.
+
+   :::image type="content" source="../media/fine-tune-button.png" alt-text="Screenshot of fine-tuning button in the Azure AI Foundry.":::
+
+1. From **Create service fine-tuning** window, choose the **Conversational language understanding** tab then select **Next**.
+
+   :::image type="content" source="../media/select-project.png" alt-text="Screenshot of conversational language understanding tab in the Azure AI Foundry.":::
 
-## Train model 
+1. In **Create CLU fine tuning task** window, complete the **Name** and **Language** fields. If you're using the free **Standard Training** mode, select **English** for the language field.
 
-# [Language Studio](#tab/language-studio)
+    > [!NOTE]
+    >
+    > * **Standard training** enables faster training times and quicker iterations; however it's only available for English.
+    > * **Advanced training** includes longer training durations and is supported for English, other languages, and multilingual projects.
+    > * For more information, *see* [Training modes](#training-modes).
 
-[!INCLUDE [Train model](../includes/language-studio/train-model.md)]
+1. From the immediate left navigation panel, choose **Train model**.
+
+   :::image type="content" source="../media/train-fine-tuning-model.png" alt-text="Screenshot of the train model selection in the Azure AI Foundry.":::
+
+1. Next, select the **+ Train model** button from the main window.
+1. In the **Train a new model** window, select one of the following:
+
+   * **Create a new training model**. Enter a new **Model name**
+   * **Overwrite an existing model name**. Replace an existing model trained on the new data.
+1. Select **Your current training version**. The training version is the algorithm that determines how your model learns from your data. The machine learning used to train models is regularly updated. We recommend using the latest version for training, as it underwent thorough testing and provides the most balanced model predictions from your data.
+
+   :::image type="content" source="../media/select-mode.png" alt-text="Screenshot of select a mode options in the Azure AI Foundry." :::
+
+1. Select **Next**.
+
+1. Select one of the **Data splitting** methods presented in the **Train a new model** window:
+
+   * **Automatically split the testing set from training data** enables the system to split your utterances between the training and testing sets, according to the specified percentages.
+   * **Use a manual split of training and testing data** enables the system to use the training and testing sets that you assigned and labeled to create your custom model. ***This option is only available if you have added utterances to your testing set when you labeled your utterances**.
+
+      :::image type="content" source="../media/data-splitting.png" alt-text="Screenshot of data splitting option in the Azure AI Foundry.":::
+
+1. Select **Next** and then select **Create**.
+
+1. Choose the training job ID from the list. A panel appears that details the training progress, job status, and other details for this job.
+
+> [!NOTE]
+> * Only successfully completed training jobs generate models.
+> * Training can take from a few minutes to a few hours based on the count of utterances.
+> * You can only have one training job running at a time. You can't start other training jobs within the same project until the running job is completed.
 
 # [REST APIs](#tab/rest-api)
 
@@ -77,26 +150,30 @@ Use the evaluation scores to guide your decisions. There might be times where a
 
 ### Get training job status
 
-Training could take sometime 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 it is successfully completed.
+Training could 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 it successfully completes.
 
 [!INCLUDE [get training model status](../includes/rest-api/get-training-status.md)]
 
 ---
 
 ### Cancel training job
 
-# [Language Studio](#tab/language-studio)
+# [Azure AI Foundry](#tab/ai-foundry)
 
-[!INCLUDE [Cancel training](../includes/language-studio/cancel-training.md)]
+When you're done with your custom model, you can delete the deployment and model. You can also delete the training and validation files you uploaded to the service, if needed:
+
+* To delete your custom model, on the left navigation pane select **My assets** → **Models + endpoints**. Choose the custom model to delete from the **Model deployments** tab, and then select **Delete**.
+* To delete your training and validation files uploaded for training, on the left navigation pane select **Data + indexes**. Choose the file to delete, and then select **Delete**.
+
+  :::image type="content" source="../media/my-assets.png" alt-text="Screenshot of my assets section in the Azure AI Foundry.":::
 
 # [REST APIs](#tab/rest-api)
 
 [!INCLUDE [Cancel training](../includes/rest-api/cancel-training.md)]
 
 ---
 
-
 ## Next steps
 
-* [Model evaluation metrics](../concepts/evaluation-metrics.md)
+Review your model's performance with [model evaluation metrics](../concepts/evaluation-metrics.md).
 <!--* [Deploy and query the model](./deploy-model.md)-->

@@ -9,7 +9,7 @@ ms.author: lajanuar
 
 ## Balance training data
 
-When it comes to training data, try to keep your schema well balanced. Including large quantities of one intent and very few of another results in a model that's biased toward particular intents.
+When it comes to training data, try to keep your schema well balanced. Including large quantities of one intent and few of another results in a model with bias towards particular intents.
 
 To address this scenario, you might need to downsample your training set. Or you might need to add to it. To downsample, you can:
 

@@ -7,14 +7,14 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 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 will be used in the next step when training your model so that your model can learn from the labeled data. If you already have labeled 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 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 will be 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.
 
@@ -23,19 +23,19 @@ Before creating a custom text classification model, you need to have labeled dat
 Before you can label data, you need:
 
 * [A successfully created project](create-project.md) with a configured Azure blob storage account, 
-* Documents containing text data that have [been uploaded](design-schema.md#data-preparation) to your storage account.
+* Documents containing the [uploaded](design-schema.md#data-preparation) text data in your storage account.
 
 See the [project development lifecycle](../overview.md#project-development-lifecycle) for more information.
 
 ## Data labeling guidelines
 
-After [preparing your data, designing your schema](design-schema.md) and [creating your project](create-project.md), you will 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 will be 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 will 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. 
 
 As you label your data, keep in mind:
 
 * In general, more labeled data leads to better results, provided the data is labeled accurately.
 
-* There is no fixed number of labels that can guarantee your model will perform the best. Model performance on possible ambiguity in your [schema](design-schema.md), and the quality of your labeled data. Nevertheless, we recommend 50 labeled documents per class.
+* There is no fixed number of labels that can guarantee your model performs the best. Model performance on possible ambiguity in your [schema](design-schema.md), and the quality of your labeled data. Nevertheless, we recommend 50 labeled documents per class.
 
 ## Label your data
 
@@ -61,7 +61,7 @@ Use the following steps to label your data:
 
     # [Multi label classification](#tab/multi-classification)
     
-    **Multi label classification**: your file can be labeled with multiple classes, you can do so by selecting all applicable check boxes next to the classes you want to label this document with.
+    **Multi label classification**: your file can be labeled with multiple classes. You can do so by selecting all applicable check boxes next to the classes you want to label this document with.
     
     :::image type="content" source="../media/multiple.png" alt-text="A screenshot showing the multiple label classification tag page." lightbox="../media/multiple.png":::
     
@@ -77,24 +77,24 @@ Use the following steps to label your data:
 
 6. In the right side pane under the **Labels** pivot you can find all the classes in your project and the count of labeled instances per each.
 
-7. In the bottom section of the right side pane you can add the current file you are viewing to the training set or the testing set. By default all the documents are added to your training set. Learn more about [training and testing sets](train-model.md#data-splitting) and how they are used for model training and evaluation.
+7. In the bottom section of the right side pane you can add the current file you're viewing to the training set or the testing set. By default all the documents are added to your training set. Learn more about [training and testing sets](train-model.md#data-splitting) and how they're used for model training and evaluation.
 
     > [!TIP]
-    > If you are planning on using **Automatic** data splitting use the default option of assigning all the documents into your training set.
+    > If you're planning on using **Automatic** data splitting, use the default option of assigning all the documents into your training set.
 
 8. Under the **Distribution** pivot you can view the distribution across training and testing sets. You have two options for viewing:
    * *Total instances* where you can view count of all labeled instances of a specific class.
    * *documents with at least one label* where each document is counted if it contains at least one labeled instance of this class.
 
-9. While you're labeling, your changes will be synced periodically, if they have not been saved yet you will find a warning at the top of your page. If you want to save manually, select **Save labels** button at the bottom of the page.
+9. While you're labeling, your changes are synced periodically, if they have not been saved yet you will find a warning at the top of your page. If you want to save manually, select **Save labels** button at the bottom of the page.
 
 ## Remove labels
 
 If you want to remove a label, uncheck the button next to the class.
 
 ## Delete or classes
 
-To delete a class, select the delete icon next to the class you want to remove. Deleting a class will remove all its labeled instances from your dataset.
+To delete a class, select the icon next to the class you want to remove. Deleting a class will remove all its labeled instances from your dataset.
 
 ## Next steps
 

@@ -7,11 +7,11 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: tutorial
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.author: lajanuar
 ---
 
-# Tutorial: Triage incoming emails with power automate
+# Tutorial: Triage incoming emails with Power Automate
 
 In this tutorial you will categorize and triage incoming email using custom text classification. Using this [Power Automate](/power-automate/getting-started) flow, when a new email is received, its contents will have a classification applied, and depending on the result, a message will be sent to a designated channel on [Microsoft Teams](https://www.microsoft.com/microsoft-teams).
 
@@ -27,7 +27,7 @@ In this tutorial you will categorize and triage incoming email using custom text
 
 ## Create a Power Automate flow
 
-1. [Sign in to power automate](https://make.powerautomate.com/)
+1. [Sign in to Power Automate](https://make.powerautomate.com/)
 
 2. From the left side menu, select **My flows** and create a **Automated cloud flow**
 

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.author: lajanuar
 ms.custom: language-service-language-detection, ignite-2024
 ---

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: quickstart
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.author: lajanuar
 ms.custom: language-service-clu, mode-other
 zone_pivot_groups: usage-custom-language-features

@@ -5,7 +5,7 @@ ms.service: azure-ai-language
 ms.topic: conceptual
 author: laujan
 ms.author: lajanuar
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.custom: language-service-question-answering
 ---
 
@@ -34,7 +34,7 @@ Typically there are three parameters you need to consider:
 
     * The throughput for custom question answering is currently capped at 10 text records per second for both management APIs and prediction APIs.
 
-    * This should also influence your **Azure AI Search** SKU selection, see more details [here](/azure/search/search-sku-tier). Additionally, you might need to adjust Azure AI Search [capacity](/azure/search/search-capacity-planning) with replicas.
+    * This should also influence your **Azure AI Search** selection, see more details [here](/azure/search/search-sku-tier). Additionally, you might need to adjust Azure AI Search [capacity](/azure/search/search-capacity-planning) with replicas.
 
 * **Size and the number of projects**: Choose the appropriate [Azure search SKU](https://azure.microsoft.com/pricing/details/search/) for your scenario. Typically, you decide the number of projects you need based on number of different subject domains. One subject domain (for a single language) should be in one project.
 
@@ -58,7 +58,7 @@ The following table gives you some high-level guidelines.
 ## Recommended settings
 
 
-The throughput for custom question answering is currently capped at 10 text records per second for both management APIs and prediction APIs. To target 10 text records per second for your service, we recommend the S1 (one instance) SKU of Azure AI Search.
+The throughput for custom question answering is currently capped at 10 text records per second for both management APIs and prediction APIs. To target 10 text records per second for your service, we recommend the S1 (one instance) tier of Azure AI Search.
 
 
 ## Keys in custom question answering

@@ -6,7 +6,7 @@ ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
 ms.topic: how-to
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ---
 
 # Authoring API

@@ -1,20 +1,20 @@
 ---
 title: Adding chitchat to a custom question answering project
 titleSuffix: Azure AI services
-description: Adding personal chitchat to your bot makes it more conversational and engaging when you create a project. Custom question answering allows you to easily add a pre-populated set of the top chitchat, into your projects.
+description: Adding personal chitchat to your bot makes it more conversational and engaging when you create a project. Custom question answering allows you to easily add a prepopulated set of the top chitchat, into your projects.
 #services: cognitive-services
 manager: nitinme
 author: laujan
 ms.author: lajanuar
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.custom: language-service-question-answering
 ---
 
 # Use chitchat with a project
 
-Adding chitchat to your bot makes it more conversational and engaging. The chitchat feature in custom question answering allows you to easily add a pre-populated set of the top chitchat, into your project. This can be a starting point for your bot's personality, and it will save you the time and cost of writing them from scratch.
+Adding chitchat to your bot makes it more conversational and engaging. The chitchat feature in custom question answering allows you to easily add a prepopulated set of the top chitchat, into your project. This can be a starting point for your bot's personality, and it will save you the time and cost of writing them from scratch.
 
 This dataset has about 100 scenarios of chitchat in the voice of multiple personas, like Professional, Friendly and Witty. Choose the persona that most closely resembles your bot's voice. Given a user query, custom question answering tries to match it with the closest known chitchat question and answer.
 
@@ -70,7 +70,7 @@ To turn the views for context and metadata on and off, select **Show columns** i
 
 ## Add more chitchat questions and answers
 
-You can add a new chitchat question pair that is not in the predefined data set. Ensure that you are not duplicating a question pair that is already covered in the chitchat set. When you add any new chitchat question pair, it gets added to your **Editorial** source. To ensure the ranker understands that this is chitchat, add the metadata key/value pair "Editorial: chitchat", as seen in the following image:
+You can add a new chitchat question pair that is not in the predefined data set. Ensure that you are not duplicating a question pair that is already covered in the chitchat set. When you add any new chitchat question pair, it gets added to your **Editorial** source. To ensure the ranker understands that this is chitchat, add the metadata key/value pair "Editorial: chitchat," as seen in the following image:
 
 :::image type="content" source="../media/chit-chat/add-new-chit-chat.png" alt-text="Add chitchat question answer pairs" lightbox="../media/chit-chat/add-new-chit-chat.png":::
 

@@ -0,0 +1,125 @@
+---
+title: Configure the custom question answering service for fine-tune models
+description: This article details Azure AI resource configurations for custom question answering fine-tune models.
+ms.service: azure-ai-language
+ms.topic: how-to
+author: laujan
+ms.author: lajanuar
+ms.date: 06/24/2025
+ms.custom: language-service-question-answering
+---
+
+# Configure your environment for Azure AI resources
+
+In this guide, we walk you through configuring your Azure AI resources and permissions for custom question and answering projects, enabling you to fine-tune models with Azure AI Search and Custom Question Answering (CQA). Completing this setup is essential for fully integrating your environment with Azure AI Services. You only need to perform this setup once—afterward, you have seamless access to advanced, AI-powered question answering capabilities.
+
+In addition, we show you how to assign the correct roles and permissions within the Azure portal. These steps help you get started quickly and effectively with Azure AI Language.
+
+## Prerequisites
+
+Before you can set up your resources, you need:
+
+* **An active Azure subscription**. If you don't have one, you can [create one for free](https://azure.microsoft.com/free/cognitive-services).
+* **Requisite permissions**. Make sure the person establishing the account and project is assigned as the Azure AI Account Owner role at the subscription level. Alternatively, having either the **Contributor** or **Cognitive Services Contributor** role at the subscription scope also meets this requirement. For more information, *see* [Role based access control (RBAC)](../../../openai/how-to/role-based-access-control.md#cognitive-services-contributor).
+*   An [Azure AI Foundry multi-service resource](../../../multi-service-resource.md) or an [Azure AI Language resource](https://portal.azure.com/?Microsoft_Azure_PIMCommon=true#create/Microsoft.CognitiveServicesTextAnalytics).
+*   An [Azure AI Search resource](https://portal.azure.com/?Microsoft_Azure_PIMCommon=true#create/Microsoft.Search) (required for accessing CQA)
+
+
+> [!NOTE]
+>
+> We highly recommend that you use an Azure AI Foundry resource in the AI Foundry; however,  you can also follow these instructions using a Language resource.
+
+## Step 1: Assign the correct role to your Search resource
+
+Azure RBAC is an authorization system built on Azure Resource Manager. It provides fine-grained access management to Azure resources.
+
+1. Navigate to the [Azure portal](https://azure.microsoft.com/#home).
+
+1. Go to your Azure Search resource. (See **All resources** to find your Search resource.)
+
+1. In the Settings section on the left panel, select **Keys**.
+
+1. Make sure the **API Access control** button is set to **API keys**.
+
+   :::image type="content" source="../media/configure-resources/api-access-control.png" alt-text="Screenshot of API access control selector in the Azure portal."::: 
+
+1. Next, select **Access Control (IAM)** on the left panel, then select **Add role assignment**.
+
+   :::image type="content" source="../media/configure-resources/add-role-assignment.png" alt-text="Screenshot of add role assignment selector in the Azure portal.":::
+
+1. Search and select the **Azure AI Administrator** role. Select **Next**.
+
+   :::image type="content" source="../media/configure-resources/azure-ai-administrator.png" alt-text="Screenshot of Azure AI Administrator from the job function roles list in the Azure portal." lightbox="../media/configure-resources/azure-ai-administrator.png":::
+
+1. Navigate to the **Members** tab and then select **Assign access to User, group, or service principal**.
+
+   :::image type="content" source="../media/configure-resources/user-group-service-principal.png" alt-text="Screenshot of assign member access selector in the Azure portal.":::
+
+1. Select **Select members**, then add your account name, and choose **Select**.
+
+1. Finally, select **Review + assign** to confirm your selection.
+
+## Step 2: Configure connections in AI Foundry
+
+Azure AI Foundry offers a unified platform where you can easily build, manage, and deploy AI solutions using a wide range of models and tools. Connections enable authentication and access to both Microsoft and external resources within your Azure AI Foundry projects.
+
+1. Sign **into** [Azure AI Foundry](https://ai.azure.com/) using your account and required subscription. Then, select the project containing your Azure AI Foundry resource.
+
+1. Next, navigate to the **Management Center** in the bottom left corner of the page.
+
+1. Scroll to the **Connected resources** section of the Management center.
+
+   :::image type="content" source="../media/configure-resources/ai-foundry-management-center.png" alt-text="Screenshot of the management center selector in the Azure AI Foundry.":::
+
+1. Select the  **+ New connection** button.
+
+   :::image type="content" source="../media/configure-resources/new-connection.png" alt-text="Screenshot of the new connection button in the Azure AI Foundry.":::
+
+1. In the new window, select **Azure AI Search** as the resource type.
+
+1. Search for and display the Azure AI Search resource you connected in [Step 1](#step-1-assign-the-correct-role-to-your-search-resource).
+
+1. Ensure the Authentication is set to **API key**.
+
+1. Select **Add connection** then select **Close**.
+
+   :::image type="content" source="../media/configure-resources/connect-azure-search.png" alt-text="Screenshot of connect search resource selector in the Azure AI Foundry.":::
+
+## Step 3: Create a fine-tuning task with connected resources
+
+1. Navigate to **Go to project** at the end of the left navigation panel.
+
+   :::image type="content" source="../media/configure-resources/go-to-project.png" alt-text="Screenshot the go-to-project button in the Azure AI Foundry.":::
+
+1. Select **Fine-tuning** from the left navigation panel, choose the **AI Service fine-tuning** tab, and then select the **+ Fine-tune** button.
+
+   :::image type="content" source="../media/configure-resources/fine-tuning.png" alt-text="Screenshot of the fine tuning selector in the Azure AI Foundry.":::
+
+1. Choose **Custom question answering** as the task type from the new window, then select **Next**.
+
+1. Under **Connected service**, select your selected Azure AI Foundry resource. Then select your newly connected search resource.
+
+1. Your resources are now set up properly. Continue with setting up the fine-tuning task and customizing your CQA project.
+
+## Change Azure AI Search resource
+
+> [!WARNING]
+> If you change the Azure Search service associated with your language resource, you lose access to all the projects already present in it. Make sure you export the existing projects before you change the Azure Search service.
+
+If you create a language resource and its dependencies (such as Search) through the Azure portal, a Search service is created for you and linked to the language resource. After these resources are created, you can update the Search resource in the **Features** tab.
+
+1.  Go to your language resource in the Azure portal.
+
+1.  Select **Features** and select the Azure AI Search service you want to link with your language resource.
+
+    > [!NOTE]
+    > Your Language resource retains your Azure AI Search keys. If you update your search resource (for example, regenerating your keys), you need to select **Update Azure AI Search keys for the current search service**.
+
+    > [!div class="mx-imgBorder"]
+    > ![Add QnA to TA](../media/configure-resources/update-custom-feature.png)
+
+1.  Select **Save**.
+
+## Next Steps
+
+[Create, test, and deploy a custom question answering project](create-test-deploy.md)

@@ -1,37 +0,0 @@
----
-title: Configure the custom question answering service
-description: This document outlines advanced configurations for custom question answering enabled resources.
-ms.service: azure-ai-language
-ms.topic: how-to
-author: laujan
-ms.author: lajanuar
-ms.date: 11/21/2024
-ms.custom: language-service-question-answering
----
-
-# Configure custom question answering enabled resources
-
-You can configure custom question answering to use a different Azure AI Search resource.
-
-## Change Azure AI Search resource
-
-> [!WARNING]
-> If you change the Azure Search service associated with your language resource, you will lose access to all the projects already present in it. Make sure you export the existing projects before you change the Azure Search service.
-
-If you create a language resource and its dependencies (such as Search) through the Azure portal, a Search service is created for you and linked to the language resource. After these resources are created, you can update the Search resource in the **Features** tab.
-
-1.  Go to your language resource in the Azure portal.
-
-2.  Select **Features** and select the Azure AI Search service you want to link with your language resource.
-    
-    > [!NOTE]
-    > Your Language resource will retain your Azure AI Search keys. If you update your search resource (for example, regenerating your keys), you will need to select **Update Azure AI Search keys for the current search service**.
-    
-    > [!div class="mx-imgBorder"]
-    > ![Add QnA to TA](../media/configure-resources/update-custom-feature.png)
-    
-3.  Select **Save**.
-
-## Next steps
-
-* [Encrypt data at rest](./encrypt-data-at-rest.md)

@@ -9,7 +9,7 @@ ms.author: lajanuar
 recommendations: false
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.custom: language-service-question-answering
 ---
 
@@ -25,15 +25,15 @@ In custom question answering, you have the option to either select the language
 > ![Multi-lingual project selection](./media/language-support/choose-language.png)
 
 * When you are creating the first project in your service, you get a choice pick the language each time you create a new project. Select this option, to create projects belonging to different languages within one service.
-* Language setting option cannot be modified for the service, once the first project is created.
+* The language setting option cannot be modified for the service once the first project is created.
 * If you enable multiple languages for the project, then instead of having one test index for the service you will have one test index per project.
 
 ## Supporting multiple languages in one project
 
 If you need to support a project system, which includes several languages, you can:
 
 * Use the [Translator service](../../translator/translator-overview.md) to translate a question into a single language before sending the question to your project. This allows you to focus on the quality of a single language and the quality of the alternate questions and answers.
-* Create a custom question answering enabled language resource, and a project inside that resource, for every language. This allows you to manage separate alternate questions and answer text that is more nuanced for each language. This gives you much more flexibility but requires a much higher maintenance cost when the questions or answers change across all languages.
+* Create a custom question answering enabled language resource, and a project inside that resource, for every language. This allows you to manage separate alternate questions and answer text that is more nuanced for each language. This provides more flexibility but requires a much higher maintenance cost when the questions or answers change across all languages.
 
 ## Single language per resource
 
@@ -47,84 +47,82 @@ If you **select the option to set the language used by all projects associated w
 
 The following list contains the languages supported for a custom question answering resource.
 
-| Language |
-|--|
-| Arabic |
-| Armenian |
-| Bangla |
-| Basque |
-| Bulgarian |
-| Catalan |
-| Chinese_Simplified |
-| Chinese_Traditional |
-| Croatian |
-| Czech |
-| Danish |
-| Dutch |
-| English |
-| Estonian |
-| Finnish |
-| French |
-| Galician |
-| German |
-| Greek |
-| Gujarati |
-| Hebrew |
-| Hindi |
-| Hungarian |
-| Icelandic |
-| Indonesian |
-| Irish |
-| Italian |
-| Japanese |
-| Kannada |
-| Korean |
-| Latvian |
-| Lithuanian |
-| Malayalam |
-| Malay |
-| Norwegian |
-| Polish |
-| Portuguese |
-| Punjabi |
-| Romanian |
-| Russian |
-| Serbian_Cyrillic |
-| Serbian_Latin |
-| Slovak |
-| Slovenian |
-| Spanish |
-| Swedish |
-| Tamil |
-| Telugu |
-| Thai |
-| Turkish |
-| Ukrainian |
-| Urdu |
-| Vietnamese |
+- Arabic
+- Armenian
+- Bangla
+- Basque
+- Bulgarian
+- Catalan
+- Chinese_Simplified
+- Chinese_Traditional
+- Croatian
+- Czech
+- Danish
+- Dutch
+- English
+- Estonian
+- Finnish
+- French
+- Galician
+- German
+- Greek
+- Gujarati
+- Hebrew
+- Hindi
+- Hungarian
+- Icelandic
+- Indonesian
+- Irish
+- Italian
+- Japanese
+- Kannada
+- Korean
+- Latvian
+- Lithuanian
+- Malayalam
+- Malay
+- Norwegian
+- Polish
+- Portuguese
+- Punjabi
+- Romanian
+- Russian
+- Serbian_Cyrillic
+- Serbian_Latin
+- Slovak
+- Slovenian
+- Spanish
+- Swedish
+- Tamil
+- Telugu
+- Thai
+- Turkish
+- Ukrainian
+- Urdu
+- Vietnamese
 
 ## Query matching and relevance
 Custom question answering depends on [Azure AI Search language analyzers](/rest/api/searchservice/language-support) for providing results.
 
 While the Azure AI Search capabilities are on par for supported languages, custom question answering has an additional ranker that sits above the Azure search results. In this ranker model, we use some special semantic and word-based features in the following languages.
 
-|Languages with additional ranker|
-|--|
-|Chinese|
-|Czech|
-|Dutch|
-|English|
-|French|
-|German|
-|Hungarian|
-|Italian|
-|Japanese|
-|Korean|
-|Polish|
-|Portuguese|
-|Spanish|
-|Swedish|
-
-This additional ranking is an internal working of the custom question answering's ranker.
+- Chinese
+- Czech
+- Dutch
+- English
+- French
+- German
+- Hungarian
+- Italian
+- Japanese
+- Korean
+- Polish
+- Portuguese
+- Spanish
+- Swedish
+
+This ranking is an internal working of the custom question answering's ranker.
 
 ## Next steps
+
+* [Question answering quickstart](./quickstart/sdk.md)
\ No newline at end of file

@@ -5,7 +5,7 @@ ms.service: azure-ai-language
 ms.topic: tutorial
 author: laujan
 ms.author: lajanuar
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.custom: language-service-question-answering
 ---
 
@@ -17,11 +17,11 @@ In this tutorial, you learn how to:
 > * Add synonyms to improve the quality of your responses
 > * Evaluate the response quality via the inspect option of the Test pane
 
-This tutorial will show you how you can improve the quality of your responses by using synonyms. Let's assume that users are not getting an accurate response to their queries, when they use alternate forms, synonyms or acronyms of a word. So, they decide to improve the quality of the response by using [Authoring API](../how-to/authoring.md) to add synonyms for keywords.
+This tutorial shows you how you can improve the quality of your responses by using synonyms. Let's assume that users aren't getting an accurate response to their queries, when they use alternate forms, synonyms or acronyms of a word. So, they decide to improve the quality of the response by using [Authoring API](../how-to/authoring.md) to add synonyms for keywords.
 
 ## Add synonyms using Authoring API
 
-Let’s us add the following words and their alterations to improve the results:
+Let improve the results by adding the following words and their alterations:
 
 |Word | Alterations|
 |--------------|--------------------------------|
@@ -58,7 +58,7 @@ Let’s us add the following words and their alterations to improve the results:
 
 ```
 
-For the question and answer pair “Fix problems with Surface Pen”, we compare the response for a query made using its synonym “troubleshoot”.
+For the question and answer pair “Fix problems with Surface Pen,” we compare the response for a query made using its synonym “troubleshoot.”
 
 ## Response before addition of synonym
 
@@ -70,7 +70,7 @@ For the question and answer pair “Fix problems with Surface Pen”, we compare
 > [!div class="mx-imgBorder"]
 > [ ![Screenshot with a confidence score of .97 highlighted in red]( ../media/adding-synonyms/score-improvement.png) ]( ../media/adding-synonyms/score-improvement.png#lightbox)
 
-As you can see, when `troubleshoot` was not added as a synonym, we got a low confidence response to the query “How to troubleshoot your surface pen”. However, after we add `troubleshoot` as a synonym to “fix problems”, we received the correct response to the query with a higher confidence score. Once, these synonyms were added, the relevance of results improved thereby improving user experience.
+As you can see, when `troubleshoot` was not added as a synonym, we got a low confidence response to the query “How to troubleshoot your surface pen.” However, after we add `troubleshoot` as a synonym to “fix problems”, we received the correct response to the query with a higher confidence score. Once these synonyms were added, the relevance of results is improved.
 
 > [!IMPORTANT]
 > Synonyms are case insensitive. Synonyms also might not work as expected if you add stop words as synonyms. The list of stop words can be found here: [List of stop words](https://github.com/Azure-Samples/azure-search-sample-data/blob/master/STOPWORDS.md).
@@ -80,8 +80,8 @@ As you can see, when `troubleshoot` was not added as a synonym, we got a low con
 * Synonyms can be added in any order. The ordering is not considered in any computational logic.
 * Synonyms can only be added to a project that has at least one question and answer pair.
 * Synonyms can be added only when there is at least one question and answer pair present in a project.
-* In case of overlapping synonym words between 2 sets of alterations, it may have unexpected results and it is not recommended to use overlapping sets.
-* Special characters are not allowed for synonyms. For hyphenated words like "COVID-19", they are treated the same as "COVID 19", and "space" can be used as a term separator. Following is the list of special characters **not allowed**:
+* In case of overlapping synonym words between two sets of alterations, it can have unexpected results and it isn't recommended to use overlapping sets.
+* Special characters are not allowed for synonyms. For hyphenated words like "COVID-19," they are treated the same as "COVID 19," and "space" can be used as a term separator. Following is the list of special characters **not allowed**:
 
 |Special character | Symbol|
 |--------------|--------------------------------|

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/21/2024
+ms.date: 06/30/2025
 ms.author: lajanuar
 ms.custom: language-service-sentiment-opinion-mining
 keywords: on-premises, Docker, container, sentiment analysis, natural language processing
@@ -130,7 +130,7 @@ In this article, you learned concepts and workflow for downloading, installing,
 * You must specify billing information when instantiating a container.
 
 > [!IMPORTANT]
-> Azure AI containers are not licensed to run without being connected to Azure for metering. Customers need to enable the containers to communicate billing information with the metering service at all times. Azure AI containers do not send customer data (e.g. text that is being analyzed) to Microsoft.
+> Azure AI containers are not licensed to run without being connected to Azure for metering. Customers need to enable the containers to communicate billing information with the metering service at all times. Azure AI containers do not send customer data (for example, text that is being analyzed) to Microsoft.
 
 ## Next steps
 

@@ -6,28 +6,37 @@ items:
   items:
   - name: What is Azure AI Language?
     href: overview.md
+    displayName: overview, introduction
   - name: Pricing
     href: https://aka.ms/unifiedLanguagePricing
   - name: Language support
     href: concepts/language-support.md
+    displayName: multilingual
   - name: Region support
     href: ./concepts/regional-support.md
+    displayName: availability, azure regions, geographic availability
   - name: Quotas and limits
     href: concepts/data-limits.md
+    displayName: service limits, rate, usage
   - name: What's new
     href: whats-new.md
+    displayName: release notes, updates, new features, changelog
 - name: Azure AI Language capabilities
   items:
   - name: Custom text classification
     items:
     - name: Custom text classification overview
       href: custom-text-classification/overview.md
+      displayName: ctc
     - name: Custom text classification quickstart
       href: custom-text-classification/quickstart.md
+      displayName: ctc setup
     - name: Custom text classification language support
       href: custom-text-classification/language-support.md
+      displayName: ctc languages, multilingual
     - name: Custom text classification FAQ
       href: custom-text-classification/faq.md
+      displayName: ctc faq, troubleshooting
     - name: Responsible use of AI
       items:
       - name: Transparency note for custom text classification
@@ -46,95 +55,140 @@ items:
       items:
       - name: Create projects
         href: custom-text-classification/how-to/create-project.md
+        displayName: project creation, setup project
       - name: Data selection and schema design
         href: custom-text-classification/how-to/design-schema.md
-        displayName: Best practices
+        displayName: best practices
       - 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
       - name: Model performance (preview)
         href: custom-text-classification/how-to/view-model-evaluation.md
+        displayName: evaluation, performance metrics, accuracy, precision, recall
       - name: Deploy a model
         href: custom-text-classification/how-to/deploy-model.md
+        displayName: deployment, classifier, production deployment
       - name: Classify text
         href: custom-text-classification/how-to/call-api.md
+        displayName: classification, prediction
       - name: Back up and recover your models
         href: custom-text-classification/fail-over.md
+        displayName: backup, disaster recovery, failover
       - name: Deploy to multiple regions
         href: concepts/custom-features/multi-region-deployment.md
+        displayName: multi-region, global deployment, regional distribution
     - name: Concepts
       items:
       - name: Evaluation metrics
         href: custom-text-classification/concepts/evaluation-metrics.md
+        displayName: performance evaluation, accuracy, f1 score, confusion matrix
       - name: Accepted data formats
         href: custom-text-classification/concepts/data-formats.md
-        displayName: Data representation
+        displayName: data representation
       - name: Project versioning
         href: concepts/custom-features/project-versioning.md
+        displayName: version control, model versions
     - name: Tutorials
       items:
-      - name: Triage incoming emails with power automate
+      - name: Triage incoming emails with Power Automate
         href: custom-text-classification/tutorials/triage-email.md
+        displayName: power automate, email classification, automation
     - name: Reference
       items:
       - name: Glossary
         href: custom-text-classification/glossary.md
-        displayName: Model, Project, Class
+        displayName: model, project, class
       - name: Service limits
         href: custom-text-classification/service-limits.md
+        displayName: quotas, restrictions, service boundaries
   - name: Conversational language understanding
     items:
     - name: Conversational language understanding overview
       href: conversational-language-understanding/overview.md
+      displayName: clu, conversational ai, intent recognition, entity extraction
     - name: Conversational language understanding quickstart
       href: conversational-language-understanding/quickstart.md
+      displayName: getting started, tutorial, conversational ai setup
     - name: Conversational language understanding language support
       href: conversational-language-understanding/language-support.md
+      displayName: clu languages, supported languages, multilingual, international support
     - name: Conversational language understanding FAQ
       href: conversational-language-understanding/faq.md
+      displayName: frequently asked questions, troubleshooting, common issues
+    - name: Responsible use of AI
+      items:
+      - name: Transparency note for conversational language understanding
+        href: /legal/cognitive-services/language-service/clu-transparency-note?context=/azure/ai-services/language-service/context/context
+      - name: Integration and responsible use
+        href: /legal/cognitive-services/language-service/guidance-integration-responsible-use?context=/azure/ai-services/language-service/context/context
+      - name: Characteristics and limitations
+        href: /legal/cognitive-services/language-service/clu-characteristics-and-limitations?context=/azure/ai-services/language-service/context/context
+      - name: Data, privacy, and security
+        href: /legal/cognitive-services/language-service/data-privacy?context=/azure/ai-services/language-service/context/context
     - name: How-to guides
       items:
         - name: Use containers
           items:
           - name: Use Docker Containers
             href: conversational-language-understanding/how-to/use-containers.md
+            displayName: containerization, container deployment, clu containers
           - name: Configure containers
             href: concepts/configure-containers.md
+            displayName: container setup
           - name: Use container instances
             href: ../containers/azure-container-instance-recipe.md?context=/azure/ai-services/language-service/context/context
           - name: Azure AI containers overview
             href: ../cognitive-services-container-support.md
         - name: Create projects
           href: conversational-language-understanding/how-to/create-project.md
+          displayName: creation, clu project, setup
         - name: Build a schema
           href: conversational-language-understanding/how-to/build-schema.md
+          displayName: design, intents, entities, conversational model
         - name: Label utterances
           href: conversational-language-understanding/how-to/tag-utterances.md
+          displayName: labeling, tag utterances, training data, annotation
         - name: Train a model
           href: conversational-language-understanding/how-to/train-model.md
+          displayName: training, clu training, conversational model training
+        - name: Configure Azure resources
+          href: conversational-language-understanding/how-to/configure-azure-resources.md
+          displayName: configuration, fine-tuning, azure ai foundry, azure portal 
         - name: View your model's performance
           href: conversational-language-understanding/how-to/view-model-evaluation.md
+          displayName: evaluation, performance metrics, clu accuracy, testing
         - name: Deploy a model
           href: conversational-language-understanding/how-to/deploy-model.md
-        - name: Call the API to make predictions
+          displayName: deployment, clu, production
+        - name: Call the API and make predictions
           href: conversational-language-understanding/how-to/call-api.md
+          displayName: predictions, clu api, intent recognition, entity extraction
         - name: Back up and recover your models
           href: conversational-language-understanding/how-to/fail-over.md
+          displayName: disaster recovery, failover, clu
         - name: Migrate from LUIS
           href: conversational-language-understanding/how-to/migrate-from-luis.md
+          displayName: language understanding, luis to clu
     - name: Concepts
       items:
         - name: Best practices
           href: conversational-language-understanding/concepts/best-practices.md
+          displayName: recommendations, guidelines, optimization
         - name: Multilingual projects
           href: conversational-language-understanding/concepts/multiple-languages.md
+          displayName: multiple languages, international, localization
         - name: Entity components
           href: conversational-language-understanding/concepts/entity-components.md
+          displayName: entities, extraction, ner components
         - name: Evaluation metrics
           href: conversational-language-understanding/concepts/evaluation-metrics.md
         - name: Data formats
@@ -145,22 +199,26 @@ items:
           href: concepts/custom-features/multi-region-deployment.md
         - name: Choosing between conversational apps
           href: conversational-language-understanding/concepts/app-architecture.md
+          displayName: architecture, clu, qna, comparison
     - name: Tutorials
       items:
         - name: Use Bot Framework
           href: conversational-language-understanding/tutorials/bot-framework.md
+          displayName: integration, chatbot, conversational, bot, clu
     - name: Reference
       items:
       - name: Prebuilt component reference
         href: conversational-language-understanding/prebuilt-component-reference.md
       - name: Service limits
         href: conversational-language-understanding/service-limits.md
+        displayName: limits, quotas, restrictions, boundaries, clu
       - name: Glossary
         href: conversational-language-understanding/glossary.md
   - name: Entity linking
     items:
     - name: Entity linking overview
       href: entity-linking/overview.md
+      displayName: knowledge base linking, disambiguation
     - name: Entity linking quickstart
       href: entity-linking/quickstart.md
     - name: Entity linking language support
@@ -177,10 +235,12 @@ items:
       items:
         - name: How to call the API
           href: entity-linking/how-to/call-api.md
+          displayName: entity linking, entity recognition
   - name: Language detection
     items:
     - name: Language detection overview
       href: language-detection/overview.md
+      displayName: language identification, automatic detection
     - name: Language detection quickstart
       href: language-detection/quickstart.md
     - name: Language detection language support
@@ -216,6 +276,7 @@ items:
     items:
     - name: Key phrase extraction overview
       href: key-phrase-extraction/overview.md
+      displayName: keyword extraction, key terms
     - name: Key phrase extraction quickstart
       href: key-phrase-extraction/quickstart.md
     - name: Key phrase extraction language support
@@ -251,10 +312,12 @@ items:
       items:
       - name: Integrate Power BI
         href: key-phrase-extraction/tutorials/integrate-power-bi.md
+        displayName: business intelligence, data visualization
   - name: Named Entity Recognition (NER)
     items:
     - name: NER overview
       href: named-entity-recognition/overview.md
+      displayName: ner introduction, entity extraction
     - name: NER quickstart
       href: named-entity-recognition/quickstart.md
     - name: NER language support
@@ -302,6 +365,7 @@ items:
         items:
         - name: Extract information in Excel using Power Automate
           href: named-entity-recognition/tutorials/extract-excel-information.md
+          displayName: excel integration, power automate, ner automation, extract entities
     - name: Custom
       items:
       - name: Custom NER overview
@@ -402,6 +466,7 @@ items:
       items:
         - name: Connect conversational language understanding and custom question answering
           href: orchestration-workflow/tutorials/connect-services.md
+          displayName: clu integration, qna integration, orchestration workflow, connect services
     - name: Reference
       items:
       - name: Service limits
@@ -412,7 +477,7 @@ items:
     items:
     - name: PII overview
       href: personally-identifiable-information/overview.md
-      displayName: native, native document
+      displayName: native document
     - name: PII quickstart
       href: personally-identifiable-information/quickstart.md
     - name: PII language support
@@ -460,6 +525,7 @@ items:
     items:
     - name: Custom question answering overview
       href: question-answering/overview.md
+      displayName: qna, faq, knowledge base
     - name: Custom question answering quickstart
       href: question-answering/quickstart/sdk.md
     - name: Custom question answering language support
@@ -479,13 +545,16 @@ items:
       items:
       - name: Migrate from QnA Maker to custom question Answering
         href: question-answering/how-to/migrate-qnamaker-to-question-answering.md
+        displayName: migration, custom question answering
       - name: Migrate projects from QnA Maker
         href: question-answering/how-to/migrate-qnamaker.md
+        displayName: migration, transfer
       - name: Getting started with custom question answering
         href: question-answering/how-to/create-test-deploy.md
+        displayName: knowledge base, test deploy
       - name: Export/import/refresh
         href: question-answering/how-to/export-import-refresh.md
-      - name: Smart URL refresh
+      - name: Use smart URL refresh
         href: question-answering/how-to/smart-url-refresh.md
       - name: Encrypt data at rest
         href: question-answering/how-to/encrypt-data-at-rest.md
@@ -495,8 +564,9 @@ items:
         href: question-answering/how-to/chit-chat.md
       - name: Change default answer
         href: question-answering/how-to/change-default-answer.md
-      - name: Configure resources
-        href: question-answering/how-to/configure-resources.md
+      - name: Configure Azure resources
+        href: question-answering/how-to/configure-azure-resources.md
+        displayName: configuration, fine-tuning, azure ai foundry, azure portal 
       - name: Analytics
         href: question-answering/how-to/analytics.md
       - name: Manage projects
@@ -533,8 +603,9 @@ items:
         href: conversational-language-understanding/concepts/app-architecture.md
     - name: Tutorials
       items:
-      - name: Create a FAQ Bot
+      - 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
@@ -545,8 +616,9 @@ items:
         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 Power Virtual Agents
+      - 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
@@ -598,6 +670,7 @@ items:
     items:
     - name: Text Analytics for health overview
       href: text-analytics-for-health/overview.md
+      displayName: healthcare nlp, medical text analysis, clinical text, health entities
     - name: Text Analytics for health quickstart
       href: text-analytics-for-health/quickstart.md
     - name: Text Analytics for health language support
@@ -641,7 +714,7 @@ items:
     items:
     - name: Summarization overview
       href: summarization/overview.md
-      displayName: native, native document
+      displayName: native document
     - name: Summarization quickstart
       href: summarization/quickstart.md
     - name: Summarization language support
@@ -679,15 +752,16 @@ items:
       - name: Data, privacy, and security
         href: ../../ai-foundry/responsible-ai/language-service/data-privacy.md
         displayName: Data privacy, logging, data retention
-
 - name: Concepts
   items:
   - name: Developer guide
     href: concepts/developer-guide.md
+    displayName: development, sdk guide, programming
   - name: Role-based-access-control
     href: concepts/role-based-access-control.md
   - name: Multilingual and emoji support
     href: concepts/multilingual-emoji-support.md
+    displayName: international, characters
   - name: Model lifecycle
     href: concepts/model-lifecycle.md
   - name: Send requests asynchronously
@@ -703,15 +777,14 @@ items:
   - name: Data, privacy, and security
     href: ../../ai-foundry/responsible-ai/language-service/data-privacy.md
     displayName: Data privacy, logging, data retention
-
 - name: How-tos
   items:
   - name: Migrate from LUIS, QnA Maker, and Text Analytics
     displayName: text analytics, luis, qna
     href: concepts/migrate.md
   - name: Use Azure Kubernetes Service
     href: tutorials/use-kubernetes-service.md
-  - name: Use language in power automate flows
+  - name: Use language in Power Automate flows
     href: tutorials/power-automate.md
   - name: Native document support
     items:
@@ -726,7 +799,7 @@ items:
       - name: Call Center
         items:
         - name: Overview
-          displayName: IVRs, IVR, Telephony Data, Transcription for Telephony Data, Real-time Transcription for Call Centers, Post-Call Analytics
+          displayName: ivrs, ivr, telephony data, transcription for telephony data, real-time transcription for call centers, post-call analytics
           href: ../speech-service/call-center-overview.md?context=%2fazure%2fai-services%2flanguage-service%2fcontext%2fcontext
         - name: Post-call transcription and analytics quickstart
           href: ../speech-service/call-center-quickstart.md?context=%2fazure%2fai-services%2flanguage-service%2fcontext%2fcontext