Merge pull request #3185 from Blackmist/rebrand

moving files for rebranding

Author: v-dirichards

.openpublishing.redirection.json

@@ -245,6 +245,16 @@
       "redirect_url": "/azure/open-datasets/dataset-catalog",
       "redirect_document_id": false
     },
+    {
+      "source_path_from_root": "/articles/ai-services/language-service/language-studio.md",
+      "redirect_url": "/azure/ai-services/language-service/overview",
+      "redirect_document_id": false
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/language-service/summarization/region-support.md",
+      "redirect_url": "/azure/ai-services/language-service/concepts/regional-support",
+      "redirect_document_id": false
+    },
     {
       "source_path_from_root": "/articles/open-datasets/dataset-genomics-data-lake.md",
       "redirect_url": "/azure/open-datasets/dataset-catalog",

articles/ai-foundry/.openpublishing.redirection.ai-studio.json

@@ -46,4 +46,4 @@ Refer to the [Content Safety overview](/azure/ai-services/content-safety/overvie
 
 ## Next step
 
-Get started using Azure AI Content Safety in [Azure AI Foundry portal](https://ai.azure.com) by following the [How-to guide](./how-to/content-safety.md).
+Get started using Azure AI Content Safety in [Azure AI Foundry portal](https://ai.azure.com) by following the [How-to guide](/azure/ai-services/content-safety/how-to/foundry).

articles/ai-studio/ai-services/content-safety-overview.md renamed to articles/ai-foundry/ai-services/content-safety-overview.md

@@ -100,7 +100,7 @@ Here are a few guides to help you get started with Azure OpenAI Service playgrou
 - [Quickstart: Use the chat playground](../../quickstarts/get-started-playground.md)
 - [Quickstart: Get started using Azure OpenAI Assistants](../../../ai-services/openai/assistants-quickstart.md?context=/azure/ai-studio/context/context)
 - [Quickstart: Use GPT-4o in the real-time audio playground](../../../ai-services/openai/realtime-audio-quickstart.md?context=/azure/ai-studio/context/context)
-- [Quickstart: Analyze images and video in the chat playground](../../quickstarts/multimodal-vision.md)
+- [Quickstart: Analyze images and video in the chat playground](/azure/ai-services/openai/gpt-v-quickstart)
 
 Each playground has different model requirements and capabilities. The supported regions vary depending on the model. For more information about model availability per region, see the [Azure OpenAI Service models documentation](../../../ai-services/openai/concepts/models.md).
 
@@ -145,5 +145,5 @@ At some point, you want to develop apps with code. Here are some developer resou
 
 ## Related content
 
-- [Azure OpenAI in Azure AI Foundry portal](../../azure-openai-in-ai-studio.md)
+- [Azure OpenAI in Azure AI Foundry portal](../../azure-openai-in-ai-foundry.md)
 - [Use Azure AI services resources](./connect-ai-services.md)

articles/ai-studio/ai-services/how-to/connect-ai-services.md renamed to articles/ai-foundry/ai-services/how-to/connect-ai-services.md

@@ -1,14 +1,15 @@
 ---
 title: A/B experiments for AI applications
+titleSuffix: Azure AI Foundry
 description: Learn about conducting A/B experiments for AI applications.
-author: s-polly
-ms.author: scottpolly
+author: lgayhardt
+ms.author: lagayhar
 ms.reviewer: skohlmeier
 ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2024
 ms.topic: concept-article
-ms.date: 11/22/2024
+ms.date: 02/27/2025
 
 #CustomerIntent: As an AI application developer, I want to learn about A/B experiments so that I can evaluate and improve my applications.
 ---
@@ -18,23 +19,21 @@ ms.date: 11/22/2024
 > [!IMPORTANT]
 >Items marked (preview) in this article are currently in public or private preview. This preview is provided without a service-level agreement, and we don't recommend it for production workloads. Certain features might not be supported or might have constrained capabilities. For more information, see [Supplemental Terms of Use for Microsoft Azure Previews](https://azure.microsoft.com/support/legal/preview-supplemental-terms/).
 
-In the  field of AI application development, A/B experimentation has emerged as a critical practice. It allows for continuous evaluation of AI applications, balancing business impact, risk, and cost. While offline and online evaluations provide some insights, they need to be supplemented with A/B experimentation to ensure the use of right metrics for measuring success.  A/B experimentation involves comparing two versions of a feature, prompt, or model using feature flags or dynamic configuration to determine which performs better. This method is essential for several reasons:
+In the  field of AI application development, A/B experimentation has emerged as a critical practice. It allows for continuous evaluation of AI applications, balancing business impact, risk, and cost. While offline and online evaluations provide some insights, they need to be supplemented with A/B experimentation to ensure the use of right metrics for measuring success. A/B experimentation involves comparing two versions of a feature, prompt, or model using feature flags or dynamic configuration to determine which performs better. This method is essential for several reasons:
 
 - **Enhancing Model Performance** - A/B experimentation allows developers to systematically test different versions of AI models, algorithms, or features to identify the most effective version. With controlled experiments, you can measure the effect of changes on key performance metrics, such as accuracy, user engagement, and response time. This iterative process enables you to identify the best model, helps fine-tuning and ensures that your models deliver the best possible results.
 - **Reducing Bias and Improving Fairness** - AI models can inadvertently introduce biases, leading to unfair outcomes. A/B experimentation helps identify and mitigate these biases by comparing the performance of different model versions across diverse user groups. This ensures that the AI applications are fair and equitable, providing consistent performance for all users.
 - **Accelerating Innovation** - A/B experimentation fosters a culture of innovation by encouraging continuous experimentation and learning. You can quickly validate new ideas and features, reducing the time and resources spent on unproductive approaches. This accelerates the development cycle and allows teams to bring innovative AI solutions to market faster.
 - **Optimizing User Experience** - User experience is paramount in AI applications. A/B experimentation enables you to experiment with different user interface designs, interaction patterns, and personalization strategies. By analyzing user feedback and behavior, you can optimize the user experience, making AI applications more intuitive and engaging.
 - **Data-Driven Decision Making** - A/B experimentation provides a robust framework for data-driven decision making. Instead of relying on intuition or assumptions, you can base your decisions on empirical evidence. This leads to more informed and effective strategies for improving AI applications.
 
-
 ## How does A/B experimentation fit into the AI application lifecycle?
 
-
 A/B experimentation and offline evaluation are both essential components in the development of AI applications, each serving unique purposes that complement each other.
 
 Offline evaluation involves testing AI models using test datasets to measure their performance on various metrics such as fluency and coherence. After selecting a model in the Azure AI Model Catalog or GitHub Model marketplace, offline preproduction evaluation is crucial for initial model validation during integration testing, allowing you to identify potential issues and make improvements before deploying the model or application to production.
 
-However, offline evaluation has its limitations. It can't fully capture the complex interactions that occur in real-world scenarios. This is where A/B experimentation comes into play. By deploying different versions of the AI model or UX features to live users, A/B experimentation provides insights into how the model and application performs in real-world conditions. This helps you understand user behavior, identify unforeseen issues, and measure the impact of changes on model evaluation metrics, operational metrics (for example, latency) and business metrics (for example, account sign-ups, conversions, etc.).
+However, offline evaluation has its limitations. It can't fully capture the complex interactions that occur in real-world scenarios. This is where A/B experimentation comes into play. By deploying different versions of the AI model or UX features to live users, A/B experimentation provides insights into how the model and application performs in real-world conditions. This helps you understand user behavior, identify unforeseen issues, and measure the impact of changes on model evaluation metrics, operational metrics (for example, latency), and business metrics (for example, account sign-ups, conversions, etc.).
 
 As shown in the diagram, while offline evaluation is essential for initial model validation and refinement, A/B experimentation provides the real-world testing needed to ensure the AI application performs effectively and fairly in practice. Together, they form a comprehensive approach to developing robust, safe, and user-friendly AI applications.
 
@@ -52,8 +51,7 @@ We're significantly simplifying the evaluation and A/B experimentation process w
 
 ## Azure AI Partners
 
-
-You're also welcome to use your own A/B experimentation provider to run experiments on your AI applications. There are several solutions to choose from available in the Azure Marketplace:
+You're also welcome to use your own A/B experimentation provider to run experiments on your AI applications. There are several solutions to choose from available in Azure Marketplace:
 
 ### Statsig
 
@@ -67,8 +65,6 @@ You're also welcome to use your own A/B experimentation provider to run experime
 ### LaunchDarkly
 [LaunchDarkly](https://azuremarketplace.microsoft.com/marketplace/apps/aad.launchdarkly?tab=Overview) is a feature management and experimentation platform built with software developers in mind. It enables you to manage feature flags on a large scale, run A/B tests and experiments, and progressively deliver software to ship with confidence.
 
-
-
 ## Related content
 
 

articles/ai-studio/ai-services/how-to/connect-azure-openai.md renamed to articles/ai-foundry/ai-services/how-to/connect-azure-openai.md

@@ -128,6 +128,6 @@ In the Azure portal, you can find resources that correspond to your project in A
 
 ## Next steps
 
-- [Quickstart: Analyze images and video in the chat playground](../quickstarts/multimodal-vision.md)
-- [Learn more about Azure AI Foundry](../what-is-ai-studio.md)
+- [Quickstart: Analyze images and video in the chat playground](/azure/ai-services/openai/gpt-v-quickstart)
+- [Learn more about Azure AI Foundry](../what-is-ai-foundry.md)
 - [Learn more about projects](../how-to/create-projects.md)

articles/ai-studio/azure-openai-in-ai-studio.md renamed to articles/ai-foundry/azure-openai-in-ai-foundry.md

@@ -28,7 +28,7 @@ At the top level, Azure AI Foundry provides access to the following resources:
 
     When you use Azure AI Foundry portal, you can directly work with Azure OpenAI without an Azure Studio project. Or you can use Azure OpenAI through a project.
 
-    For more information, visit [Azure OpenAI in Azure AI Foundry portal](../azure-openai-in-ai-studio.md).
+    For more information, visit [Azure OpenAI in Azure AI Foundry portal](../azure-openai-in-ai-foundry.md).
 
 - **Management center**: The management center streamlines governance and management of Azure AI Foundry resources such as hubs, projects, connected resources, and deployments.
 
@@ -108,7 +108,7 @@ Azure AI services including Azure OpenAI provide control plane endpoints for ope
 
 To reduce the complexity of Azure RBAC management, Azure AI Foundry provides a *control plane proxy* that allows you to perform operations on connected Azure AI services and Azure OpenAI resources. Performing operations on these resources through the control plane proxy only requires Azure RBAC permissions on the hub. The Azure AI Foundry service then performs the call to the Azure AI services or Azure OpenAI control plane endpoint on your behalf.
 
-For more information, see [Role-based access control in Azure AI Foundry portal](rbac-ai-studio.md).
+For more information, see [Role-based access control in Azure AI Foundry portal](rbac-ai-foundry.md).
 
 ## Attribute-based access control