Merge pull request #7501 from MicrosoftDocs/main

Auto Publish – main to live - 2025-10-06 22:06 UTC

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

articles/ai-foundry/concepts/evaluation-evaluators/azure-openai-graders.md

@@ -2,6 +2,7 @@
 title: Azure OpenAI Graders for generative AI
 titleSuffix: Azure AI Foundry
 description: Learn about Azure OpenAI Graders for evaluating AI model outputs, including label grading, string checking, text similarity, and custom grading.
+ai-usage: ai-assisted
 author: lgayhardt
 ms.author: lagayhar
 ms.reviewer: mithigpe

articles/ai-foundry/responsible-ai/openai/data-privacy.md

@@ -48,7 +48,7 @@ The diagram below illustrates how your data is processed. This diagram covers se
 1. How Azure AI Foundry creates a fine-tuned (custom) model with your uploaded data. 
 1. How Azure AI Foundry and Microsoft personnel analyze prompts and completions (text and image) for harmful content and for patterns suggesting the use of the service in a manner that violates the Code of Conduct or other applicable product terms. 
 
-:::image type="content" source="media\flow-2.jpg" alt-text="Data flow diagram for the service." lightbox="media\flow-2.jpg":::
+:::image type="content" source="media\flow-3.png" alt-text="Data flow diagram for the service." lightbox="media\flow-3.png":::
 
 As depicted in the diagram above, managed customers may [apply to modify abuse monitoring](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOE9MUTFMUlpBNk5IQlZWWkcyUEpWWEhGOCQlQCN0PWcu). 
 
@@ -159,7 +159,7 @@ To learn more about Microsoft's privacy and security commitments see the [Micros
 
 |Date  |Changes  |
 |---------|---------|
-| 29 September 2025 | Expanded document to Azure Direct Models; separated content filtering and abuse monitoring sections; added clarifications on abuse monitoring and severe or recurring abuse. |
+| 3 October 2025 | Expanded document to Azure Direct Models; separated content filtering and abuse monitoring sections; added clarifications on abuse monitoring and severe or recurring abuse. |
 | 17 December 2024 | Added information about data processing and storage in connection with new Stored completions feature; added language clarifying that Azure OpenAI features in preview may not support all data storage conditions; removed "preview" designation for Batch processing |
 |18 November 2024 | Added information about location of data processing for new ‘Data zone’ deployment types; added information about new AI review of prompts and completions as part of preventing abuse and generation of harmful content  |
 | 4 September 2024 | Added information (and revised existing text accordingly) about data processing for new features including Assistants API (preview), Batch (preview), and Global Deployments; revised language related to location of data processing, in accordance with [Azure data residency principles](https://azure.microsoft.com/explore/global-infrastructure/data-residency#select-geography); added information about data processing for safety evaluations of fine-tuned models; clarified commitments related to use of prompts and completions; minor revisions to improve clarity  |

articles/ai-foundry/responsible-ai/openai/media/flow-3.png

@@ -519,9 +519,9 @@ items:
             href: ../cognitive-services-container-support.md
     - name: Concepts
       items:
-      - name: Recognized entity types
+      - name: Recognized entity types 🆕
         href: personally-identifiable-information/concepts/entity-categories.md
-      - name: Recognized entities list
+      - name: Recognized entities list 🆕
         href: personally-identifiable-information/concepts/entity-categories-list.md
       - name: Recognized entity categories for conversation
         href: personally-identifiable-information/concepts/conversations-entity-categories.md

articles/ai-services/language-service/toc.yml

@@ -3,11 +3,11 @@ author: goergenj
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: include
-ms.date: 07/09/2025
+ms.date: 10/06/2025
 ms.author: jagoerge
 ---
 
 > [!IMPORTANT]
-> Intent recognition in Azure AI Speech is being retired on September 30, 2025. Your applications won't be able to use intent recognition directly via Azure AI Speech after this date. However, you're still able to perform intent recognition using Azure AI Language Service or Azure OpenAI.
+> Intent recognition in Azure AI Speech was retired on September 30, 2025. Applications can no longer use intent recognition via Azure AI Speech. However, you're still able to perform intent recognition using Azure AI Language Service or Azure OpenAI.
 > 
 > This change doesn't affect other Azure AI Speech capabilities such as [speech to text](../speech-to-text.md) (including no change to speaker diarization), [text to speech](../text-to-speech.md), and [speech translation](../speech-translation.md). 

articles/ai-services/speech-service/includes/intent-recognition-retire.md

@@ -8,6 +8,6 @@ ms.author: pafarley
 ---
 
 > [!IMPORTANT]
-> Speaker recognition in Azure AI Speech will be retired on September 30th 2025. Your applications won't be able to use speaker recognition after this date.
+> Speaker recognition in Azure AI Speech was retired on September 30th, 2025. Applications can no longer use the speaker recognition APIs.
 > 
-> This change doesn't affect other Azure AI Speech capabilities such as [speech to text](../speech-to-text.md) (including no change to speaker diarization), [text to speech](../text-to-speech.md), and [speech translation](../speech-translation.md). 
+> This change doesn't affect other Azure AI Speech capabilities such as [speech to text](../speech-to-text.md) (including no change to speaker diarization), [text to speech](../text-to-speech.md), and [speech translation](../speech-translation.md).

articles/ai-services/speech-service/includes/retire-speaker-recognition.md

@@ -31,7 +31,7 @@ Use this component to measure the accuracy of a trained model. You provide a dat
 ## How to use Evaluate Model
 1. Connect the **Scored dataset** output of the [Score Model](./score-model.md) or Result dataset output of the [Assign Data to Clusters](./assign-data-to-clusters.md) to the left input port of **Evaluate Model**. 
     > [!NOTE] 
-    > If use components like "Select Columns in Dataset" to select part of input dataset, please ensure
+    > If you use components like "Select Columns in Dataset" to select part of input dataset, please ensure
     > Actual label column (used in training), 'Scored Probabilities' column and 'Scored Labels' column exist to calculate metrics like AUC, Accuracy for binary classification/anomaly detection.
     > Actual label column, 'Scored Labels' column exist to calculate metrics for multi-class classification/regression.
     > 'Assignments' column, columns 'DistancesToClusterCenter no.X' (X is centroid index, ranging from 0, ..., Number of centroids-1)     exist to calculate metrics for clustering.

articles/machine-learning/component-reference/evaluate-model.md

@@ -12,6 +12,7 @@ author: lgayhardt
 ms.author: lagayhar
 ms.reviewer: chenlujiao
 ms.date: 09/30/2024
+ms.update-cycle: 365-days
 ---
 
 # Prompt flow ecosystem

articles/machine-learning/prompt-flow/community-ecosystem.md

@@ -12,6 +12,7 @@ author: lgayhardt
 ms.author: lagayhar
 ms.reviewer: keli19
 ms.date: 06/26/2024
+ms.update-cycle: 365-days
 ---
 
 # Connections in prompt flow

articles/machine-learning/prompt-flow/concept-connections.md

@@ -12,6 +12,7 @@ author: lgayhardt
 ms.author: lagayhar
 ms.reviewer: keli19
 ms.date: 06/28/2024
+ms.update-cycle: 365-days
 ---
 
 # Flows in prompt flow?