@@ -161,7 +161,7 @@ This section supplements the [skill reference](cognitive-search-predefined-skill
 
 1. Add templates for OCR and image analysis from the Azure portal, or copy the definitions from the [skill reference](cognitive-search-predefined-skills.md) documentation. Insert them into the skills array of your skillset definition.
 
-1. If necessary, [include a Microsoft Foundry resource key](cognitive-search-attach-cognitive-services.md) in the skillset. Azure AI Search makes calls to a billable Foundry resource for OCR and image analysis for transactions that exceed the free limit (20 per indexer per day). The Foundry resource must be in the same region as your search service.
+1. If necessary, [include a Microsoft Foundry resource key](cognitive-search-attach-cognitive-services.md) in the skillset. Azure AI Search makes calls to a billable Microsoft Foundry resource for OCR and image analysis for transactions that exceed the free limit (20 per indexer per day). Unless you use a keyless connection (preview), the Microsoft Foundry resource must be in the same region as your search service.
 
 1. If original images are embedded in PDF or application files like PPTX or DOCX, you need to add a Text Merge skill if you want image output and text output together. Working with embedded images is discussed further on in this article.
 

@@ -10,7 +10,7 @@ ms.date: 11/20/2025
 [!INCLUDE [Full text introduction](full-text-intro.md)]
 
 > [!TIP]
-> You can download the [source code](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart) to start with a finished project or follow these steps to create your own.
+> You can download the [source code](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-keyword-search) to start with a finished project or follow these steps to create your own.
 
 ## Prerequisites
 

@@ -10,7 +10,7 @@ ms.date: 11/20/2025
 [!INCLUDE [Full text introduction](full-text-intro.md)]
 
 > [!TIP]
-> You can download the [source code](https://github.com/Azure-Samples/azure-search-java-samples/tree/main/quickstart) to start with a finished project or follow these steps to create your own.
+> You can download the [source code](https://github.com/Azure-Samples/azure-search-java-samples/tree/main/quickstart-keyword-search) to start with a finished project or follow these steps to create your own.
 
 ## Prerequisites
 

@@ -10,7 +10,7 @@ ms.date: 11/20/2025
 [!INCLUDE [Full text introduction](full-text-intro.md)]
 
 > [!TIP]
-> You can download the [source code](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart) to start with a finished project or follow these steps to create your own.
+> You can download the [source code](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart-keyword-search) to start with a finished project or follow these steps to create your own.
 
 ## Prerequisites
 

@@ -10,7 +10,7 @@ ms.date: 11/20/2025
 [!INCLUDE [Full text introduction](full-text-intro.md)]
 
 > [!TIP]
-> You can download the [source code](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart)  to start with a finished project or follow these steps to create your own.
+> You can download the [source code](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Keyword-Search) to start with a finished project or follow these steps to create your own.
 
 ## Prerequisites
 
@@ -36,7 +36,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you must:
 
 You run the sample code in a Jupyter notebook. So, you need to set up your environment to run Jupyter notebooks.
 
-1. Download or copy the [sample notebook from GitHub](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart).
+1. Download or copy the [sample notebook from GitHub](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Keyword-Search).
 
 1. Open the notebook in Visual Studio Code.
 

@@ -12,7 +12,7 @@ In this quickstart, you use the [Azure AI Search REST APIs](/rest/api/searchserv
 This quickstart uses fictional hotel data from the [azure-search-sample-data](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/hotels/hotel-json-documents) repo to populate the index.
 
 > [!TIP]
-> You can download the [source code](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart) to start with a finished project or follow these steps to create your own.
+> You can download the [source code](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-keyword-search) to start with a finished project or follow these steps to create your own.
 
 ## Prerequisites
 

@@ -10,7 +10,7 @@ ms.date: 11/20/2025
 [!INCLUDE [Full text introduction](full-text-intro.md)]
 
 > [!TIP]
-> You can download the [source code](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart) to start with a finished project or follow these steps to create your own.
+> You can download the [source code](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart-keyword-search) to start with a finished project or follow these steps to create your own.
 
 ## Prerequisites
 

@@ -17,11 +17,11 @@ In this quickstart, you use an IDE and the [**Azure.Search.Documents**](/dotnet/
 We recommend [Visual Studio](https://visualstudio.microsoft.com/vs/community/) for this quickstart.
 
 > [!TIP]
-> You can download the [source code](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-semantic-search) to start with a finished project or follow these steps to create your own.
+> You can download the [source code](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-semantic-ranking) to start with a finished project or follow these steps to create your own.
 
 ### Install libraries
 
-1. Start Visual Studio and open the [quickstart-semantic-search.sln](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-semantic-search) or create a new project using a console application template.
+1. Start Visual Studio and open the [quickstart-semantic-ranking.sln](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-semantic-ranking) or create a new project using a console application template.
 
 1. In **Tools** > **NuGet Package Manager**, select **Manage NuGet Packages for Solution...**.
 
@@ -41,7 +41,7 @@ If you signed in to the [Azure portal](https://portal.azure.com), you're signed
 
 In this section, you update a search index to include a semantic configuration. The code gets the index definition from the search service and adds a semantic configuration.
 
-1. Open the [BuildIndex project](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-semantic-search/BuildIndex) in Visual Studio. The program consists of the following code.
+1. Open the [BuildIndex project](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-semantic-ranking/BuildIndex) in Visual Studio. The program consists of the following code.
 
    This code uses a SearchIndexClient to update an index on your search service.
 
@@ -167,7 +167,7 @@ In this section, you update a search index to include a semantic configuration.
 
 In this section, the program runs several semantic queries in sequence.
 
-1. Open the [QueryIndex project](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-semantic-search/QueryIndex) in Visual Studio. The program consists of the following code.
+1. Open the [QueryIndex project](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-semantic-ranking/QueryIndex) in Visual Studio. The program consists of the following code.
 
    This code uses a SearchClient for sending queries to an index.
 

@@ -17,13 +17,13 @@ In this quickstart, use a Jupyter notebook and the [**azure-search-documents**](
 We recommend [Visual Studio Code](https://code.visualstudio.com/download) with Python 3.10 or later and the [Python extension](https://code.visualstudio.com/docs/languages/python) for this quickstart.
 
 > [!TIP]
-> You can [download a finished notebook](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Semantic-Search) to start with a finished project or follow these steps to create your own.
+> You can [download a finished notebook](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Semantic-Ranking) to start with a finished project or follow these steps to create your own.
 
 We recommend a virtual environment for this quickstart:
 
 1. Start Visual Studio Code.
 
-1. Open the **semantic-search-quickstart.ipynb** file or create a new notebook.
+1. Open the **semantic-ranking-quickstart.ipynb** file or create a new notebook.
 
 1. Open the Command Palette by using **Ctrl+Shift+P**.
 
@@ -58,7 +58,7 @@ If you signed in to the [Azure portal](https://portal.azure.com), you're signed
 
 In this section, you update a search index to include a semantic configuration. The code gets the index definition from the search service and adds a semantic configuration.
 
-1. Open the [semantic-search-quickstart.ipynb](https://github.com/Azure-Samples/azure-search-python-samples/blob/main/Quickstart-Semantic-Search/semantic-search-quickstart.ipynb) file in Visual Studio Code or create a new file.
+1. Open the [semantic-ranking-quickstart.ipynb](https://github.com/Azure-Samples/azure-search-python-samples/blob/main/Quickstart-Semantic-Ranking/semantic-ranking-quickstart.ipynb) file in Visual Studio Code or create a new file.
 
 1. Provide the variables used in the solution.
 

@@ -16,9 +16,9 @@ In this quickstart, you use a REST client and the [Azure AI Search REST APIs](/r
 We recommend [Visual Studio Code](https://code.visualstudio.com/download) with a [REST client extension](https://marketplace.visualstudio.com/items?itemName=humao.rest-client) for this quickstart.
 
 > [!TIP]
-> You can download the [source code](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-semantic-search) to start with a finished project or follow these steps to create your own.
+> You can download the [source code](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-semantic-ranking) to start with a finished project or follow these steps to create your own.
 
-1. Start Visual Studio Code and open the [semantic-search-index-update.rest](https://github.com/Azure-Samples/azure-search-rest-samples/blob/main/Quickstart-semantic-search/semantic-search-index-update.rest) file or create a new file.
+1. Start Visual Studio Code and open the [semantic-index-update.rest](https://github.com/Azure-Samples/azure-search-rest-samples/blob/main/Quickstart-semantic-ranking/semantic-index-update.rest) file or create a new file.
 
 1. At the top, set environment variables for your search service, authorization, and index name.
 
@@ -141,7 +141,7 @@ To update an index using the REST API, you must provide the entire schema, plus
 
 Required semantic parameters include `query_type` and `semantic_configuration_name`. Here's an example of a basic semantic query using the minimum parameters.
 
-1. Open the [semantic-search-query.rest](https://github.com/Azure-Samples/azure-search-rest-samples/blob/main/Quickstart-semantic-search/semantic-search-query.rest) file or create a new file.
+1. Open the [semantic-query.rest](https://github.com/Azure-Samples/azure-search-rest-samples/blob/main/Quickstart-semantic-ranking/semantic-query.rest) file or create a new file.
 
 1. At the top of the file, set environment variables for your search service, authorization, and index name.
 

@@ -20,7 +20,7 @@ The quickstart assumes the following is available on your computer:
 - [TypeScript](https://www.typescriptlang.org/) for writing the sample code.
 
 > [!TIP]
-> You can download the [source code](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart-semantic-ranking-js) to start with a finished project or follow these steps to create your own.
+> You can download the [source code](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart-semantic-ranking-ts) to start with a finished project or follow these steps to create your own.
 
 ### Set up local development environment
 

@@ -10,7 +10,7 @@ ms.custom:
   - devx-track-dotnet
   - ignite-2023
 ms.topic: concept-article
-ms.date: 12/10/2025
+ms.date: 01/13/2026
 ---
 
 # C# samples for Azure AI Search
@@ -47,9 +47,9 @@ Code samples from the Azure AI Search team demonstrate features and workflows. T
 
 | Sample | Article | Description |
 |--|--|--|
-| [quickstart](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart/AzureSearchQuickstart) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query an index using sample data. |
 | [quickstart-agentic-retrieval](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-agentic-retrieval) | [Quickstart: Agentic retrieval](search-get-started-agentic-retrieval.md) | Integrate semantic ranking with LLM-powered query planning and answer generation. |
-| [quickstart-semantic-search](https://github.com/Azure-Samples/azure-search-dotnet-samples/blob/main/quickstart-semantic-search/) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
+| [quickstart-keyword-search](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-keyword-search/AzureSearchQuickstart) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query an index using sample data. |
+| [quickstart-semantic-ranking](https://github.com/Azure-Samples/azure-search-dotnet-samples/blob/main/quickstart-semantic-ranking/) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
 | [quickstart-vector-search](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-vector-search) | [Quickstart: Vector search](search-get-started-vector.md) | Index and query vector content. |
 | [search-website](https://github.com/Azure-Samples/azure-search-static-web-app) | [Tutorial: Add search to web apps](tutorial-csharp-overview.md) | Build an end-to-end search app that uses the push API for bulk upload and a rich client for hosting the app and handling search requests. |
 | [tutorial-ai-enrichment](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/tutorial-ai-enrichment) | [Tutorial: AI-generated searchable content from Azure blobs](tutorial-skillset.md) | Create a skillset that iterates over Azure blobs to extract information and infer structure. |

@@ -12,7 +12,7 @@ ms.custom:
   - devx-track-extended-java
   - ignite-2023
 ms.topic: concept-article
-ms.date: 12/15/2025
+ms.date: 01/13/2026
 ---
 
 # Java samples for Azure AI Search
@@ -48,9 +48,9 @@ Code samples from the Azure AI Search team demonstrate features and workflows. T
 
 | Sample | Article | Description |
 |--|--|--|
-| [quickstart](https://github.com/Azure-Samples/azure-search-java-samples/tree/main/quickstart) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query a search index using sample data. |
-| [semantic-ranking-quickstart](https://github.com/Azure-Samples/azure-search-java-samples/tree/main/semantic-ranking-quickstart) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
-| [vector-quickstart](https://github.com/Azure-Samples/azure-search-java-samples/tree/main/vector-quickstart) | [Quickstart: Vector search](search-get-started-vector.md) | Index and query vector content. |
+| [quickstart-keyword-search](https://github.com/Azure-Samples/azure-search-java-samples/tree/main/quickstart-keyword-search) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query a search index using sample data. |
+| [quickstart-semantic-ranking](https://github.com/Azure-Samples/azure-search-java-samples/tree/main/quickstart-semantic-ranking) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
+| [quickstart-vector-search](https://github.com/Azure-Samples/azure-search-java-samples/tree/main/quickstart-vector-search) | [Quickstart: Vector search](search-get-started-vector.md) | Index and query vector content. |
 
 > [!TIP]
 > Use the [samples browser](/samples/browse/?languages=java&products=azure-cognitive-search) to search for Microsoft code samples on GitHub. You can filter your search by product, service, and language.

@@ -11,7 +11,7 @@ ms.custom:
   - devx-track-js
   - ignite-2023
 ms.topic: concept-article
-ms.date: 12/12/2025
+ms.date: 01/13/2026
 ---
 
 # JavaScript samples for Azure AI Search
@@ -60,7 +60,7 @@ Code samples from the Azure AI Search team demonstrate features and workflows. T
 
 | Sample | Article | Description |
 |--|--|--|
-| [quickstart](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query a search index using sample data. |
+| [quickstart-keyword-search](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart-keyword-search) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query a search index using sample data. |
 | [quickstart-semantic-ranking-js](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart-semantic-ranking-js) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
 | [quickstart-vector-js](https://github.com/Azure-Samples/azure-search-javascript-samples/tree/main/quickstart-vector-js) | [Quickstart: Vector search](search-get-started-vector.md) | Index and query vector content. |
 

@@ -11,7 +11,7 @@ ms.custom:
   - devx-track-python
   - ignite-2023
 ms.topic: concept-article
-ms.date: 11/21/2025
+ms.date: 01/13/2026
 ---
 
 # Python samples for Azure AI Search
@@ -36,9 +36,9 @@ Code samples from the Azure AI Search team demonstrate features and workflows. T
 
 | Sample | Article | Description |
 |--|--|--|
-| [Quickstart](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query a search index using sample data. |
 | [Quickstart-Agentic-Retrieval](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Agentic-Retrieval) | [Quickstart: Agentic retrieval](search-get-started-agentic-retrieval.md) | Integrate semantic ranking with LLM-powered query planning and answer generation. |
-| [Quickstart-Semantic-Search](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Semantic-Search) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
+| [Quickstart-Keyword-Search](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Keyword-Search) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query a search index using sample data. |
+| [Quickstart-Semantic-Ranking](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Semantic-Ranking) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
 | [Quickstart-Vector-Search](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Vector-Search) | [Quickstart: Vector search](search-get-started-vector.md) | Index and query vector content. |
 | [agentic-retrieval-pipeline-example](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/agentic-retrieval-pipeline-example) | [Tutorial: Build an end-to-end agentic retrieval solution](agentic-retrieval-how-to-create-pipeline.md) | Unlike [Quickstart-Agentic-Retrieval](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Agentic-Retrieval), this sample incorporates Foundry Agent Service for request orchestration. |
 

@@ -9,7 +9,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: concept-article
-ms.date: 12/17/2025
+ms.date: 01/13/2026
 ---
 
 # REST samples for Azure AI Search
@@ -26,9 +26,9 @@ Code samples from the Azure AI Search team demonstrate features and workflows. T
 
 | Sample | Article | Description |
 |--|--|--|
-| [quickstart](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query a search index using sample data. |
 | [quickstart-agentic-retrieval](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-agentic-retrieval) | [Quickstart: Agentic retrieval](search-get-started-agentic-retrieval.md) | Integrate semantic ranking with LLM-powered query planning and answer generation. |
-| [quickstart-semantic-search](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-semantic-search) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
+| [quickstart-keyword-search](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-keyword-search) | [Quickstart: Full-text search](search-get-started-text.md) | Create, load, and query a search index using sample data. |
+| [quickstart-semantic-ranking](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-semantic-ranking) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
 | [quickstart-vectors](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-vectors) | [Quickstart: Vector search](search-get-started-vector.md) | Index and query vector content. |
 | [acl](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/acl) | [Query-time ACL and RBAC enforcement](search-query-access-control-rbac-enforcement.md) | Implement query-time access control using role-based access control (RBAC) and access control lists (ACLs). |
 | [custom-analyzers](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/custom-analyzers) | [Tutorial: Create a custom analyzer for phone numbers](tutorial-create-custom-analyzer.md) | Use an analyzer to preserve patterns and special characters in searchable content. |

@@ -117,11 +117,11 @@ In most cases, choose a region near you, unless any of the following apply:
 
 1. Do you have business continuity and disaster recovery (BCDR) requirements? Create two or more search services in different Azure regions, each with two or more replicas so that they can be spread across multiple [availability zones](/azure/reliability/reliability-ai-search#availability-zone-support). For example, if you're operating in North America, you might choose East US and West US, or North Central US and South Central US, for each search service. For more information, see [Multi-region deployments in Azure AI Search](search-multi-region.md).
 
-1. Do you need [AI enrichment](cognitive-search-concept-intro.md), [integrated data chunking and vectorization](vector-search-integrated-vectorization.md), or [multimodal search](multimodal-search-overview.md)? For [billing purposes](cognitive-search-attach-cognitive-services.md), your Azure AI Search service and Microsoft Foundry resource must be in the same region.
+1. Do you need [AI enrichment](cognitive-search-concept-intro.md), [integrated data chunking and vectorization](vector-search-integrated-vectorization.md), or [multimodal search](multimodal-search-overview.md) powered by Foundry Tools? For billing purposes, you must [attach your Microsoft Foundry resource](cognitive-search-attach-cognitive-services.md) to your search service via a keyless connection (preview) or key-based connection. Key-based connections require both services to be in the same region.
 
-   + Check [Azure AI Search regions](search-region-support.md#azure-public-regions). If you're using OCR, entity recognition, or other skills backed by Azure AI, the **AI enrichment** column indicates whether Azure AI Search and Foundry are in the same region.
+   + Check [Azure AI Search regions](search-region-support.md#azure-public-regions). If you're using OCR, entity recognition, or other skills backed by Azure AI, the **AI enrichment** column indicates whether Azure AI Search and Microsoft Foundry are in the same region.
 
-   + Check [Azure Vision in Foundry Tools regions](/azure/ai-services/computer-vision/overview-image-analysis#region-availability) for multimodal APIs that enable text and image vectorization. These APIs are powered by Azure Vision and accessed through a Foundry resource. However, they're generally available in fewer regions than the Foundry resource itself.
+   + Check [Azure Vision in Foundry Tools regions](/azure/ai-services/computer-vision/overview-image-analysis#region-availability) for multimodal APIs that enable text and image vectorization. These APIs are powered by Azure Vision and accessed through a Microsoft Foundry resource. However, they're generally available in fewer regions than the Microsoft Foundry resource itself.
 
 ## Choose a tier
 

@@ -48,7 +48,7 @@ Select the following image to sign in to Azure and open a template. The template
 
 :::image type="content" source="~/reusable-content/ce-skilling/azure/media/template-deployments/deploy-to-azure-button.svg" alt-text="Button to deploy the Resource Manager template to Azure." border="false" link="https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fazure%2Fazure-quickstart-templates%2Fmaster%2Fquickstarts%2Fmicrosoft.search%2Fazure-search-create%2Fazuredeploy.json":::
 
-The Azure portal displays a form that allows you to easily provide parameter values. Some parameters are prefilled with the default values from the template. Provide your subscription, resource group, location, and service name. If you want to use Foundry Tools in an [AI enrichment](cognitive-search-concept-intro.md) pipeline, for example to analyze binary image files for text, choose a location that offers both Azure AI Search and Foundry Tools. Both services are required to be in the same region for AI enrichment workloads. After you complete the form, agree to the terms and conditions and then select the purchase button to complete your deployment.
+The Azure portal displays a form that allows you to easily provide parameter values. Some parameters are prefilled with the default values from the template. Provide your subscription, resource group, location, and service name. If you want to use Foundry Tools in an [AI enrichment](cognitive-search-concept-intro.md) pipeline, such as analyzing binary image files for text, choose a location that offers both Azure AI Search and Foundry Tools. Unless you use a keyless connection (preview), your Azure AI Search service and Microsoft Foundry resource must be in the same region for AI enrichment workloads. After you complete the form, agree to the terms and conditions, and then select the purchase button to complete your deployment.
 
 > [!div class="mx-imgBorder"]
 > ![Azure portal display of template](./media/search-get-started-arm/arm-portalscrnsht.png)

@@ -42,7 +42,7 @@ For content extraction, you can choose either default extraction via Azure AI Se
 | Default extraction | Extracts location metadata from PDF images only. Doesn't require another Azure AI resource. |
 | Enhanced extraction | Extracts location metadata from text and images for multiple document types. Requires a [Microsoft Foundry resource](/azure/ai-services/multi-service-resource) <sup>1</sup> in a [supported region](cognitive-search-skill-document-intelligence-layout.md#supported-regions). |
 
-<sup>1</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
+<sup>1</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) (preview) to create the skillset, both resources must be in the same region.
 
 ### Supported embedding methods
 
@@ -56,12 +56,12 @@ The portal supports the following models for each method. Deployment instruction
 
 | Provider | Models for image verbalization | Models for multimodal embeddings |
 |--|--|--|
-| [Microsoft Foundry resource](/azure/ai-services/multi-service-resource) <sup>1</sup> | Embedding model: [Azure Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>2</sup> | [Azure Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>2</sup> |
-| [Microsoft Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects?view=foundry-classic&pivots=web-portal&preserve-view=true) | LLMs:<br>phi-4<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large<br>Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> | Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> |
-| [Microsoft Foundry project](/azure/ai-foundry/how-to/create-projects?view=foundry-classic&pivots=web-portal&preserve-view=true) | LLMs:<br>phi-4<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large | |
-| [Azure OpenAI resource](/azure/ai-foundry/openai/how-to/create-resource?view=foundry-classic&pivots=web-portal&preserve-view=true) <sup>4, 5</sup> | LLMs:<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large | |
+| [Microsoft Foundry resource](/azure/ai-services/multi-service-resource) <sup>1</sup> | **Embedding model**: [Azure Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>2</sup> | [Azure Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>2</sup> |
+| [Microsoft Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects?view=foundry-classic&pivots=web-portal&preserve-view=true) | **LLMs**:<br>phi-4<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>**Embedding models**:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large<br>Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> | Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> |
+| [Microsoft Foundry project](/azure/ai-foundry/how-to/create-projects?view=foundry-classic&pivots=web-portal&preserve-view=true) | **LLMs**:<br>phi-4<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>**Embedding models**:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large | |
+| [Azure OpenAI resource](/azure/ai-foundry/openai/how-to/create-resource?view=foundry-classic&pivots=web-portal&preserve-view=true) <sup>4, 5</sup> | **LLMs**:<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>**Embedding models**:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large | |
 
-<sup>1</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
+<sup>1</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) (preview) to create the skillset, both resources must be in the same region.
 
 <sup>2</sup> The Azure Vision multimodal embeddings APIs are available in [select regions](/azure/ai-services/computer-vision/overview-image-analysis#region-availability).
 

@@ -16,7 +16,7 @@ ms.date: 12/16/2025
 
 In this quickstart, you use the **Import data (new)** wizard in the Azure portal to get started with [integrated vectorization](vector-search-integrated-vectorization.md). The wizard chunks your content and calls an embedding model to vectorize the chunks at indexing and query time.
 
-This quickstart uses text-based PDFs from the [azure-search-sample-data](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/sustainable-ai-pdf) repo. However, you can use images and still complete this quickstart.
+This quickstart uses text-based PDFs from the [azure-search-sample-data](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/sustainable-ai-pdf) repo. Although you can use images to complete this quickstart, we recommend [Quickstart: Multimodal search in the Azure portal](search-get-started-portal-image-search.md) for advanced image processing.
 
 ## Prerequisites
 
@@ -46,12 +46,12 @@ The portal supports the following embedding models for integrated vectorization.
 
 | Provider | Supported models |
 |--|--|
-| [Microsoft Foundry resource](/azure/ai-services/multi-service-resource) <sup>1</sup> | For text and images: [Azure Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>2</sup> |
-| [Microsoft Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects) | For text:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large<br><br>For text and images:<br>Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> |
-| [Microsoft Foundry project](/azure/ai-foundry/how-to/create-projects) | For text:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
-| [Azure OpenAI resource](/azure/ai-services/openai/how-to/create-resource) <sup>4, 5</sup> | For text:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
+| [Microsoft Foundry resource](/azure/ai-services/multi-service-resource) <sup>1</sup> | **For text and images**: [Azure Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>2</sup> |
+| [Microsoft Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects) | **For text**:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large<br><br>**For text and images**:<br>Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> |
+| [Microsoft Foundry project](/azure/ai-foundry/how-to/create-projects) | **For text**:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
+| [Azure OpenAI resource](/azure/ai-services/openai/how-to/create-resource) <sup>4, 5</sup> | **For text**:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
 
-<sup>1</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
+<sup>1</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) (preview) to create the skillset, both resources must be in the same region.
 
 <sup>2</sup> The Azure Vision multimodal embeddings APIs are available in [select regions](/azure/ai-services/computer-vision/overview-image-analysis#region-availability).
 

@@ -224,7 +224,7 @@ SearchIndex index = new SearchIndex(indexName)
 await indexClient.CreateIndexAsync(index);
 ```
 
-For more examples, see [azure-search-dotnet-samples/quickstart/v11/](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart/AzureSearchQuickstart).
+For more examples, see [azure-search-dotnet-samples/quickstart-keyword-search/v11](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-keyword-search/AzureSearchQuickstart).
 
 ### [**Other SDKs**](#tab/index-other-sdks)
 

@@ -54,7 +54,7 @@ For integrated vectorization, use one of the following embedding models on an Az
 
 <sup>2</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Foundry portal](https://ai.azure.com/?cid=learnDocs) aren't supported. You must create an Azure OpenAI resource in the Azure portal.
 
-<sup>3</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
+<sup>3</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) (preview) to create the skillset, both resources must be in the same region.
 
 <sup>4</sup> The Azure Vision multimodal embedding model is available in [select regions](/azure/ai-services/computer-vision/overview-image-analysis#region-availability).
 

@@ -214,7 +214,7 @@ SearchIndex index = new SearchIndex(indexName)
 await indexClient.CreateIndexAsync(index);
 ```
 
-For more examples, see the [quickstart/v11 on GitHub](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart/AzureSearchQuickstart).
+For more examples, see [azure-search-dotnet-samples/quickstart-keyword-search/v11](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-keyword-search/AzureSearchQuickstart).
 
 ### [**Other SDKs**](#tab/other-sdks-assign)
 

@@ -1,141 +1,93 @@
 ---
-title: 'Try Azure AI Search for free'
+title: Try for Free
 titleSuffix: Azure AI Search
-description: Learn how to create a trial subscription and use credits for trying advanced features.
+description: Learn how to start a trial subscription and use credits to try advanced Azure AI Search features.
 manager: nitinme
 author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.update-cycle: 180-days
-ms.topic: article
-ms.date: 11/06/2025
+ms.topic: how-to
+ms.date: 01/13/2026
 ms.custom: references_regions
 ---
 
 # Try Azure AI Search for free
 
-If you're new to Azure, you can set up an Azure free account to explore Azure AI Search and other services at no charge. Information retrieval over your own content is useful for many scenarios including AI generative search.
+If you're new to Azure, you can create an Azure free account to explore Azure AI Search and other services at no charge. The free account provides credits that you can use to create and test services for 30 days.
 
-This article explains how to get the most value from your Azure free account so that you can complete your evaluation of Azure AI Search quickly and efficiently.
+This article explains how to maximize the value of your Azure free account to quickly and efficiently evaluate Azure AI Search.
 
-## Step one: Sign up for an Azure free account
+## Prerequisites
 
-To try Azure AI Search for free, [sign up for an Azure free account](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn). The free account is active for 30 days, and comes with free credits so that you can create billable services at no charge.
++ An internet connection and a supported web browser.
++ A phone number, credit or debit card, and Microsoft or GitHub account to create an Azure free account.
 
-Currently, the credit is equivalent to USD 200. The exact amount is subject to change, and you can verify the credit on the Azure sign-up page.
+## Create an Azure free account
 
-> [!div class="nextstepaction"]
-> [Try Azure for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn)
+To try Azure AI Search for free, [sign up for an Azure free account](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
 
-After you sign up, you can immediately use either of these links to access Azure resources and experiences:
+The free account is active for 30 days and includes credits that allow you to create billable services at no charge. Currently, the credits are equivalent to USD200. This amount is subject to change, so verify the credit on the sign-up page.
 
-+ [Sign in to Azure portal](https://portal.azure.com/) to view, manage, and create more resources. You can also use the Azure portal to track your credits and projected costs.
+## Choose a region
 
-+ [Sign in to the Microsoft Foundry portal](https://ai.azure.com/?cid=learnDocs) for a no-code approach to deploying models on Azure OpenAI and using Azure AI Search for information retrieval. **We recommend you start here first.**
+You can optionally integrate Azure AI Search with Foundry Tools for [AI enrichment](cognitive-search-concept-intro.md), [integrated vectorization](vector-search-integrated-vectorization.md), and [multimodal search](multimodal-search-overview.md). For billing purposes, you must [attach your Microsoft Foundry resource](cognitive-search-attach-cognitive-services.md) to your search service via a keyless connection (preview) or key-based connection. Key-based connections require both services to be in the same region.
 
-## Step two: "Day One" tasks
+Before you create resources for a key-based connection, confirm regional support:
 
-In the Foundry (new) portal, you can create an end-to-end solution that integrates Azure AI Search and Foundry Agent Service for knowledge retrieval.
++ [**Azure AI Search regions**](search-region-support.md): The **AI enrichment** column indicates whether Azure AI Search and Microsoft Foundry are in the same region.
 
-The portal supports creating *knowledge sources* that map to your indexed content in Azure AI Search and *knowledge bases* that orchestrate retrieval operations, including query decomposition, hybrid search, and result reranking. You can then configure a Foundry agent to use this knowledge base as a Model Context Protocol (MCP) tool, allowing the agent to retrieve relevant information and provide grounded, citation-backed responses.
++ [**Azure Vision regions**](/azure/ai-services/computer-vision/overview-image-analysis?tabs=4-0#region-availability): The **Multimodal embeddings** column indicates regional support for the multimodal APIs that enable text and image vectorization. Azure Vision provides these APIs, which you access through a Microsoft Foundry resource. Ensure that Azure AI Search and Microsoft Foundry are in the same region as the multimodal APIs.
 
-For more information about the programmatic experience, see [Connect a Foundry IQ knowledge base to Foundry Agent Service](/azure/ai-foundry/agents/how-to/tools/knowledge-retrieval).
+> [!TIP]
+> If you don't need features powered by Foundry Tools, ignore the Azure Vision regions and choose an Azure AI Search region that provides the features and capacity you need.
 
-## Step three: Have a plan for next steps
+## Choose a pricing tier
 
-The trial period can go by quick. Having a plan of action can help you get the most out of your trial subscription. For Azure AI Search, most newer customers and developers are exploring RAG patterns.
+Azure AI Search offers several [pricing tiers](search-sku-tier.md), but only two tiers stay within the free account credit limits:
 
-For a next step evaluation of [RAG scenarios](retrieval-augmented-generation-overview.md), you should have three or five Azure resources for:
++ **Free** doesn't consume credits and provides 50 MB of storage. You can have one free search service per Azure subscription. This tier is always free and doesn't expire, even after your 30-day trial ends. However, it doesn't support semantic ranking or managed identities for Microsoft Entra ID authentication and authorization, which are commonly used in quickstarts.
 
-- Storing data
-- Deploying embedding and chat models (**Azure OpenAI**)
-- Applying Foundry Tools for creating AI-generated content during indexing (optional)
-- Adding information retrieval (**Azure AI Search**)
-- Adding a frontend app (optional)
-
-Many of our quickstarts and tutorials use Azure Storage, so we recommend creating an Azure Storage account for getting started.
-
-Generative search requires embedding and chat models. The Azure cloud provides Azure OpenAI, but you can also use Azure Vision in Foundry Tools for multimodal embeddings (but not chat). Another model provider is Foundry and deploying chat and embedding models into the model catalog. However, for initial exploration, we recommend Azure OpenAI for its familiarity and mainstream offerings.
-
-Application frontends are useful if you're prototyping a solution for a wider audience. You can use Azure Web apps or build an ASP.NET MVC application for this task. Otherwise, if you're working locally, you can view output in Jupyter notebooks in Visual Studio Code or another IDE. Or view results in console apps or other apps that run on localhost.
-
-## Check regions
-
-Azure AI Search offers integrated operations with applied AI in the Azure cloud. For data residency and efficient operations, integration typically depends on services running within the same region.
++ **Basic** (recommended) consumes about one-third of your USD200 credits over 30 days and provides 15 GB of storage in most regions. This tier supports all features, including semantic ranking and managed identities, and runs on dedicated infrastructure for consistent performance.
 
 > [!NOTE]
-> The same-region requirement doesn't apply to Azure OpenAI and Foundry for interoperability with Azure AI Search. However, using the same region can improve performance and reduce latency.
-
-For [AI enrichment](cognitive-search-concept-intro.md), [integrated vectorization](vector-search-integrated-vectorization.md), and [multimodal search](multimodal-search-overview.md) powered by Foundry Tools, you must create Azure AI Search and Foundry in the same region. This is required for [billing purposes](cognitive-search-attach-cognitive-services.md).
-
-Before you create these resources:
-
-+ Check [Azure AI Search regions](search-region-support.md). The **AI enrichment** column indicates whether Azure AI Search and Foundry are in the same region.
-
-+ Check [Azure Vision regions](/azure/ai-services/computer-vision/overview-image-analysis?tabs=4-0#region-availability). The **Multimodal embeddings** column indicates regional support for the multimodal APIs that enable text and image vectorization. Azure Vision provides these APIs, which you access through a Foundry resource. Ensure that your search service and Foundry resource are in the same region as the multimodal APIs.
-
-### Create services
+> Free search services that remain inactive for an extended period of time might be deleted to free up capacity, should the region be experiencing capacity constraints.
 
-1. [Create a search service](search-create-service-portal.md) if you don't have one already. Choose the Basic tier and, if applicable, the same region as Foundry. Most Azure AI Search regions provide higher capacity storage limits. There are just a few that have older and lower limits. For the Basic tier, as you install, confirm that you have a 15-GB partition.
+## Create resources
 
-   > [!div class="nextstepaction"]
-   > [Create a search service](search-create-service-portal.md)
+Most Azure AI Search scenarios require the following resources:
 
-1. [Create an Azure Storage account](/azure/storage/common/storage-account-create?tabs=azure-portal). Choose a general purpose account and use default settings.
+1. [Create an Azure AI Search service](search-create-service-portal.md). Choose the pricing tier that fits your needs and, if applicable, the same region as Microsoft Foundry. Most Azure AI Search regions provide higher-capacity storage limits. Only a few have older, lower limits. For the Basic tier, confirm that you have a 15-GB partition during service creation.
 
-1. [Create an Azure OpenAI resource](/azure/ai-services/openai/how-to/create-resource?pivots=web-portal).
+1. [Create an Azure Storage account](/azure/storage/common/storage-account-create?tabs=azure-portal) to index your own files. Choose a general purpose account and use the default settings.
 
-1. [Create a Foundry resource](/azure/ai-services/multi-service-resource) to use applied AI in your indexing workloads and Azure Vision multimodal APIs as an embedding model provider. You can create and transform content during indexing if applied AI can be attached. For multimodal APIs, make sure you choose a region that provides those APIs. Look for this tile in Azure Marketplace:
+1. [Create a Microsoft Foundry resource](/azure/ai-services/multi-service-resource) to use AI enrichment in your indexing workloads and the Azure Vision multimodal APIs as an embedding model provider.
 
-### Try the quickstarts
+## Run a quickstart
 
-Try the Azure portal quickstarts for Azure AI Search or quickstarts that use Visual Studio Code with REST or Python extensions.  It's the fastest approach creating searchable content, and you don't need coding skills to complete the tasks.
+To get started with Azure AI Search, try one of the following quickstarts:
 
-- [Quickstart: Vector search in the Azure portal](search-get-started-portal-import-vectors.md)
-- [Quickstart: Image search in the Azure portal](search-get-started-portal-image-search.md)
-- [Quickstart: Keyword in the Azure portal](search-get-started-portal.md)
-- [Quickstart: Agentic retrieval](search-get-started-agentic-retrieval.md)
-- [Quickstart: Vector search using a REST client](search-get-started-vector.md)
++ Quickstart: Agentic retrieval ([portal](get-started-portal-agentic-retrieval.md) or [programmatic](search-get-started-agentic-retrieval.md))
++ Quickstart: Keyword search ([portal](search-get-started-portal.md) or [programmatic](search-get-started-text.md))
++ Quickstart: Vector search ([portal](search-get-started-portal-import-vectors.md) or [programmatic](search-get-started-vector.md))
 
-Foundry supports connecting to content in Azure AI Search.
+You can also explore the [azure-search-vector-samples](https://github.com/Azure/azure-search-vector-samples) GitHub repository or [solution accelerators](resource-tools.md). Many samples and accelerators include Bicep scripts that deploy all Azure resources and dependencies, allowing you to quickly explore operational solutions.
 
-- [Quickstart: Chat using your own data with Azure OpenAI](/azure/ai-services/openai/use-your-data-quickstart)
-- [Tutorial: Build a custom chat app with the prompt flow SDK](/azure/ai-foundry/tutorials/copilot-sdk-create-resources)
+## Use a portal to explore features
 
-Developers should review [azure-search-vector-samples](https://github.com/Azure/azure-search-vector-samples) repository or the solution accelerators. You can deploy and run any of these samples using the Azure trial subscription. 
+You can access Azure AI Search through two portals, each optimized for different scenarios:
 
-Many samples and [accelerators](resource-tools.md) come with bicep scripts that deploy all Azure resources and dependencies, so you can skip installation steps and explore an operational solution as soon as the development completes.
-
-## Step four: Track your credits 
-
-During the trial period, you want to stay under the USD 200 credit allocation. Most services are Standard, so you won't be charged while they're not in use, but an Azure AI Search service on the Basic tier is provisioned on dedicated clusters and it can only be used by you. It's billable during its lifetime. If you provision a basic search service, expect Azure AI Search to consume about one third of your available credits during the trial period.
-
-During the trial period, the Azure portal provides a notification on the top right that tells you how many credits are used up and what remains. 
-
-You can also monitor billing by searching for *subscriptions* in the Azure portal to view subscription information at any time. The Overview page gives you spending rates, forecasts, and cost management. For more information, see [Check usage of free services included with your Azure free account](/azure/cost-management-billing/manage/check-free-service-usage).
-
-## Consider the free tier
-
-You can create a search service that doesn't consume credits. Here are some points about the free tier to keep in mind:
-
-+ You can have one free search service per Azure subscription.
-+ You can complete all of the quickstarts and most tutorials, except for those featuring semantic ranking and managed identities for Microsoft Entra ID authentication and authorization.
-+ Storage is capped at 50 MB.
-+ You can have up to three indexes, indexers, data sources, and skillset at one time.
-
-Review the [service limits](search-limits-quotas-capacity.md) for other constraints that apply to the free tier.
-
-> [!NOTE]
-> Free services that remain inactive for an extended period of time might be deleted to free up capacity if the region is under capacity constraints.
+| Portal | Description | What you can do |
+|--------|-------------|-----------------|
+| [Azure portal](https://portal.azure.com/) | The primary management interface for Azure resources and your Azure AI Search service. **This portal is most useful for classic search scenarios and overall resource management.** | <ul><li>Create and configure your search service.</li><li>Build knowledge bases and knowledge sources for [agentic retrieval](search-what-is-azure-search.md#what-is-agentic-retrieval).</li><li>Build indexes, indexers, data sources, and skillsets for [classic search](search-what-is-azure-search.md#what-is-classic-search).</li><li>Query your knowledge bases and indexes.</li><li>Track credits and monitor costs.</li></ul> |
+| [Microsoft Foundry portal](https://ai.azure.com/?cid=learnDocs) | A unified platform for deploying models and building AI applications. **This portal is most useful for agentic retrieval (RAG) scenarios.** | <ul><li>Deploy embedding and chat models.</li><li>Use [Foundry IQ](/azure/ai-foundry/agents/how-to/tools/knowledge-retrieval) to connect your Azure AI Search knowledge base to an AI agent.</li></ul> |
 
-## Next steps
+## Track your credit usage
 
-Sign up for an Azure free account:
+During the trial period, you should stay under the USD200 credit allocation. Most services are on the Standard tier, so you aren't charged while they're not in use. However, an Azure AI Search service on the Basic tier is provisioned on dedicated clusters, so it's billable during its lifetime and can only be used by you. If you create a Basic search service, expect Azure AI Search to consume about one-third of your available credits during the trial period.
 
-> [!div class="nextstepaction"]
-> [Try Azure for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn)
+In the Azure portal, a notification in the upper-right corner shows how many credits have been used and how many remain. You can also monitor billing by searching for **Subscriptions** in the topmost search bar. The **Overview** page shows spending rates, forecasts, and cost management. For more information, see [Check usage of free services included with your Azure free account](/azure/cost-management-billing/manage/check-free-service-usage).
 
-When you're ready, add Azure AI Search as your first resource:
+## Next step
 
-> [!div class="nextstepaction"]
-> [Create a search service](search-create-service-portal.md)
+Ready to move beyond exploration? After your free trial ends, learn how to [plan and manage capacity](search-capacity-planning.md) and [plan and manage costs](search-sku-manage-costs.md) for production workloads.