Merge pull request #7063 from jonburchel/2025-09-12-canonical-tasks-seo-review

SEO optimizations for canonical tasks review

Author: prmerger-automator[bot]

articles/ai-foundry/concepts/encryption-keys-portal.md

@@ -1,7 +1,7 @@
 ---
 title: Customer-Managed Keys for Azure AI Foundry
 titleSuffix: Azure AI Foundry
-description: Learn about using customer-managed keys for encryption to improve data security with Azure AI Foundry.
+description: Learn how to use customer-managed keys (CMK) for enhanced encryption and data security in Azure AI Foundry. Configure Azure Key Vault integration and meet compliance requirements.
 ms.author: jburchel 
 author: jonburchel 
 ms.reviewer: deeikele
@@ -13,12 +13,13 @@ ms.custom:
   - build-aifnd
   - build-2025
 zone_pivot_groups: project-type
+ai-usage: ai-assisted
 # Customer intent: As an admin, I want to understand how I can use my own encryption keys with Azure AI Foundry.
 ---
 
 # Customer-managed keys for encryption with Azure AI Foundry
 
-Customer-managed key (CMK) encryption in [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs) provides enhanced control over the encryption of your data. By using a CMK, you can manage your own encryption keys to add an extra layer of protection and meet compliance requirements more effectively.
+Customer-managed key (CMK) encryption in [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs) provides enhanced control over encryption of your data. Learn how to use customer-managed keys to add an extra layer of protection and meet compliance requirements more effectively with Azure Key Vault integration.
 
 ## About encryption in Azure AI Foundry
 

articles/ai-foundry/how-to/develop/trace-agents-sdk.md

@@ -1,33 +1,33 @@
 ---
-title: How to trace your AI application
+title: View Trace Results for AI Agents in Azure AI Foundry
 titleSuffix: Azure AI Foundry
-description: This article provides instructions on how to trace your application with Azure AI Inference SDK.
+description: View trace results for AI agents using Azure AI Foundry SDK and OpenTelemetry. Learn to see execution traces, debug performance, and monitor AI agent behavior step-by-step.
 author: lgayhardt
 ms.author: lagayhar
 ms.reviewer: amibp
 ms.date: 08/21/2025
 ms.service: azure-ai-foundry
 ms.topic: how-to
-
+ai-usage: ai-assisted
 ---
 
-# Trace your AI agents using Azure AI Foundry portal and SDK (preview)
+# View trace results for AI agents in Azure AI Foundry (preview)
 
 [!INCLUDE [feature-preview](../../includes/feature-preview.md)]
 
-This article walks you through how to instrument tracing in agents using Azure AI Foundry SDK with OpenTelemetry and Azure Monitor for enhanced observability and debugging.
+Learn how to view trace results for AI agents in Azure AI Foundry. This article shows you how to see execution traces, analyze agent behavior, and debug performance issues using Azure AI Foundry SDK with OpenTelemetry and Azure Monitor for enhanced observability.
 
 Determining the reasoning behind your agent's executions is important for troubleshooting and debugging. However, it can be difficult for complex agents for a number of reasons:
 * There could be a high number of steps involved in generating a response, making it hard to keep track of all of them.
 * The sequence of steps might vary based on user input.
 * The inputs/outputs at each stage might be long and deserve more detailed inspection.
 * Each step of an agent's runtime might also involve nesting. For example, an agent might invoke a tool, which uses another process, which then invokes another tool. If you notice strange or incorrect output from a top-level agent run, it might be difficult to determine exactly where in the execution the issue was introduced.
 
-Tracing solves this by allowing you to clearly see the inputs and outputs of each primitive involved in a particular agent run, in the order in which they were invoked.
+Trace results solve this by allowing you to view the inputs and outputs of each primitive involved in a particular agent run, displayed in the order they were invoked, making it easy to understand and debug your AI agent's behavior.
 
-## Tracing in the Azure AI Foundry Agents playground
+## View trace results in the Azure AI Foundry Agents playground
 
-The Agents playground in the Azure AI Foundry portal lets you trace threads and runs that your agents produce. To open a trace, select **Thread logs** in an active thread. You can also optionally select **Metrics** to enable automatic evaluations of the model's performance across several dimensions of **AI quality** and **Risk and safety**.
+The Agents playground in the Azure AI Foundry portal lets you view trace results for threads and runs that your agents produce. To see trace results, select **Thread logs** in an active thread. You can also optionally select **Metrics** to enable automatic evaluations of the model's performance across several dimensions of **AI quality** and **Risk and safety**.
 
 > [!NOTE]
 > Evaluation results are available for 24 hours before expiring. To get evaluation results, select your desired metrics and chat with your agent.
@@ -39,14 +39,14 @@ The Agents playground in the Azure AI Foundry portal lets you trace threads and
 
 :::image type="content" source="../../media/trace/trace-agent-playground.png" alt-text="A screenshot of the agent playground in the Azure AI Foundry portal." lightbox="../../media/trace/trace-agent-playground.png":::
 
-After selecting **Thread logs**, the screen that appears will let you view the: thread, run, run steps and any tool calls that were made. You can view the inputs and outputs between the agent and user, as well the associated metadata and any evaluations you selected.
+After selecting **Thread logs**, you can view trace results including: thread details, run information, run steps and any tool calls that were made. The trace results show you the inputs and outputs between the agent and user, as well the associated metadata and any evaluations you selected.
 
 :::image type="content" source="../../agents/media/thread-trace.png" alt-text="A screenshot of a trace." lightbox="../../agents/media/thread-trace.png":::
 
 > [!TIP]
-> If you want to view the trace of a previous thread, select **My threads** in the **Agents** screen. Choose a thread, and then select **Try in playground**.
+> If you want to view trace results from a previous thread, select **My threads** in the **Agents** screen. Choose a thread, and then select **Try in playground**.
 > :::image type="content" source="../../agents/media/thread-highlight.png" alt-text="A screenshot of the threads screen." lightbox="../../agents/media/thread-highlight.png":::
-> You will be able to see the **Thread logs** button at the top of the screen to view the trace.
+> You will be able to see the **Thread logs** button at the top of the screen to view the trace results.
 
 
 > [!NOTE]

articles/ai-foundry/how-to/develop/trace-application.md

@@ -1,20 +1,21 @@
 ---
-title: How to trace AI applications using OpenAI SDK
+title: View Trace Results for AI Applications using OpenAI SDK
 titleSuffix: Azure AI Foundry
-description: Learn how to trace applications that use OpenAI SDK in Azure AI Foundry
+description: View trace results for AI applications using OpenAI SDK with OpenTelemetry in Azure AI Foundry. See execution traces, diagnose issues, and monitor application performance.
 author: lgayhardt
 ms.author: lagayhar
 ms.reviewer: ychen
 ms.date: 08/29/2025
 ms.service: azure-ai-foundry
 ms.topic: how-to
+ai-usage: ai-assisted
 ---
 
-# Trace AI applications using OpenAI SDK
+# View trace results for AI applications using OpenAI SDK
 
-Tracing provides deep visibility into execution of your application by capturing detailed telemetry at each execution step. This helps diagnose issues and enhance performance by identifying problems such as inaccurate tool calls, misleading prompts, high latency, low-quality evaluation scores, and more.  
+Learn how to view trace results that provide deep visibility into AI application execution. See detailed telemetry captured at each step to diagnose issues and enhance performance by identifying problems such as inaccurate tool calls, misleading prompts, high latency, and low-quality evaluation scores.  
 
-This article explains how to implement tracing for AI applications using **OpenAI SDK** with OpenTelemetry in Azure AI Foundry.
+This article explains how to view trace results for AI applications using **OpenAI SDK** with OpenTelemetry in Azure AI Foundry.
 
 ## Prerequisites
 
@@ -66,6 +67,28 @@ The following steps show how to configure your resource:
     > [!IMPORTANT]
     > Using a project's endpoint requires configuring Microsoft Entra ID in your application. If you don't have Entra ID configured, use the Azure Application Insights connection string as indicated in step 3 of the tutorial.
 
+## View trace results in Azure AI Foundry portal
+
+Once you have tracing configured and your application is instrumented, you can view trace results in the Azure AI Foundry portal:
+
+1. Go to [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) and navigate to your project.
+
+1. On the side navigation bar, select **Tracing**.
+
+1. You'll see a list of trace results from your instrumented applications. Each trace shows:
+   - **Trace ID**: Unique identifier for the trace
+   - **Start time**: When the trace began
+   - **Duration**: How long the operation took
+   - **Status**: Success or failure status
+   - **Operations**: Number of spans in the trace
+
+1. Select any trace to view detailed trace results including:
+   - Complete execution timeline
+   - Input and output data for each operation
+   - Performance metrics and timing
+   - Error details if any occurred
+   - Custom attributes and metadata
+
 ## Instrument the OpenAI SDK
 
 When developing with the OpenAI SDK, you can instrument your code so traces are sent to Azure AI Foundry. Follow these steps to instrument your code:
@@ -126,7 +149,7 @@ When developing with the OpenAI SDK, you can instrument your code so traces are
     )
     ```
 
-1. If you go back to Azure AI Foundry portal, you should see the trace displayed:
+1. If you go back to Azure AI Foundry portal, you can view the trace results:
 
     :::image type="content" source="../../media/how-to/develop/trace-application/tracing-display-simple.png" alt-text="A screenshot showing how a simple chat completion request is displayed in the trace." lightbox="../../media/how-to/develop/trace-application/tracing-display-simple.png":::
 
@@ -167,7 +190,7 @@ When developing with the OpenAI SDK, you can instrument your code so traces are
         return responses
     ```
 
-1. Traces look as follows:
+1. Trace results look as follows:
 
     :::image type="content" source="../../media/how-to/develop/trace-application/tracing-display-decorator.png" alt-text="A screenshot showing how a method using a decorator is displayed in the trace." lightbox="../../media/how-to/develop/trace-application/tracing-display-decorator.png":::
 

articles/ai-foundry/how-to/evaluate-results.md

@@ -1,7 +1,7 @@
 ---
-title: View Evaluation Results in the Azure AI Foundry Portal
+title: See Evaluation Results in Azure AI Foundry Portal
 titleSuffix: Azure AI Foundry
-description: This article provides instructions on how to view evaluation results in the Azure AI Foundry portal.
+description: See and analyze AI model evaluation results in Azure AI Foundry portal. Learn to view performance metrics, compare results, and interpret evaluation data for model optimization.
 ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2023
@@ -12,21 +12,23 @@ ms.date: 05/19/2025
 ms.reviewer: mithigpe
 ms.author: lagayhar
 author: lgayhardt
+ai-usage: ai-assisted
 ---
 
-# View evaluation results in the Azure AI Foundry portal
+# See evaluation results in the Azure AI Foundry portal
 
-You can use the Azure AI Foundry portal evaluation page to visualize and assess your results. You can use it as a control center to optimize, troubleshoot, and select the ideal AI model for your deployment needs. The portal can help you with data-driven decision-making and performance enhancement in your Azure AI Foundry projects. You can access and interpret the results from various sources, including your flow, the playground quick test session, evaluation submission UI, and SDK. You have the flexibility to interact with your results in a way that best suits your workflow and preferences.
+Learn how to see evaluation results in the Azure AI Foundry portal. This guide shows you how to view and interpret AI model evaluation data, performance metrics, and quality assessments. Access evaluation results from flows, playground sessions, and SDK to make data-driven decisions about your AI models.
 
 After you visualize your evaluation results, you can dive into a thorough examination. You can view individual results and compare these results across multiple evaluation runs. You can identify trends, patterns, and discrepancies, which helps you gain invaluable insights into the performance of your AI system under various conditions.
 
 In this article, you learn how to:
 
-- View evaluation result and metrics.
-- Compare evaluation results.
-- Improve performance.
+- See evaluation results and metrics.
+- View detailed evaluation data.
+- Compare evaluation results across runs.
+- Interpret performance indicators.
 
-## Find your evaluation results
+## See your evaluation results
 
 After you submit your evaluation, you can locate the submitted evaluation run within the run list. Go to the **Evaluation** page.
 

articles/ai-foundry/how-to/fine-tune-managed-compute.md

@@ -1,7 +1,7 @@
 ---
-title: Fine-tune models using a managed compute with Azure AI Foundry portal (preview)
+title: Deploy Fine-Tuned Models with Managed Compute in Azure AI Foundry
 titleSuffix: Azure AI Foundry
-description: Learn how to fine-tune models using a managed compute with Azure AI Foundry.
+description: Deploy fine-tuned models using managed compute in Azure AI Foundry portal. Step-by-step guide to fine-tune, train, and deploy custom models with GPU compute resources.
 ms.service: azure-ai-foundry
 ms.topic: how-to
 ms.date: 08/15/2025
@@ -13,15 +13,15 @@ author: ssalgadodev
 ms.custom: 
   - references_regions
   - hub-only
-
+ai-usage: ai-assisted
 #customer intent: As a data scientist using a managed compute, I want to learn how to fine-tune models to improve model performance for specific tasks. 
 ---
 
 # Fine-tune models using managed compute (preview)
 
 [!INCLUDE [feature-preview](../includes/feature-preview.md)]
 
-This article explains how to use a managed compute to fine-tune a model in the Azure AI Foundry portal. Fine-tuning involves adapting a pretrained model to a new, related task or domain. When you use a managed compute for fine-tuning, you use your computational resources to adjust training parameters such as learning rate, batch size, and number of training epochs to optimize the model's performance for a specific task. 
+Learn how to deploy fine-tuned models using managed compute in Azure AI Foundry portal. This guide walks you through the complete process of fine-tuning and deploying custom models by adjusting training parameters such as learning rate, batch size, and training epochs to optimize performance for your specific use cases. 
 
 Fine-tuning a pretrained model to use for a related task is more efficient than building a new model, as fine-tuning builds upon the pretrained model's existing knowledge and reduces the time and data needed for training.
 

articles/ai-foundry/how-to/fine-tune-serverless.md

@@ -1,7 +1,7 @@
 ---
-title: Fine-tune models using serverless API deployments in Azure AI Foundry portal
+title: Deploy Fine-Tuned Models with Serverless API in Azure AI Foundry
 titleSuffix: Azure AI Foundry
-description: Learn how to fine-tune models deployed via serverless API deployments in Azure AI Foundry.
+description: Deploy fine-tuned models using serverless API in Azure AI Foundry. Complete guide to fine-tune, train, and deploy custom large language models with cost-effective serverless options.
 ms.service: azure-ai-foundry
 ms.topic: how-to
 ms.date: 04/14/2025
@@ -12,13 +12,14 @@ manager: nitinme
 author: ssalgadodev
 ms.custom: references_regions
 zone_pivot_groups: azure-ai-model-fine-tune
+ai-usage: ai-assisted
 ---
 
 # Fine-tune models using serverless API deployments in Azure AI Foundry
 
 [!INCLUDE [Feature preview](~/reusable-content/ce-skilling/azure/includes/ai-studio/includes/feature-preview.md)]
 
-Azure AI Foundry enables you to customize large language models to your specific datasets through a process called fine-tuning. This process offers significant benefits by allowing for customization and optimization tailored to specific tasks and applications. The advantages include improved performance, cost efficiency, reduced latency, and tailored outputs.
+Learn how to deploy fine-tuned models using serverless API deployments in Azure AI Foundry. This comprehensive guide shows you how to fine-tune large language models to your specific datasets and deploy them with serverless infrastructure, offering improved performance, cost efficiency, reduced latency, and tailored outputs.
 
 **Cost Efficiency**: Azure AI Foundry's fine-tuning can be more cost-effective, especially for large-scale deployments, thanks to pay-as-you-go pricing.
 

articles/ai-foundry/openai/chatgpt-quickstart.md

@@ -1,7 +1,7 @@
 ---
-title: 'Quickstart - Get started using chat completions with Azure OpenAI in Azure AI Foundry Models'
+title: 'Get Answers with Azure OpenAI Chat Completions'
 titleSuffix: Azure OpenAI
-description: Walkthrough on how to get started using chat completions with Azure OpenAI.
+description: Get answers using Azure OpenAI chat completions in Azure AI Foundry Models. Learn how to ask questions and get AI responses with GPT models and API integration.
 manager: nitinme
 ms.service: azure-ai-openai
 ms.custom: build-2023, build-2023-dataai, devx-track-python, devx-track-dotnet, devx-track-extended-java, devx-track-js, devx-track-go
@@ -11,11 +11,12 @@ ms.author: mbullwin
 ms.date: 07/02/2025
 zone_pivot_groups: openai-quickstart-new
 recommendations: false
+ai-usage: ai-assisted
 ---
 
-# Quickstart: Get started using chat completions with Azure OpenAI in Azure AI Foundry Models
+# Quickstart: Get answers using Azure OpenAI chat completions
 
-Use this article to get started using Azure OpenAI.
+Learn how to get answers using Azure OpenAI chat completions. This guide shows you how to ask questions and receive AI-powered responses from GPT models.
 
 ::: zone pivot="programming-language-studio"
 

articles/ai-foundry/openai/how-to/fine-tuning.md

@@ -1,7 +1,7 @@
 ---
 title: 'Customize a model with Azure OpenAI in Azure AI Foundry Models'
 titleSuffix: Azure OpenAI
-description: Learn how to create your own customized model with Azure OpenAI by using Python, the REST APIs, or Azure AI Foundry portal.
+description: Learn how to fine-tune and customize Azure OpenAI models using Python, REST APIs, or Azure AI Foundry portal. Improve model performance with LoRA adaptation and custom datasets.
 manager: nitinme
 ms.service: azure-ai-openai
 ms.custom: build-2023, build-2023-dataai, devx-track-python, references_regions
@@ -10,11 +10,12 @@ ms.date: 07/02/2025
 author: mrbullwinkle
 ms.author: mbullwin
 zone_pivot_groups: openai-fine-tuning
+ai-usage: ai-assisted
 ---
 
 # Customize a model with fine-tuning
 
-Azure OpenAI in Azure AI Foundry Models lets you tailor our models to your personal datasets by using a process known as *fine-tuning*. This customization step lets you get more out of the service by providing:
+Learn how to fine-tune Azure OpenAI models in Azure AI Foundry Models to customize them for your specific datasets and use cases. Fine-tuning enables you to get more out of the service by providing:
 
 - Higher quality results than what you can get just from [prompt engineering](../concepts/prompt-engineering.md)
 - The ability to train on more examples than can fit into a model's max request context limit.