@@ -6,7 +6,7 @@ author: HeidiSteen
 ms.author: heidist 
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 06/11/2025
+ms.date: 10/20/2025
 ms.update-cycle: 180-days
 ms.custom:
   - ignite-2023
@@ -16,7 +16,7 @@ ms.custom:
 
 # Attach an Azure AI services resource to a skillset in Azure AI Search
 
-If you're using built-in skills for optional [AI enrichment](cognitive-search-concept-intro.md) in Azure AI Search, you can enrich a small number of documents free of charge, limited to 20 transactions daily per index. For larger and more frequent workloads, you should attach a billable [Azure AI services multi-service resource](/azure/ai-services/multi-service-resource#azure-ai-services-resource-for-azure-ai-search-skills?pivots=azportal). 
+If you're using built-in skills for optional [AI enrichment](cognitive-search-concept-intro.md) in Azure AI Search, you can enrich a small number of documents free of charge, limited to 20 transactions daily per index. For larger and more frequent workloads, you should attach a billable [classic Azure AI services multi-service resource](/azure/ai-services/multi-services-resource-search-skills). 
 
 Azure AI Search uses dedicated, internally hosted Azure AI services multi-service resources for built-in skills execution, but needs your multi-service resource for billing purposes. 
 
@@ -26,7 +26,7 @@ An Azure AI services multi-service resource provides a collection of Azure AI se
 + [Azure AI Language](/azure/ai-services/language-service/overview) for language detection, entity recognition, sentiment analysis, and key phrase extraction
 + [Azure AI Translator](/azure/ai-services/translator/translator-overview) for machine text translation
 
-Exceptions to billing through the multi-service resource include [AzureOpenAIEmbedding](cognitive-search-skill-azure-openai-embedding.md) or the [AML skill](cognitive-search-aml-skill.md) billing. Azure AI Search doesn't internally host models from Azure OpenAI or the Azure AI Foundry model catalog. Usage for AML and Azure OpenAI skills and vectorizers are through [Azure OpenAI Standard pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/#pricing) and [Azure Machine Learning Standard pricing](https://azure.microsoft.com/pricing/details/machine-learning/), respectively. A few other skills, such as Text Split and Text Merge, aren't billable.
+Exceptions to billing through the multi-service resource include the [AzureOpenAIEmbedding skill](cognitive-search-skill-azure-openai-embedding.md), [GenAI Prompt skill](cognitive-search-skill-genai-prompt.md), and [AML skill](cognitive-search-aml-skill.md) billing. Azure AI Search doesn't internally host models from Azure OpenAI or the Azure AI Foundry model catalog. Usage for AML and Azure OpenAI skills and vectorizers are through [Azure OpenAI Standard pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/#pricing) and [Azure Machine Learning Standard pricing](https://azure.microsoft.com/pricing/details/machine-learning/), respectively. A few other skills, such as Text Split and Text Merge, aren't billable.
 
 To attach an Azure AI multi-service resource, you must provide connection information in the skillset. You can use a key on the connection, or implement a keyless approach that's currently in preview.
 
@@ -35,8 +35,13 @@ To attach an Azure AI multi-service resource, you must provide connection inform
 
 ## Prerequisites
 
-+ Connectivity over a public endpoint, unless your search service meets the creation date, tier, and region requirements for private connections to an Azure AI services multi-service resource.
-+ [Azure AI multi-service resource](/azure/ai-services/multi-service-resource) created via the [Azure portal](https://portal.azure.com) only.
++ Connectivity over a public endpoint, unless your search service meets the creation date, tier, and region requirements for [private connections](search-indexer-howto-access-private.md) to an Azure AI services multi-service resource.
+
++ [Azure AI multi-service resource](/azure/ai-services/multi-services-resource-search-skills) created via the [Azure portal](https://portal.azure.com) only.
+
+  Your multi-service resource should have API kind set to `CognitiveServices`. You can view this property in the Azure portal page for your multi-service account:
+
+  :::image type="content" source="media/cognitive-search-attach-cognitive-services/cognitive-services-kind.png" alt-text="Screenshot of the API kind property in the Azure portal." border="true":::
 
 > [!NOTE]
 > If your Azure AI resource is configured to use a private endpoint, Azure AI Search can connect [using a shared private link](search-indexer-howto-access-private.md) For more information, see the [requirements and limits for using shared private links](search-limits-quotas-capacity.md#shared-private-link-resource-limits).
@@ -68,7 +73,7 @@ As with keys, the details you provide about the Azure AI Services resource are u
 Identity is set to null.
 
 ```http
-POST https://[service-name].search.windows.net/skillsets/[skillset-name]?api-version=2024-11-01-Preview  
+POST https://[service-name].search.windows.net/skillsets/[skillset-name]?api-version=2025-09-01  
 
 {  
     "name": "my skillset name",  
@@ -92,7 +97,7 @@ Identity is set to the resource ID of the user-assigned managed identity. To fin
 For a user-assigned managed identity, set the `@odata.type` and the `userAssignedIdentity` properties.
 
 ```http
-POST https://[service-name].search.windows.net/skillsets/[skillset-name]?api-version=2024-11-01-Preview  
+POST https://[service-name].search.windows.net/skillsets/[skillset-name]?api-version=2025-09-01 
 
 {  
     "name": "my skillset name",  

@@ -9,7 +9,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 09/21/2025
+ms.date: 10/21/2025
 ms.update-cycle: 365-days
 ---
 
@@ -67,6 +67,17 @@ If the enrichment pipeline doesn't have any errors, a debug session can be used
 
 Debug sessions help identify the root cause of errors or warnings by analyzing the data, skill inputs and outputs, and field mappings. If the indexer encounters configuration issues, such as incorrect network setup, permission-related access errors, or similar, please review the specific error message along with the linked documentation provided. For troubleshooting guidance, refer to the [common indexer errors and warnings](cognitive-search-common-errors-warnings.md).
 
+## Debug Sessions with private connectivity
+
+If your AI enrichment pipeline uses shared private links to access Azure resources, additional configuration is required to ensure indexer and debug sessions work correctly. This includes permissions, trusted access, and network setup.
+
+- If you're using [managed identity](search-how-to-managed-identities.md), assign the necessary roles to your search service identity, including `Storage Blob Data Contributor`, so debug sessions can write session data to your storage account.
+- Ensure the search service has access to all resources referenced in the [skillset definition](cognitive-search-working-with-skillsets.md), including any used in the debug session.
+- In your storage account, [enable trusted services](search-indexer-howto-access-trusted-service-exception.md) to allow access from Azure AI Search.
+- Set `"executionEnvironment" = "private"` property in the indexer definition to ensure the [indexer runs in a private context](search-indexer-howto-access-private.md?#4---configure-the-indexer-to-run-in-the-private-environment).
+- Create a [shared private link](search-indexer-howto-access-private.md) for each resource accessed by the search service, including: your data source, if configured to indexer AI enrichment cache and knowledge store, and any other resources configured in your skillset.
+- For other troubleshooting guidance, refer to the [common indexer errors and warnings](cognitive-search-common-errors-warnings.md).
+
 
 ## Debug session layout
 

@@ -9,7 +9,7 @@ ms.custom:
   - references_regions
   - ignite-2024
 ms.topic: reference
-ms.date: 09/29/2025
+ms.date: 10/21/2025
 ms.update-cycle: 365-days
 ---
 
@@ -249,7 +249,7 @@ This example demonstrates how to output text content in fixed-sized chunks and e
           "ordinalPosition": 0,
           "boundingPolygons": "[[{\"x\":1.5548,\"y\":0.4036},{\"x\":6.9691,\"y\":0.4033},{\"x\":6.9691,\"y\":0.8577},{\"x\":1.5548,\"y\":0.8581}],[{\"x\":1.181,\"y\":1.0627},{\"x\":7.1393,\"y\":1.0626},{\"x\":7.1393,\"y\":1.7363},{\"x\":1.181,\"y\":1.7365}],[{\"x\":1.1923,\"y\":2.1466},{\"x\":3.4585,\"y\":2.1496},{\"x\":3.4582,\"y\":2.4251},{\"x\":1.1919,\"y\":2.4221}],[{\"x\":1.1813,\"y\":2.6518},{\"x\":7.2464,\"y\":2.6375},{\"x\":7.2486,\"y\":3.5913},{\"x\":1.1835,\"y\":3.6056}],[{\"x\":1.3349,\"y\":3.9489},{\"x\":2.1237,\"y\":3.9508},{\"x\":2.1233,\"y\":4.1128},{\"x\":1.3346,\"y\":4.111}],[{\"x\":1.5705,\"y\":4.5322},{\"x\":5.801,\"y\":4.5326},{\"x\":5.801,\"y\":4.7311},{\"x\":1.5704,\"y\":4.7307}]]"
         },
-        "sections": ["sectionHeading"]
+        "sections": []
       },
       {
         "id": "2_25134f52-04c3-415a-ab3d-80729bd58e67",
@@ -259,7 +259,7 @@ This example demonstrates how to output text content in fixed-sized chunks and e
           "ordinalPosition": 1,
           "boundingPolygons": "[[{\"x\":2.2041,\"y\":0.4109},{\"x\":4.3967,\"y\":0.4131},{\"x\":4.3966,\"y\":0.5505},{\"x\":2.204,\"y\":0.5482}],[{\"x\":2.5042,\"y\":0.6422},{\"x\":4.8539,\"y\":0.6506},{\"x\":4.8527,\"y\":0.993},{\"x\":2.5029,\"y\":0.9845}],[{\"x\":2.3705,\"y\":1.1496},{\"x\":2.6859,\"y\":1.15},{\"x\":2.6858,\"y\":1.2612},{\"x\":2.3704,\"y\":1.2608}],[{\"x\":3.7418,\"y\":1.1709},{\"x\":3.8082,\"y\":1.171},{\"x\":3.8081,\"y\":1.2508},{\"x\":3.7417,\"y\":1.2507}],[{\"x\":3.9692,\"y\":1.1445},{\"x\":4.0541,\"y\":1.1445},{\"x\":4.0542,\"y\":1.2621},{\"x\":3.9692,\"y\":1.2622}],[{\"x\":4.5326,\"y\":1.2263},{\"x\":5.1065,\"y\":1.229},{\"x\":5.106,\"y\":1.346},{\"x\":4.5321,\"y\":1.3433}],[{\"x\":5.5508,\"y\":1.2267},{\"x\":5.8992,\"y\":1.2268},{\"x\":5.8991,\"y\":1.3408},{\"x\":5.5508,\"y\":1.3408}]]"
         },
-        "sections": ["sectionHeading", "title"]
+        "sections": []
        }
     ],
     "normalized_images": [ 
@@ -286,6 +286,7 @@ This example demonstrates how to output text content in fixed-sized chunks and e
     ] 
 }
 ```
+Note that the `“sections”` in the sample output above appear blank. To populate them, you’ll need to add an additional skill configured with `outputFormat` set to `markdown`to ensure the sections are properly filled.
 
 The skill uses [Azure AI Document Intelligence](/azure/ai-services/document-intelligence/overview) to compute locationMetadata. Refer to [Document Intelligence layout model](/azure/ai-services/document-intelligence/concept-layout) for details on how pages and bounding polygon coordinates are defined.
 

@@ -47,7 +47,7 @@ Architecturally, a search service sits between the external data stores that con
 
 ![Azure AI Search architecture](media/search-what-is-azure-search/azure-search.svg "Azure AI Search architecture")
 
-On the indexing side, if your content is on Azure, you can used indexers and skillsets for automated and AI-enriched indexing. Or, create a logic app workflow for equivalent automation over an even broader set of supported data sources. 
+On the indexing side, if your content is on Azure, you can use indexers and skillsets for automated and AI-enriched indexing. Or, create a logic app workflow for equivalent automation over an even broader set of supported data sources. 
 
 On the retrieval side, your app can be an agent or tool, a bot, or any client that sends requests to a search index or knowledge agent.