Merge pull request #8677 from MicrosoftDocs/main

Auto Publish – main to live - 2025-11-19 18:10 UTC

Author: learn-build-service-prod[bot]

articles/ai-foundry/agents/concepts/standard-agent-setup.md

@@ -81,12 +81,10 @@ Standard setup enforces project-level data isolation by default. Two blob storag
         * Assign role: Storage Blob Data Contributor 
     * Azure Blob Storage Container: `<workspaceId>- agents-blobstore` 
         * Assign role: Storage Blob Data Owner  
-    * Cosmos DB for NoSQL container: `<'${projectWorkspaceId}>-thread-message-store'`
-        * Assign role: Cosmos DB Built-in Data Contributor 
-    * Cosmos DB for NoSQL container: `<'${projectWorkspaceId}>-thread-message-store'` 
-        * Assign role: Cosmos DB Built-in Data Contributor 
-    * Cosmos DB for NoSQL container: `<'${projectWorkspaceId}>-agent-entity-store'` 
-        * Assign role: Cosmos DB Built-in Data Contributor 
+    * Cosmos DB for NoSQL Database: `enterprise_memory`
+        * Assign role: Cosmos DB Built-in Data Contributor
+        * Scope: Database level to cover all containers (no individual container specific role assignment). 
+
 11. Once all resources are provisioned, all developers who want to create/edit agents in the project should be assigned the role: Azure AI User on the project scope.
 
 ### Use Bicep template

articles/ai-foundry/agents/concepts/threads-runs-messages.md

@@ -8,9 +8,8 @@ ms.author: aahi
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-agent-service
 ms.topic: conceptual
-ms.date: 09/24/2025
+ms.date: 11/19/2025
 ms.custom: azure-ai-agents
-monikerRange: 'foundry-classic || foundry'
 ---
 
 # Threads, runs, and messages in Foundry Agent Service

articles/ai-foundry/agents/how-to/tools/bing-custom-search.md

@@ -7,11 +7,10 @@ manager: nitinme
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-agent-service
 ms.topic: how-to
-ms.date: 09/26/2025
+ms.date: 11/19/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
-monikerRange: 'foundry-classic || foundry'
 ---
 
 # Grounding with Bing Custom Search (preview)

articles/ai-foundry/agents/how-to/tools/bing-grounding.md

@@ -7,11 +7,10 @@ manager: nitinme
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-agent-service
 ms.topic: how-to
-ms.date: 09/26/2025
+ms.date: 11/19/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
-monikerRange: 'foundry-classic || foundry'
 ---
 
 # Grounding with Bing Search 

articles/ai-foundry/agents/how-to/tools/deep-research.md

@@ -5,7 +5,7 @@ description: Learn how to use the deep research tool with agents.
 author: aahill
 ms.author: aahi
 manager: nitinme
-ms.date: 11/13/2025
+ms.date: 11/19/2025
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-agent-service
 ms.topic: how-to
@@ -15,7 +15,6 @@ ms.custom: references_regions
 # Deep Research tool (preview)
 
 > [!NOTE]
-> * The `o3-deep-research` model is available for use **only with the Deep Research tool**. It is **not** available in the Azure OpenAI Chat Completions and Responses APIs.
 > * The **parent** Foundry project resource and the contained  `o3-deep-research` model and GPT models **must exist** in the same Azure subscription and region. Supported regions are **West US** and **Norway East**.
 > * This tool is only available in `2025-05-15-preview` API. We highly recommend that you migrate to use the `2025-11-15-preview` API. This enables you to use the `o3-deep-research` model with [web search](../../../default/agents/how-to/tools/web-search.md) or MCP tool.
 

articles/ai-foundry/agents/how-to/tools/logic-apps.md

@@ -7,13 +7,12 @@ manager: nitinme
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-agent-service
 ms.topic: how-to
-ms.date: 07/16/2025
+ms.date: 11/19/2025
 author: aahill
 ms.author: aahi
 ms.reviewer: umangsehgal
 zone_pivot_groups: selection-logic-apps
 ms.custom: azure-ai-agents
-monikerRange: 'foundry-classic || foundry'
 ---
 
 # How to use Logic Apps with Foundry Agent Service

articles/ai-foundry/agents/how-to/tools/openapi-spec.md

@@ -7,11 +7,10 @@ manager: nitinme
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-agent-service
 ms.topic: how-to
-ms.date: 08/07/2025
+ms.date: 11/19/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
-monikerRange: 'foundry-classic || foundry'
 ---
 # How to use Foundry Agent Service with OpenAPI Specified Tools
 

articles/ai-foundry/agents/overview.md

@@ -82,8 +82,15 @@ Then, equip your agent with tools. These let it access enterprise knowledge (suc
     :::column span="1":::
 ### 4. Orchestration
 
+:::moniker range="foundry-classic"
 Next, the agent needs coordination. [Connected agents](how-to\connected-agents.md) orchestrates the full lifecycle such as handling tool calls, updating conversation state, managing retries, and logging outputs.
 
+:::moniker-end
+:::moniker range="foundry"
+Next, the agent needs coordination. [Workflows](../default/agents/concepts/workflow.md) orchestrate the full lifecycle such as handling tool calls, updating conversation state, managing retries, and logging outputs.
+
+:::moniker-end
+
     :::column-end:::
     :::column span="1":::
 ### 5. Observability
@@ -107,7 +114,7 @@ Agent Service provides a production-ready foundation for deploying intelligent a
 |------------|--------------------------------|
 | **1. Visibility into conversations** | Full access to structured [conversations](../default/agents/concepts/runtime-components.md#conversation), including both user↔agent and agent↔agent messages. Ideal for UIs, debugging, and training |
 | **2. Multi-agent coordination** | Built-in support for agent-to-agent messaging. |
-| **3. Tool orchestration** | Server-side execution and retry of [tool calls](how-to\tools\overview.md) with structured logging. No manual orchestration required. |
+| **3. Tool orchestration** | Server-side execution and retry of tool calls with structured logging. No manual orchestration required. |
 | **4. Trust and safety** | Integrated [content filters](../openai/how-to/content-filters.md) help prevent misuse and mitigate prompt injection risks (XPIA). all outputs are policy-governed. |
 | **5. Enterprise integration** | Bring your own [storage](./how-to/use-your-own-resources.md#use-an-existing-azure-cosmos-db-for-nosql-account-for-conversation-storage), [Azure AI Search index](./how-to/use-your-own-resources.md#use-an-existing-azure-ai-search-resource), and [virtual network](how-to\virtual-networks.md) to meet compliance needs. |
 | **6. Observability and debugging** | Conversations, tool invocations, and message traces are [fully traceable](../how-to/develop/trace-agents-sdk.md); [Application Insights integration](./how-to/metrics.md) for telemetry |

articles/ai-foundry/concepts/evaluation-evaluators/custom-evaluators.md

@@ -16,10 +16,12 @@ monikerRange: 'foundry-classic || foundry'
 ai-usage: ai-assisted
 ---
 
-# Custom evaluators
+# Custom evaluators (preview)
 
 [!INCLUDE [version-banner](../../includes/version-banner.md)]
 
+[!INCLUDE [feature-preview](../../includes/feature-preview.md)]
+
 To start evaluating your application's generations, built-in evaluators are great out of the box. To cater to your evaluation needs, you can build your own code-based or prompt-based evaluator.
 
 ## Code-based evaluators

articles/ai-foundry/default/agents/how-to/vs-code-agents-workflow-low-code.md

@@ -65,9 +65,9 @@ To test the workflow in the VS Code extension playground, follow these steps:
 1. Select the version of the workflow you want to test.
 1. Right-click the workflow and select **Open in Local Agent Playground**.
     Alternatively, select the **Local Agent Playground** link in the **Tools** subsection, and then select your agent from the dropdown list.
-    This step opens the **Local Agent Playground** pane and starts a thread with your agent so that you can send messages.
+    This step opens the **Local Agent Playground** pane and starts a conversation with your agent so that you can send messages.
 1. In the input box at the bottom of the **Local Agent Playground** pane, type a message to send to the agent and press **Enter**.
-1. Review the agent's response in the thread.
+1. Review the agent's response in the conversation.
 
 ## Convert YAML based workflow to Agent Framework code