@@ -43,19 +43,18 @@ A Conversational Language Understanding (CLU) fine-tuning task is a workspace pr
 
    :::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.
+1. From the main window, select **the AI Service fine-tuning** tab and then the **+ Fine-tune** button.
 
-   :::image type="content" source="../media/fine-tune-button.png" alt-text="Screenshot of fine-tuning button in the Azure AI Foundry.":::
+   :::image type="content" source="../media/fine-tune-button.png" alt-text="Screenshot of fine-tune button in the Azure AI Foundry.":::
 
-1. From **Create service fine-tuning** window, choose the **Conversational language understanding** tab then select **Next**.
+1. From the **Create service fine-tuning** window, choose the **Conversational language understanding** tab and then select **Next**.
 
    :::image type="content" source="../media/select-project.png" alt-text="Screenshot of conversational language understanding tab in the Azure AI Foundry.":::
 
-1. In **Create CLU fine-tuning task** window, complete the **Name** and **Language** fields. If you're planning to fine-tune a model using the free **Standard Training** mode, select **English** for the language field.
+1. In the **Create CLU fine-tuning task** window, complete the **Name** and **Language** fields. If you're planning to fine-tune a model using the free **Standard Training** mode, select **English** for the language field.
 
 1. Select the  **Create** button. It can take a few minutes for the *creating* operation to complete.
 
-
    > [!NOTE]
    >
    > * **Standard training** enables faster training times and quicker iterations; however it's only available for English.
@@ -178,4 +177,4 @@ If your project is no longer required, you can delete it using the REST API. To
 After you create your fine-tuning workspace, start your fine-tuning task by defining your intents and entities and adding them to your schema:
 
 * [Build your fine-tuning schema](build-schema.md)
-* [Label utterances](tag-utterances.md)
+* [Label utterances](tag-utterances.md)
\ No newline at end of file

@@ -22,7 +22,7 @@ Use this article to get started with Conversational Language understanding using
 * **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)](/azure/ai-foundry/openai/how-to/role-based-access-control#cognitive-services-contributor).
 *  [Azure AI Foundry multi-service resource](/azure/ai-services/multi-service-resource). For more information, *see* [Configure an Azure AI Foundry resource](../../how-to/configure-azure-resources.md#option-1-configure-an-azure-ai-foundry-resource). Alternately, you can use an [Azure AI Language resource](https://portal.azure.com/?Microsoft_Azure_PIMCommon=true#create/Microsoft.CognitiveServicesTextAnalytics).
-* Foundry project created in the Azure AI Foundry. For more information, *see* [Create an AI Foundry project](/azure/ai-foundry/how-to/create-projects).
+* A Foundry project created in the Azure AI Foundry. For more information, *see* [Create an AI Foundry project](/azure/ai-foundry/how-to/create-projects).
 
 ## Get started with Azure AI Foundry
 

@@ -2,17 +2,16 @@
 title: Project best practices
 description: Best practices for custom question answering
 ms.service: azure-ai-language
-ms.subservice: azure-ai-qna-maker
 ms.topic: how-to
 author: laujan
 ms.author: lajanuar
 recommendations: false
-ms.date: 06/21/2025
+ms.date: 08/29/2025
 ---
 
 # Project best practices
 
-The following list of QnA pairs will be used to represent a project to highlight best practices when authoring in custom question answering. 
+The following list of QnA pairs are used to represent a project to highlight best practices when authoring in custom question answering. 
 
 |Question                             |Answer                                                 | 
 |-------------------------------------|-------------------------------------------------------|
@@ -30,9 +29,9 @@ The following list of QnA pairs will be used to represent a project to highlight
 
 - Custom question answering employs a transformer-based ranker that takes care of user queries that are semantically similar to questions in the project. For example, consider the following question answer pair:
 
-   **Question: “What is the price of Microsoft Stock?”**
+   **Question: "What is the price of Microsoft Stock?"**
 
-   **Answer: “$200”.**
+   **Answer: "$200".**
 
    The service can return expected responses for semantically similar queries such as:
 
@@ -46,51 +45,51 @@ The following list of QnA pairs will be used to represent a project to highlight
 
    "What is the market value of a Microsoft share?"
 
-   However, please note that the confidence score with which the system returns the correct response will vary based on the input query and how different it is from the original question answer pair.
+   The system's confidence score depends on the input query and how closely it matches the original question-answer pair. Greater differences between them can lead to changes in the confidence level.
 
-- There are certain scenarios which require the customer to add an alternate question. When a query does not return the correct answer despite it being present in the project, we advise adding that query as an alternate question to the intended QnA pair.
+- There are certain scenarios that require the customer to add an alternate question. When a query doesn't return the correct answer despite it being present in the project, we advise adding that query as an alternate question to the intended QnA pair.
 
 ## How many alternate questions per QnA is optimal?
 
-- Users can add up to 10 alternate questions depending on their scenario. Alternate questions beyond the first 10 aren’t considered by our core ranker. However, they are evaluated in the other processing layers resulting in better output overall. All the alternate questions will be considered in the preprocessing step to look for an exact match.
+- Users can add up to 10 alternate questions depending on their scenario. Alternate questions beyond the first 10 aren't considered via our core ranker. However, they're evaluated in the other processing layers resulting in better output overall. All the alternate questions are considered in the preprocessing step to look for an exact match.
 
 - Semantic understanding in custom question answering should be able to take care of similar alternate questions.
 
-- The return on investment will start diminishing once you exceed 10 questions. Even if you’re adding more than 10 alternate questions, try to make the initial 10 questions as semantically dissimilar as possible so that all intents for the answer are captured by these 10 questions. For the project above, in QNA #1, adding alternate questions such as "How can I buy a car?", "I wanna buy a car." are not required. Whereas adding alternate questions such as "How to purchase a car.", "What are the options for buying a vehicle?" can be useful.
+- The return on investment starts diminishing once you exceed 10 questions. Even if you're adding more than 10 alternate questions, try to make the initial 10 questions as semantically dissimilar as possible so that all intents for the answer are captured via these 10 questions. For the project in QNA #1, adding alternate questions such as "How can I buy a car?", "I wanna buy a car." aren't required. Whereas adding alternate questions such as "How to purchase a car.", "What are the options for buying a vehicle?" can be useful.
 
 ## When to add synonyms to a project
 
 - Custom question answering provides the flexibility to use synonyms at the project level, unlike QnA Maker where synonyms are shared across projects for the entire service.
 
-- For better relevance, the customer needs to provide a list of acronyms that the end user intends to use interchangeably. For instance, the following is a list of acceptable acronyms:
+- For better relevance, the customer needs to provide a list of acronyms that the end user intends to use interchangeably. For instance, the following list provides acceptable acronyms:
 
-   MSFT – Microsoft
+   * MSFT – Microsoft
 
-   ID – Identification
+   * ID – Identification
 
-   ETA – Estimated time of Arrival
+   * ETA – Estimated time of Arrival
 
-- Apart from acronyms, if you think your words are similar in context of a particular domain and generic language models won’t consider them similar, it’s better to add them as synonyms. For instance, if an auto company producing a car model X receives queries such as "my car’s audio isn’t working" and the project has questions on "fixing audio for car X", then we need to add "X" and "car" as synonyms.
+- Apart from acronyms, if you think your words are similar in context of a particular domain and generic language models don't consider them similar, it's better to add them as synonyms. For instance, if an auto company producing a car model X receives queries such as "my car's audio isn't working" and the project has questions on "fixing audio for car X," then we need to add "X" and "car" as synonyms.
 
-- The Transformer based model already takes care of most of the common synonym cases, for e.g.- Purchase – Buy, Sell - Auction, Price – Value. For example, consider the following QnA pair: Q: "What is the price of Microsoft Stock?" A: "$200".
+- The Transformer based model already takes care of most of the common synonym cases, for example- Purchase – Buy, Sell - Auction, Price – Value. For example, consider the following QnA pair: Q: "What is the price of Microsoft Stock?" A: "$200".
 
-If we receive user queries like "Microsoft stock value", "Microsoft share value", "Microsoft stock worth", "Microsoft share worth", "stock value", etc., they should be able to get correct answer even though these queries have words like share, value, worth which are not originally present in the knowledge base.
+Users should receive accurate answers to queries like "Microsoft stock value," "Microsoft share value," or "stock worth," even if terms such as "share," "value," or "worth" aren't present in the knowledge base.
 
 ## How are lowercase/uppercase characters treated?
 
-Custom question answering takes casing into account but it's intelligent enough to understand when it is to be ignored. You should not be seeing any perceivable difference due to wrong casing.
+Custom question answering takes casing into account but it's intelligent enough to understand when it's to be ignored. You shouldn't be seeing any perceivable difference due to wrong casing.
 
 ## How are QnAs prioritized for multi-turn questions?
 
-When a KB has hierarchical relationships (either added manually or via extraction) and the previous response was an answer related to other QnAs, for the next query we give slight preference to all the children QnAs, sibling QnAs and grandchildren QnAs in that order. Along with any query, the [custom question Answering API] (/rest/api/cognitiveservices/questionanswering/question-answering/get-answers) expects a "context" object with the property "previousQnAId" which denotes the last top answer. Based on this previous QnA ID, all the related QnAs are boosted.
+When a knowledge base has hierarchical relationships, and the previous answer related to other QnAs, the system slightly favors, in order: child QnAs, sibling QnAs, then grandchild QnAs for the next query. Along with any query, the [custom question Answering API] (/rest/api/cognitiveservices/questionanswering/question-answering/get-answers) expects a "context" object with the property "previousQnAId" that denotes the last top answer. Based on this previous QnA ID, all the related QnAs are boosted.
 
 ## How are accents treated?
 
-Accents are supported for all major European languages. If the query has an incorrect accent, confidence score might be slightly different, but the service still returns the relevant answer and takes care of minor errors by leveraging fuzzy search.
+Accents are supported for all major European languages. If the query has an incorrect accent, confidence score might be slightly different, but the service still returns the relevant answer and takes care of minor errors by using fuzzy search.
 
 ## How is punctuation in a user query treated?
 
-Punctuation is ignored in user query before sending it to the ranking stack. Ideally it should not impact the relevance scores. Punctuation that are ignored are as follows:  ,?:;\"'(){}[]-+。./!*؟
+Punctuation is ignored in user query before sending it to the ranking stack. Ideally it shouldn't impact the relevance scores. Punctuation that is ignored:  ,?:;\"'(){}[]-+。./!*؟
 
 ## Next steps
 

@@ -2,7 +2,6 @@
 title: Export/import/refresh | custom question answering projects and projects
 description: Learn about backing up your custom question answering projects and projects
 ms.service: azure-ai-language
-ms.subservice: azure-ai-qna-maker
 ms.topic: how-to
 author: laujan
 ms.author: lajanuar

@@ -0,0 +1,116 @@
+---
+title: Create, test, and deploy your custom question answering project in Azure AI Foundry
+description: Create a custom question answering project from your own content, such as FAQs or product manuals. This article includes an example of creating a custom question answering project from a simple FAQ webpage, to answer questions.
+ms.service: azure-ai-language
+ms.topic: include
+ms.date: 08/30/2025
+---
+
+This quickstart guides you through the essential steps needed to create, test, and deploy a custom question answering (CQA) project in the Azure AI Foundry. Whether you're transitioning from Language Studio or starting from scratch, this quickstart is for you. It provides clear and actionable instructions to achieve a fast and successful CQA project deployment.
+
+> [!NOTE]
+>
+> * If you already have an Azure AI Language or multi-service resource—whether used on its own or through Language Studio—you can continue to use those existing Language resources within the Azure AI Foundry portal. For more information, see [How to use Azure AI services in the Azure AI Foundry portal](../../../../ai-services/connect-services-ai-foundry-portal.md).
+> * 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.
+>
+
+## Prerequisites
+
+Before you get started, you need the following resources and permissions:
+
+* **An active Azure subscription**. If you don't have one, [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). For more information on how to connect your Azure AI Search resource, *see* [Configure connections in AI Foundry](../../conversational-language-understanding/how-to/configure-azure-resources.md#step-2-configure-connections-in-ai-foundry)
+* A Foundry project created in the Azure AI Foundry. For more information, *see* [Create an AI Foundry project](/azure/ai-foundry/how-to/create-projects).
+
+## Get started
+
+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.
+
+## Create your CQA fine tuning task
+
+In the Azure AI Foundry, a fine-tuning task serves as your workspace for your CQA solutions. Previously, a **fine-tuning task** was referred to as a **CQA project**. You might encounter both terms used interchangeably in older CQA documentation.
+
+1. After you select the Azure AI Foundry project to use for this quickstart, select **fine-tuning** from the left navigation menu.
+
+     :::image type="content" source="../media/agents/fine-tuning-selection.png" alt-text="Screenshot of the fine-tuning menu selection in the Azure AI Foundry.":::
+
+1. From the main window, select the **AI Service fine-tuning** tab and then the **+ Fine-tune button**.
+
+     :::image type="content" source="../media/agents/fine-tune-button.png" alt-text="Screenshot of fine-tune button in the Azure AI Foundry.":::
+
+1. From the **Create service fine-tuning** window, choose the **Custom question answering** tab and then select **Next**.
+
+     :::image type="content" source="../media/agents/custom-question-answering-tab.png" alt-text="Screenshot of custom question answering tab in the Azure AI Foundry.":::
+
+1. Select your **Connected Azure AI Search resource** from the **Create CQA fine tuning task** window. For more information, *see* [Configure Azure resource connections](../../conversational-language-understanding/how-to/configure-azure-resources.md#step-2-configure-connections-in-ai-foundry).
+
+1. Next, complete the **Name** and **Language** fields. For this project, you can leave the **Default answer when no answer is returned** field as is (**No answer found**).
+
+1. Select the **Create** button.
+
+## Add a CQA knowledge base source
+
+A CQA knowledge base is a structured set of question-and-answer pairs optimized for conversational AI. The knowledge base uses natural language processing to interpret user queries and return context-aware, accurate answers from a specific dataset.
+
+1. From the **Getting Started** menu, select **Manage sources**.
+
+     :::image type="content" source="../media/agents/manage-sources.png" alt-text="Screenshot of manage sources selection in the Azure AI Foundry.":::
+
+1. From the main window, select the **+ Add source** drop-down menu.
+
+1. From the drop-down menu you can select **Add chit chat**, **Add URLs**, or **Add Files**.
+
+     :::image type="content" source="../media/agents/add-source-menu.png" alt-text="Screenshot of add source drop-down menu in the Azure AI Foundry.":::
+
+1. For this project, let's choose **Add chitchat**.
+
+1. From the **Add new source** window, let's choose **Friendly**.
+
+     :::image type="content" source="../media/agents/select-source-type.png" alt-text="Screenshot of the select source selection and add button in the Azure AI Foundry.":::
+
+1. Finally, select **Add**. It may take a few minutes for the source to be created.
+
+1. Once created, the source is listed in the **Manage sources** window.
+
+     :::image type="content" source="../media/agents/manage-sources-list.png" alt-text="Screenshot of manage sources list in the Azure AI Foundry.":::
+
+## Test your knowledge base
+
+1. Select **Test knowledge base** from the **Getting Started** menu.
+
+1. Type the following in the **Type your question** field and then select **Run**.
+
+     ```text
+       Hello! How are you doing today?
+
+     ```
+
+1. In the inspection interface, you can review the response confidence level and choose the most suitable answer.
+
+    :::image type="content" source="../media/agents/inspection-interface.png" alt-text="Screenshot of the inspection interface in the Azure AI Foundry.":::
+
+
+## Deploy your knowledge base
+
+Deploying a CQA knowledge base means publishing your curated question-and-answer content as a live, searchable endpoint. This process moves your project from a testing phase to a production environment enabling client applications to use it for various projects and solutions, including chatbots.
+
+1. Once your inspection is complete, choose the **Deploy knowledge base** section from the **Getting Started** menu.
+
+1. Select the **Deploy** button first from the **Deploy knowledge base** main window and then from the **Deploy this project** pop-up window. It takes a few minutes to deploy.
+
+1. After deployment is complete, your deployed project is listed in the **Deploy knowledge base** window.
+
+That's it! Your Custom Question Answering (CQA) knowledge base provides a natural language interface to your data, allowing users to interact with information in a conversational manner. By deploying this solution, you can create advanced chatbots and interactive agents that comprehend user questions, supply precise answers, and adjust to changing informational requirements.
+
+
+
+
+

@@ -1,95 +0,0 @@
----
-title: Create, test, and deploy your custom question answering project
-description: You can create a custom question answering project from your own content, such as FAQs or product manuals. This article includes an example of creating a custom question answering project from a simple FAQ webpage, to answer questions.
-ms.service: azure-ai-language
-ms.subservice: azure-ai-qna-maker
-ms.topic: include
-ms.date: 06/30/2025
----
-
-You can create a custom question answering project from your own content, such as FAQs or product manuals. This article includes an example of creating a custom question answering project from a product manual, to answer questions.
-
-## Prerequisites
-
-> [!div class="checklist"]
-> * If you don't have an Azure subscription, create a [free account](https://azure.microsoft.com/free/cognitive-services/) before you begin.
-> * A [language resource](https://aka.ms/create-language-resource) with the custom question answering feature enabled. Remember your Microsoft Entra ID, Subscription, language resource name you selected when you created the resource.
-
-
-
-## Create your first custom question answering project
-
-1. Sign in to the [Language Studio](https://language.azure.com/) with your Azure credentials.
-
-2. Scroll down to the **Answer questions** section and select **Open custom question answering**.
-
-    > [!div class="mx-imgBorder"]
-    > ![Open custom question answering](../media/create-test-deploy/open-custom-question-answering.png)
-
-3. If your resource is not yet connected to Azure Search select **Connect to Azure Search**. This will open a new browser tab to **Features** pane of your resource in the Azure portal.
-
-    > [!div class="mx-imgBorder"]
-    > ![Connect to Azure Search](../media/create-test-deploy/connect-to-azure-search.png)
-
-4. Select **Enable custom question answering**, choose the Azure Search resource to link to, and then select **Apply**.
-
-    > [!div class="mx-imgBorder"]
-    > ![Enable custom question answering](../media/create-test-deploy/enable-custom-question-answering.png)
-
-5. Return to the Language Studio tab. You might need to refresh this page for it to register the change to your resource. Select **Create new project**.
-
-6. Choose the option **I want to set the language for all projects created in this resource** > select **English** > Select **Next**.
-
-7. Enter a project name of **Sample-project**, a description of **My first question answering project**, and leave the default answer with a setting of **No answer found**.
-
-8. Review your choices and select **Create project**
-
-9. From the **Manage sources** page select **Add source** > **URLS**.
-
-10. Select **Add url** enter the following values and then select **Add all**:
-
-    |URL Name|URL Value|
-    |--------|---------|
-    |Surface Book User Guide |https://download.microsoft.com/download/7/B/1/7B10C82E-F520-4080-8516-5CF0D803EEE0/surface-book-user-guide-EN.pdf |
-
-    The extraction process takes a few moments to read the document and identify questions and answers.
-
-    After successfully adding the source, you can then edit the source contents to add more custom question answer sets.
-
-
-
-## Test your project
-
-1. Select the link to your source, this will open the edit project page.
-
-2. Select **Test** from the menu bar > Enter the question **How do I setup my surface book?**. An answer will be generated based on the question answer pairs that were automatically identified and extracted from your source URL:
-
-    > [!div class="mx-imgBorder"]
-    > ![Test question chat interface](../media/create-test-deploy/test-question.png)
-
-    If you check the box for **include short answer response** you will also see a precise answer, if available, along with the answer passage in the test pane when you ask a question.
-
-3. Select **Inspect** to examine the response in more detail. The test window is used to test your changes to your project before deploying your project.
-
-    > [!div class="mx-imgBorder"]
-    > ![See the confidence interval](../media/create-test-deploy/inspect-test.png)
-
-    From the **Inspect** interface, you can see the level of confidence that this response will answer the question and directly edit a given question and answer response pair.
-
-
-
-## Deploy your project
-
-1. Select the Deploy project icon to enter the deploy project menu.
-
-    > [!div class="mx-imgBorder"]
-    > ![Deploy project](../media/create-test-deploy/deploy-knowledge-base.png)
-
-    When you deploy a project, the contents of your project move from the `test` index to a `prod` index in Azure Search.
-
-2. Select **Deploy** > and then when prompted select **Deploy** again.
-
-    > [!div class="mx-imgBorder"]
-    > ![Successful deployment](../media/create-test-deploy/successful-deployment.png)
-
-    Your project is now successfully deployed. You can use the endpoint to answer questions in your own custom application to answer or in a bot.

@@ -1,27 +1,23 @@
 ---
-title: "Quickstart: Use SDK to create and manage project - custom question answering"
-description: This quickstart shows you how to create and manage your project using custom question answering.
+title: "Quickstart: custom question answering"
+description: This quickstart shows you how to create and manage your  custom question answering projects.
 ms.service: azure-ai-language
 ms.topic: quickstart
-ms.date: 03/24/2025
+ms.date: 08/29/2025
 author: laujan
 ms.author: lajanuar
 recommendations: false
 ms.devlang: csharp
 # ms.devlang: csharp, python
 ms.custom: devx-track-python, devx-track-csharp, language-service-question-answering, mode-api, devx-track-dotnet
-zone_pivot_groups: custom-qna-quickstart
+zone_pivot_groups: custom-cqa-quickstart
 ---
 
-# Quickstart: custom question answering
+# Quickstart: custom question answering (CQA)
 
-> [!NOTE]
-> Are you looking to migrate your workloads from QnA Maker? See our [migration guide](../how-to/migrate-qnamaker-to-question-answering.md) for information on feature comparisons and migration steps.
 
-Get started with the custom question answering client library. Follow these steps to install the package and try out the example code for basic tasks.
-
-::: zone pivot="studio"
-[!INCLUDE [Studio quickstart](../includes/studio.md)]
+::: zone pivot="foundry"
+[!INCLUDE [Azure AI Foundry quickstart](../includes/azure-ai-foundry.md)]
 ::: zone-end
 
 ::: zone pivot="rest"
@@ -44,11 +40,8 @@ If you want to clean up and remove an Azure AI services subscription, you can de
 * [Azure CLI](../../../multi-service-resource.md?pivots=azcli#clean-up-resources)
 
 
-
 ## Explore the REST API
 
-To learn about automating your custom question answering pipeline consult the REST API documentation. Currently authoring functionality is only available via REST API:
-
 * [Authoring API reference](/rest/api/questionanswering/question-answering-projects)
 * [Authoring API cURL examples](../how-to/authoring.md)
 * [Runtime API reference](/rest/api/questionanswering/question-answering)