Merge pull request #4755 from MicrosoftDocs/release-build-2025-azure-ai-language

Release build 2025 azure ai language

Author: thomps23

articles/ai-services/language-service/conversational-language-understanding/how-to/create-project.md

@@ -6,19 +6,18 @@ author: jboback
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/21/2024
+ms.date: 05/01/2025
 ms.author: jboback
 ms.custom: language-service-clu
 ---
 
-# How to create a CLU project
+# How to create a CLU fine-tuning task
 
 Use this article to learn how to set up these requirements and create a project. 
 
-
 ## Prerequisites
 
-Before you start using CLU, you will need several things:
+Before you start using CLU, you will need a few items:
 
 * An Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services).
 * An Azure AI Language resource 
@@ -43,7 +42,7 @@ Before you start using CLU, you will need an Azure AI Language resource.
 
 Once you have a Language resource created, create a Conversational Language Understanding project. 
 
-### [Language Studio](#tab/language-studio)
+### [Azure AI Foundry](#tab/azure-ai-foundry)
 
 [!INCLUDE [Create project](../includes/language-studio/create-project.md)]
 
@@ -55,7 +54,7 @@ Once you have a Language resource created, create a Conversational Language Unde
 
 ## Import project
 
-### [Language Studio](#tab/language-studio)
+### [Azure AI Foundry](#tab/azure-ai-foundry)
 
 You can export a Conversational Language Understanding project as a JSON file at any time by going to the conversation projects page, selecting a project, and from the top menu, clicking on **Export**.
 
@@ -79,11 +78,11 @@ You can import a CLU JSON into the service
 
 ## Export project
 
-### [Language Studio](#tab/Language-Studio)
+### [Azure AI Foundry](#tab/azure-ai-foundry)
 
 You can export a Conversational Language Understanding project as a JSON file at any time by going to the conversation projects page, selecting a project, and pressing **Export**.
 
-### [REST APIs](#tab/rest-apis)
+### [REST APIs](#tab/rest-api)
 
 You can export a Conversational Language Understanding project as a JSON file at any time.
 
@@ -93,7 +92,7 @@ You can export a Conversational Language Understanding project as a JSON file at
 
 ## Get CLU project details
 
-### [Language Studio](#tab/language-studio)
+### [Azure AI Foundry](#tab/azure-ai-foundry)
 
 [!INCLUDE [Language Studio project details](../includes/language-studio/project-details.md)]
 
@@ -105,7 +104,7 @@ You can export a Conversational Language Understanding project as a JSON file at
 
 ## Delete project 
 
-### [Language Studio](#tab/language-studio)
+### [Azure AI Foundry](#tab/azure-ai-foundry)
 
 [!INCLUDE [Delete project](../includes/language-studio/delete-project.md)]
 

articles/ai-services/language-service/conversational-language-understanding/how-to/view-model-evaluation.md

@@ -29,7 +29,7 @@ See the [project development lifecycle](../overview.md#project-development-lifec
 
 ## Model details
 
-### [Language studio](#tab/Language-studio)
+### [Azure AI Foundry](#tab/azure-ai-foundry)
 
 [!INCLUDE [Model performance](../includes/language-studio/model-performance.md)]
 
@@ -41,7 +41,7 @@ See the [project development lifecycle](../overview.md#project-development-lifec
 
 ## Load or export model data
 
-### [Language studio](#tab/Language-studio)
+### [Azure AI Foundry](#tab/azure-ai-foundry)
 
 [!INCLUDE [Load export model](../includes/language-studio/load-export-model.md)]
 
@@ -54,7 +54,7 @@ See the [project development lifecycle](../overview.md#project-development-lifec
 
 ## Delete model
 
-### [Language studio](#tab/Language-studio)
+### [Azure AI Foundry](#tab/azure-ai-foundry)
 
 [!INCLUDE [Delete model](../includes/language-studio/delete-model.md)]
 

articles/ai-services/language-service/conversational-language-understanding/includes/language-studio/create-project.md

@@ -25,5 +25,4 @@ To create a new project you need to provide the following details:
 |Utterances primary language     | The primary language of your project. Your training data should primarily be in this language.        |
 |Enable multiple languages    |  Whether you would like to enable your project to support [multiple languages](../../language-support.md#multi-lingual-option) at once.       |
 
-Once you're done, select **Next** and review the details. Select **create** to complete the process. You should now see the **Build Schema** screen in your project.
-
+Once you're done, select **Create**. You should now see the Getting started landing page in your project.

articles/ai-services/language-service/conversational-language-understanding/includes/quickstarts/rest-api.md

@@ -24,7 +24,11 @@ ms.author: jboback
 
     :::image type="content" source="../../../media/azure-portal-resource-credentials.png" alt-text="A screenshot showing the key and endpoint page in the Azure portal" lightbox="../../../media/azure-portal-resource-credentials.png":::
 
+## Import a new CLU fine-tuning project
 
+Once you have a Language resource or an Azure AI resource created, create a fine-tuning task and select Azure AI language and select Conversational language understanding as the task type. A task is a work area for building your custom models based on your data. Your task can only be accessed by you and others who have access to the resource being used. 
+
+For this quickstart, you can download [this sample](https://github.com/Azure-Samples/cognitive-services-sample-data-files/blob/master/language-service/CLU/EmailAppDemo.json) and import it. This task can predict the intended commands from user input, such as: reading emails, deleting emails, and attaching a document to an email. 
 
 ## Import a new CLU sample project
 

articles/ai-services/language-service/conversational-language-understanding/language-support.md

@@ -6,7 +6,7 @@ author: jboback
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 05/01/2025
 ms.author: jboback
 ms.custom: language-service-clu
 ---
@@ -18,7 +18,7 @@ Use this article to learn about the languages currently supported by CLU feature
 ## Multi-lingual option
 
 > [!TIP]
-> See [How to train a model](how-to/train-model.md#training-modes) for information on which training mode you should use for multilingual projects. 
+> We recommend using English for the LLM-powered features, like Quick Deploy and Conversation-level understanding, but your project will continue to function for all languages.
 
 With conversational language understanding, you can train a model in one language and use to predict intents and entities from utterances in another language. This feature is powerful because it helps save time and effort. Instead of building separate projects for every language, you can handle multi-lingual dataset in one project. Your dataset doesn't have to be entirely in the same language but you should enable the multi-lingual option for your project while creating or later in project settings. If you notice your model performing poorly in certain languages during the evaluation process, consider adding more data in these languages to your training set.
 
@@ -147,8 +147,6 @@ Conversational language understanding supports utterances in the following langu
 | Chinese (Traditional) | `zh-hant` |
 | Zulu | `zu` |
 
-
-
 ## Next steps
 
 * [Conversational language understanding overview](overview.md)

articles/ai-services/language-service/conversational-language-understanding/media/llm-quick-deploy.png

@@ -6,16 +6,16 @@ author: jboback
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: overview
-ms.date: 03/24/2025
+ms.date: 05/01/2025
 ms.author: jboback
 ms.custom: language-service-clu
 ---
 
 # What is conversational language understanding?
 
-Conversational language understanding is one of the custom features offered by [Azure AI Language](../overview.md). It is a cloud-based API service that applies machine-learning intelligence to enable you to build natural language understanding component to be used in an end-to-end conversational application. 
+Conversational language understanding is one of the custom features offered by [Azure AI Language](../overview.md). It's a cloud-based API service that applies machine-learning intelligence to enable you to build natural language understanding component to be used in an end-to-end conversational application. 
 
-Conversational language understanding (CLU) enables users to build custom natural language understanding models to predict the overall intention of an incoming utterance and extract important information from it. CLU only provides the intelligence to understand the input text for the client application and doesn't perform any actions. By creating a CLU project, developers can iteratively label utterances, train and evaluate model performance before making it available for consumption. The quality of the labeled data greatly impacts model performance. To simplify building and customizing your model, the service offers a custom web portal that can be accessed through the [Language studio](https://aka.ms/languageStudio). You can easily get started with the service by following the steps in this [quickstart](quickstart.md). 
+Conversational language understanding (CLU) enables users to build custom natural language understanding models to predict the overall intention of an incoming utterance and extract important information from it. CLU only provides the intelligence to understand the input text for the client application and doesn't perform any actions. By creating a CLU project, developers can iteratively label utterances, train and evaluate model performance before making it available for consumption. The quality of the labeled data greatly impacts model performance. To simplify building and customizing your model, the service offers a custom web portal that can be accessed through the [Azure AI Foundry](https://language.cognitive.azure.com/). You can easily get started with the service by following the steps in this [quickstart](quickstart.md). 
 
 This documentation contains the following article types:
 
@@ -26,7 +26,7 @@ This documentation contains the following article types:
 
 ## Example usage scenarios
 
-CLU can be used in multiple scenarios across a variety of industries. Some examples are:
+CLU can be used in multiple scenarios across various industries. Some examples are:
 
 ### End-to-end conversational bot
 
@@ -42,18 +42,36 @@ When you integrate a client application with a speech to text component, users c
 
 ### Enterprise chat bot
 
-In a large corporation, an enterprise chat bot may handle a variety of employee affairs. It might handle frequently asked questions served by a custom question answering knowledge base, a calendar specific skill served by conversational language understanding, and an interview feedback skill served by LUIS. Use Orchestration workflow to connect all these skills together and appropriately route the incoming requests to the correct service.
+In a large corporation, an enterprise chat bot may handle various employee affairs. It might handle frequently asked questions served by a custom question answering knowledge base, a calendar specific skill served by conversational language understanding, and an interview feedback skill served by LUIS. Use Orchestration workflow to connect all these skills together and appropriately route the incoming requests to the correct service.
 
+### Agents
+
+CLU is utilized by the [intent routing](https://aka.ms/intent-triage-agent-template) agent template, which detects user intent and provides exact answering. Perfect for deterministically intent routing and exact question answering with human control.
 
 ## Project development lifecycle
 
-Creating a CLU project typically involves several different steps. 
+Creating a CLU project typically involves several different steps.
+
+:::image type="content" source="media/llm-quick-deploy.png" alt-text="Chart of the LLM-powered quick deploy path." lightbox="media/llm-quick-deploy.png":::
+
+> [!NOTE]
+> In the Azure AI Foundry, you’ll create a fine-tuning task as your workspace for customizing your CLU model. Formerly, a CLU fine-tuning task was called a CLU project. You may see these terms used interchangeably in legacy CLU documentation.
+
+CLU offers two paths for you to get the most out of your implementation.
+
+Option 1 (LLM-powered quick deploy):
+
+1. **Define your schema**: Know your data and define the actions and relevant information that needs to be recognized from user's input utterances. In this step, you create the intents and provide a detailed description on the meaning of your intents that you want to assign to user's utterances.
+
+2. **Deploy the model**: Deploying a model with the LLM-based training config makes it available for use via the Runtime API.
+
+3. **Predict intents and entities**: Use your custom model deployment to predict custom intents and prebuilt entities from user’s utterances. 
 
-:::image type="content" source="media/development-lifecycle.png" alt-text="The development lifecycle" lightbox="media/development-lifecycle.png":::
+Option 2 (Custom machine learned model)
 
-Follow these steps to get the most out of your model:
+Follow these steps to get the most out of your trained model:
 
-1. **Define your schema**: Know your data and define the actions and relevant information that needs to be recognized from user's input utterances. In this step you create the [intents](glossary.md#intent) that you want to assign to user's utterances, and the relevant [entities](glossary.md#entity) you want extracted.
+1. **Define your schema**: Know your data and define the actions and relevant information that needs to be recognized from user's input utterances. In this step, you create the [intents](glossary.md#intent) that you want to assign to user's utterances, and the relevant [entities](glossary.md#entity) you want extracted.
 
 2. **Label your data**: The quality of data labeling is a key factor in determining model performance. 
 
@@ -80,7 +98,7 @@ As you use CLU, see the following reference documentation and samples for Azure
 
 ## Responsible AI 
 
-An AI system includes not only the technology, but also the people who will use it, the people who will be affected by it, and the environment in which it's deployed. Read the transparency note for CLU to learn about responsible AI use and deployment in your systems. You can also see the following articles for more information:
+An AI system includes not only the technology, but also the people who use it, the people who are affected by it, and the environment in which it's deployed. Read the transparency note for CLU to learn about responsible AI use and deployment in your systems. You can also see the following articles for more information:
 
 [!INCLUDE [Responsible AI links](../includes/overview-responsible-ai-links.md)]
 

articles/ai-services/language-service/conversational-language-understanding/overview.md

@@ -6,17 +6,17 @@ author: jboback
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: quickstart
-ms.date: 04/29/2025
+ms.date: 05/01/2025
 ms.author: jboback
 ms.custom: language-service-clu, mode-other
-zone_pivot_groups: usage-custom-language-features
+zone_pivot_groups: usage-custom-language-features-foundry
 ---
 
 # Quickstart: Conversational language understanding 
 
-Use this article to get started with Conversational Language understanding using Language Studio and the REST API. Follow these steps to try out an example.
+Use this article to get started with Conversational Language understanding using Azure AI Foundry and the REST API. Follow these steps to try out an example.
 
-::: zone pivot="language-studio"
+::: zone pivot="azure-ai-foundry"
 
 [!INCLUDE [Language Studio quickstart](includes/quickstarts/language-studio.md)]
 

articles/ai-services/language-service/conversational-language-understanding/quickstart.md

@@ -23,6 +23,10 @@ The Language service also provides several new features as well, which can eithe
 * Preconfigured, which means the AI models that the feature uses aren't customizable. You just send your data, and use the feature's output in your applications.
 * Customizable, which means you train an AI model using our tools to fit your data specifically.
 
+Language features are also utilized in [agent templates](https://aka.ms/ai-agent-catalog):
+    * [Intent routing](https://aka.ms/intent-triage-agent-template) detects user intent and provides exact answering. Perfect for deterministically intent routing and exact question answering with human controls.
+    * [Exact question answering](https://aka.ms/exact-answer-agent-template) answers high-value predefined questions deterministically to ensure consistent and accurate responses.
+
 > [!TIP]
 > Unsure which feature to use? See [Which Language service feature should I use](#which-language-service-feature-should-i-use) to help you decide.