freshness

Author: PatrickFarley

articles/ai-foundry/responsible-ai/computer-vision/limited-access-identity.md

@@ -7,7 +7,7 @@ ms.author: pafarley
 manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: article
-ms.date: 06/17/2022
+ms.date: 07/28/2025
 ---
 
 # Limited Access to Face API

articles/ai-services/computer-vision/sdk/overview-sdk.md

@@ -6,7 +6,7 @@ author: PatrickFarley
 manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: overview
-ms.date: 06/01/2024
+ms.date: 07/28/2025
 ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.update-cycle: 365-days
 ms.author: pafarley
@@ -20,13 +20,13 @@ The Image Analysis SDK provides a convenient way to access the Image Analysis se
 > [!IMPORTANT]
 > **Breaking Changes in SDK version 1.0.0-beta.1**
 >
-> The Image Analysis SDK was rewritten in version 1.0.0-beta.1 to better align with other Azure SDKs. All APIs have changed. See the updated [quickstart](/azure/ai-services/computer-vision/quickstarts-sdk/image-analysis-client-library-40), [samples](#github-samples) and [how-to-guides](/azure/ai-services/computer-vision/how-to/call-analyze-image-40) for information on how to use the new SDK.
+> The Image Analysis SDK was rewritten in version 1.0.0-beta.1 to better align with other Azure SDKs. All APIs are changed. See the updated [quickstart](/azure/ai-services/computer-vision/quickstarts-sdk/image-analysis-client-library-40), [samples](#github-samples), and [how-to-guides](/azure/ai-services/computer-vision/how-to/call-analyze-image-40) for information on how to use the new SDK.
 >
 > Major changes:
 > - The SDK now calls the generally available [Computer Vision REST API (2023-10-01)](/rest/api/computervision/operation-groups?view=rest-computervision-2023-10-01), instead of the preview [Computer Vision REST API (2023-04-01-preview)](/rest/api/computervision/operation-groups?view=rest-computervision-2023-04-01-preview).
 > - Support for JavaScript was added.
 > - C++ is no longer supported.
-> - Image Analysis with a custom model, and Image Segmentation (background removal) are no longer supported in the SDK, because the [Computer Vision REST API (2023-10-01)](/rest/api/computervision/operation-groups?view=rest-computervision-2023-10-01) does not yet support them. To use either feature, call the [Computer Vision REST API (2023-04-01-preview)](/rest/api/computervision/operation-groups?view=rest-computervision-2023-04-01-preview) directly (using the `Analyze` and `Segment` operations respectively).
+> - Image Analysis with a custom model, and Image Segmentation (background removal) are no longer supported in the SDK, because the [Computer Vision REST API (2023-10-01)](/rest/api/computervision/operation-groups?view=rest-computervision-2023-10-01) doesn't yet support them. To use either feature, call the [Computer Vision REST API (2023-04-01-preview)](/rest/api/computervision/operation-groups?view=rest-computervision-2023-04-01-preview) directly (using the `Analyze` and `Segment` operations respectively).
 
 ## Supported languages
 

articles/ai-services/content-safety/concepts/groundedness.md

@@ -6,7 +6,7 @@ author: PatrickFarley
 manager: nitinme
 ms.service: azure-ai-content-safety
 ms.topic: conceptual
-ms.date: 04/29/2025
+ms.date: 07/28/2025
 ms.author: pafarley
 ---
 

articles/ai-services/content-safety/concepts/harm-categories.md

@@ -7,14 +7,14 @@ manager: nitinme
 ms.service: azure-ai-content-safety
 ms.custom: build-2023
 ms.topic: conceptual
-ms.date: 04/29/2025
+ms.date: 07/28/2025
 ms.author: pafarley
 ---
 
 
 # Harm categories in Azure AI Content Safety
 
-This guide describes all of the harm categories and ratings that Azure AI Content Safety uses to flag content. Both text and image content use the same set of flags.
+Azure AI Content Safety uses harm categories to flag and rate objectionable content in both text and images. This guide describes all of the harm categories and ratings that Azure AI Content Safety uses. Understanding these categories helps you configure moderation and compliance for your use cases. Both text and image content use the same set of flags.
 
 ## Harm categories
 

articles/ai-services/content-safety/concepts/jailbreak-detection.md

@@ -7,16 +7,15 @@ manager: nitinme
 ms.service: azure-ai-content-safety
 ms.custom: build-2023
 ms.topic: conceptual
-ms.date: 04/29/2025
+ms.date: 07/28/2025
 ms.author: pafarley
 ---
 
 # Prompt Shields
 
-Generative AI models can pose risks of exploitation by malicious actors. To mitigate these risks, we integrate safety mechanisms to restrict the behavior of large language models (LLMs) within a safe operational scope. However, despite these safeguards, LLMs can still be vulnerable to adversarial inputs that bypass the integrated safety protocols.
-
-Prompt Shields is a unified API that analyzes inputs to LLMs and detects adversarial user input attacks.
+Prompt Shields is a unified API in Azure AI Content Safety that detects and blocks adversarial user input attacks on large language models (LLMs). It helps prevent harmful, unsafe, or policy-violating AI outputs by analyzing prompts and documents before content is generated.
 
+Generative AI models can pose risks of exploitation by malicious actors. To mitigate these risks, we integrate safety mechanisms to restrict the behavior of large language models (LLMs) within a safe operational scope. However, despite these safeguards, LLMs can still be vulnerable to adversarial inputs that bypass the integrated safety protocols. In these cases, specialized filters like Prompt Shields are effective.
 
 ## User scenarios
 

articles/ai-services/content-safety/includes/groundedness-detection-overview.md

@@ -4,13 +4,12 @@ author: PatrickFarley
 manager: nitinme
 ms.service: azure-ai-content-safety
 ms.topic: include
-ms.date: 05/08/2025
+ms.date: 07/28/2025
 ms.author: pafarley
 ---
 
 
-
-The Groundedness detection feature detects whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users. Ungroundedness refers to instances where the LLMs produce information that is non-factual or inaccurate from what was present in the source materials.
+in Azure AI Content Safety helps you ensure that large language model (LLM) responses are based on your provided source material, reducing the risk of non-factual or fabricated outputs Ungroundedness refers to instances where the LLMs produce information that is non-factual or inaccurate from what was present in the source materials.
 
 ## Key terms