final batch

s-polly · s-polly · commit d49a5af34b14 · 2025-08-08T09:32:48.000-05:00
diff --git a/articles/ai-foundry/concepts/ai-red-teaming-agent.md b/articles/ai-foundry/concepts/ai-red-teaming-agent.md
@@ -2,7 +2,6 @@
 title: AI Red Teaming Agent
 titleSuffix: Azure AI Foundry
 description: This article provides conceptual overview of the AI Red Teaming Agent.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: how-to
 ms.date: 04/04/2025
@@ -37,7 +36,7 @@ When thinking about AI-related safety risks developing trustworthy AI systems, M
 
 :::image type="content" source="../media/evaluations/red-teaming-agent/map-measure-mitigate-ai-red-teaming.png" alt-text="Diagram of how to use AI Red Teaming Agent showing proactive to reactive and less costly to more costly." lightbox="../media/evaluations/red-teaming-agent/map-measure-mitigate-ai-red-teaming.png":::
 
-AI Red Teaming Agent can be used to run automated scans and simulate adversarial probing to help accelerate the identification and evaluation of known risks at scale. This helps teams "shift left" from costly reactive incidents to more proactive testing frameworks that can catch issues before deployment. Manual AI red teaming process is time and resource intensive. It relies on the creativity of safety and security expertise to simulate adversarial probing. This process can create a bottleneck for many organizations to accelerate AI adoption. With the AI Red Teaming Agent, organizations can now leverage Microsoft’s deep expertise to scale and accelerate their AI development with Trustworthy AI at the forefront.
+AI Red Teaming Agent can be used to run automated scans and simulate adversarial probing to help accelerate the identification and evaluation of known risks at scale. This helps teams "shift left" from costly reactive incidents to more proactive testing frameworks that can catch issues before deployment. Manual AI red teaming process is time and resource intensive. It relies on the creativity of safety and security expertise to simulate adversarial probing. This process can create a bottleneck for many organizations to accelerate AI adoption. With the AI Red Teaming Agent, organizations can now leverage Microsoft's deep expertise to scale and accelerate their AI development with Trustworthy AI at the forefront.
 
 We encourage teams to use the AI Red Teaming Agent to run automated scans throughout the design, development, and pre-deployment stage:
 
@@ -105,7 +104,7 @@ Learn more about the tools leveraged by the AI Red Teaming Agent.
 - [Azure AI Risk and Safety Evaluations](./safety-evaluations-transparency-note.md)
 - [PyRIT: Python Risk Identification Tool](https://github.com/Azure/PyRIT)
 
-The most effective strategies for risk assessment we’ve seen leverage automated tools to surface potential risks, which are then analyzed by expert human teams for deeper insights. If your organization is just starting with AI red teaming, we encourage you to explore the resources created by our own AI red team at Microsoft to help you get started.
+The most effective strategies for risk assessment we've seen leverage automated tools to surface potential risks, which are then analyzed by expert human teams for deeper insights. If your organization is just starting with AI red teaming, we encourage you to explore the resources created by our own AI red team at Microsoft to help you get started.
 
 - [Planning red teaming for large language models (LLMs) and their applications](../openai/concepts/red-teaming.md)
 - [Three takeaways from red teaming 100 generative AI products](https://www.microsoft.com/security/blog/2025/01/13/3-takeaways-from-red-teaming-100-generative-ai-products/)
diff --git a/articles/ai-foundry/concepts/fine-tuning-overview.md b/articles/ai-foundry/concepts/fine-tuning-overview.md
@@ -2,7 +2,6 @@
 title: Fine-tune models with Azure AI Foundry
 titleSuffix: Azure AI Foundry
 description: This article explains what fine-tuning is and under what circumstances you should consider doing it.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - build-2024
@@ -26,10 +25,10 @@ Fine-tuning excels at customizing language models for specific applications and
 - **Domain Specialization:** Adapt a language model for a specialized field like medicine, finance, or law – where domain specific knowledge and terminology is important. Teach the model to understand technical jargon and provide more accurate responses.
 - **Task Performance:** Optimize a model for a specific task like sentiment analysis, code generation, translation, or summarization. You can significantly improve the performance of a smaller model on a specific application, compared to a general purpose model.
 - **Style and Tone:** Teach the model to match your preferred communication style – for example, adapt the model for formal business writing, brand-specific voice, or technical writing.
-- **Instruction Following:** Improve the model’s ability to follow specific formatting requirements, multi-step instructions, or structured outputs. In multi-agent frameworks, teach the model to call the right agent for the right task.
+- **Instruction Following:** Improve the model's ability to follow specific formatting requirements, multi-step instructions, or structured outputs. In multi-agent frameworks, teach the model to call the right agent for the right task.
 - **Compliance and Safety:** Train a fine-tuned model to adhere to organizational policies, regulatory requirements, or other guidelines unique to your application.
 - **Language or Cultural Adaptation:** Tailor a language model for a specific language, dialect, or cultural context that may not be well represented in the training data.
-Fine-tuning is especially valuable when a general-purpose model doesn’t meet your specific requirements – but you want to avoid the cost and complexity of training a model from scratch.
+Fine-tuning is especially valuable when a general-purpose model doesn't meet your specific requirements – but you want to avoid the cost and complexity of training a model from scratch.
 
 ## Serverless or Managed Compute?
 Before picking a model, it's important to select the fine-tuning product that matches your needs. Azure's AI Foundry offers two primary modalities for fine tuning: serverless and managed compute.
diff --git a/articles/ai-foundry/concepts/foundry-models-overview.md b/articles/ai-foundry/concepts/foundry-models-overview.md
@@ -2,7 +2,6 @@
 title: Explore Azure AI Foundry Models
 titleSuffix: Azure AI Foundry
 description: This article introduces Azure AI Foundry Models and the model catalog in Azure AI Foundry portal.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - build-2025
diff --git a/articles/ai-foundry/concepts/model-lifecycle-retirement.md b/articles/ai-foundry/concepts/model-lifecycle-retirement.md
@@ -2,7 +2,6 @@
 title: Deprecation for Foundry Models
 titleSuffix: Azure AI Foundry
 description: Learn about the lifecycle stages, deprecation, and retirement for Azure AI Foundry Models.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: concept-article
 ms.date: 06/17/2025
diff --git a/articles/ai-foundry/foundry-models/concepts/content-filter.md b/articles/ai-foundry/foundry-models/concepts/content-filter.md
@@ -8,7 +8,6 @@ ms.service: azure-ai-model-inference
 ms.topic: concept-article
 ms.date: 05/19/2025
 ms.custom: ignite-2024, github-universe-2024
-manager: scottpolly
 ms.reviewer: fasantia
 reviewer: santiagxf
 ---
diff --git a/articles/ai-foundry/foundry-models/concepts/default-safety-policies.md b/articles/ai-foundry/foundry-models/concepts/default-safety-policies.md
@@ -7,7 +7,6 @@ ms.author: mopeakande
 ms.service: azure-ai-model-inference
 ms.topic: concept-article
 ms.date: 05/19/2025
-manager: scottpolly
 ms.reviewer: fasantia
 reviewer: santiagxf
 ---
diff --git a/articles/ai-foundry/foundry-models/concepts/endpoints.md b/articles/ai-foundry/foundry-models/concepts/endpoints.md
@@ -3,7 +3,6 @@ title: Endpoints for Azure AI Foundry Models
 titleSuffix: Azure AI Foundry
 description: Learn about the Azure AI Foundry Models endpoint
 author: msakande
-manager: scottpolly
 ms.service: azure-ai-model-inference
 ms.topic: how-to
 ms.date: 05/19/2025
diff --git a/articles/ai-foundry/foundry-models/concepts/model-versions.md b/articles/ai-foundry/foundry-models/concepts/model-versions.md
@@ -6,7 +6,6 @@ ms.service: azure-ai-model-inference
 ms.topic: concept-article
 ms.custom: ignite-2024, github-universe-2024
 ms.date: 05/19/2025
-manager: scottpolly
 author: msakande
 ms.author: mopeakande
 recommendations: false
diff --git a/articles/ai-foundry/foundry-models/concepts/models.md b/articles/ai-foundry/foundry-models/concepts/models.md
@@ -4,7 +4,6 @@ titleSuffix: Azure AI Foundry
 description: Explore the available Azure AI Foundry Models and their capabilities.
 author: msakande
 ms.author: mopeakande
-manager: scottpolly
 reviewer: santiagxf
 ms.reviewer: fasantia
 ms.date: 08/04/2025
diff --git a/articles/ai-foundry/foundry-models/how-to/configure-content-filters.md b/articles/ai-foundry/foundry-models/how-to/configure-content-filters.md
@@ -2,7 +2,6 @@
 title: 'How to configure content filters for models in Azure AI Foundry'
 titleSuffix: Azure AI Foundry
 description: Learn to use and configure the content filters that come with Azure AI Foundry, including getting approval for gated modifications.
-manager: scottpolly
 ms.service: azure-ai-model-inference
 ms.topic: how-to
 ms.date: 05/19/2025
diff --git a/articles/ai-foundry/foundry-models/how-to/github/create-model-deployments.md b/articles/ai-foundry/foundry-models/how-to/github/create-model-deployments.md
@@ -6,7 +6,6 @@ ms.service: azure-ai-model-inference
 ms.topic: how-to
 ms.date: 05/19/2025
 ms.custom: ignite-2024, github-universe-2024
-manager: scottpolly
 author: ssalgadodev
 ms.author: ssalgado
 recommendations: false
diff --git a/articles/ai-foundry/foundry-models/how-to/inference.md b/articles/ai-foundry/foundry-models/how-to/inference.md
@@ -2,7 +2,6 @@
 title: How to use the Azure AI Foundry Models inference endpoints to consume models
 titleSuffix: Azure AI Foundry
 description: Learn how to use the Azure AI Foundry Models inference endpoint to consume models
-manager: scottpolly
 author: msakande
 reviewer: santiagxf
 ms.service: azure-ai-model-inference
diff --git a/articles/ai-foundry/foundry-models/quotas-limits.md b/articles/ai-foundry/foundry-models/quotas-limits.md
@@ -3,7 +3,6 @@ title: Azure AI Foundry Models quotas and limits
 titleSuffix: Azure AI Foundry
 description: Quick reference, detailed description, and best practices on the quotas and limits for the Azure AI Foundry service.
 author: msakande
-manager: scottpolly
 ms.service: azure-ai-model-inference
 ms.custom: ignite-2024, github-universe-2024
 ms.topic: concept-article
diff --git a/articles/ai-foundry/how-to/concept-data-privacy.md b/articles/ai-foundry/how-to/concept-data-privacy.md
@@ -2,7 +2,6 @@
 title: Data, privacy, and security for use of models through the model catalog in Azure AI Foundry portal
 titleSuffix: Azure AI Foundry
 description: Get details about how data that customers provide is processed, used, and stored when a user deploys a model from the model catalog.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom: references_regions, build-2024
 ms.topic: concept-article
diff --git a/articles/ai-foundry/how-to/deploy-models-openai.md b/articles/ai-foundry/how-to/deploy-models-openai.md
@@ -2,7 +2,6 @@
 title: How to deploy Azure OpenAI models with Azure AI Foundry
 titleSuffix: Azure AI Foundry
 description: Learn how to deploy Azure OpenAI models with Azure AI Foundry.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2023
diff --git a/articles/ai-foundry/how-to/develop/create-hub-project-sdk.md b/articles/ai-foundry/how-to/develop/create-hub-project-sdk.md
@@ -2,7 +2,6 @@
 title: How to create a hub using the Azure Machine Learning SDK/CLI
 titleSuffix: Azure AI Foundry
 description: This article provides instructions on how to create an Azure AI Foundry hub using the Azure Machine Learning SDK and Azure CLI extension.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom: build-2024, devx-track-azurecli
 ms.topic: how-to
diff --git a/articles/ai-foundry/how-to/flow-bulk-test-evaluation.md b/articles/ai-foundry/how-to/flow-bulk-test-evaluation.md
@@ -2,7 +2,6 @@
 title: Submit batch run and evaluate a flow
 titleSuffix: Azure AI Foundry
 description: Learn how to submit batch run and use built-in evaluation methods in prompt flow to evaluate how well your flow performs with a large dataset with Azure AI Foundry.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2023
@@ -161,7 +160,7 @@ In prompt flow, we provide multiple built-in evaluation methods to help you meas
 |---|---|---|---|---|---|
 | Classification Accuracy Evaluation | Accuracy | Measures the performance of a classification system by comparing its outputs to ground truth. | No | prediction, ground truth | in the range [0, 1]. |
 | QnA Relevance Scores Pairwise Evaluation | Score, win/lose | Assesses the quality of answers generated by a question answering system. It involves assigning relevance scores to each answer based on how well it matches the user question, comparing different answers to a baseline answer, and aggregating the results to produce metrics such as averaged win rates and relevance scores. | Yes | question, answer (no ground truth or context)  | Score: 0-100, win/lose: 1/0 |
-| QnA Groundedness Evaluation | Groundedness | Measures how grounded the model's predicted answers are in the input source. Even if LLM’s responses are true, if not verifiable against source, then is ungrounded.  | Yes | question, answer, context (no ground truth)  | 1 to 5, with 1 being the worst and 5 being the best. |
+| QnA Groundedness Evaluation | Groundedness | Measures how grounded the model's predicted answers are in the input source. Even if LLM's responses are true, if not verifiable against source, then is ungrounded.  | Yes | question, answer, context (no ground truth)  | 1 to 5, with 1 being the worst and 5 being the best. |
 | QnA GPT Similarity Evaluation | GPT Similarity | Measures similarity between user-provided ground truth answers and the model predicted answer using GPT Model.  | Yes | question, answer, ground truth (context not needed)  | in the range [0, 1]. |
 | QnA Relevance Evaluation | Relevance | Measures how relevant the model's predicted answers are to the questions asked.  | Yes | question, answer, context (no ground truth)  | 1 to 5, with 1 being the worst and 5 being the best. |
 | QnA Coherence Evaluation | Coherence  | Measures the quality of all sentences in a model's predicted answer and how they fit together naturally.  | Yes | question, answer (no ground truth or context)  | 1 to 5, with 1 being the worst and 5 being the best. |
diff --git a/articles/ai-foundry/how-to/prompt-flow-tools/llm-tool.md b/articles/ai-foundry/how-to/prompt-flow-tools/llm-tool.md
@@ -2,7 +2,6 @@
 title: LLM tool for flows in Azure AI Foundry portal
 titleSuffix: Azure AI Foundry
 description: This article introduces you to the large language model (LLM) tool for flows in Azure AI Foundry portal.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2023
diff --git a/articles/ai-foundry/how-to/prompt-flow-tools/prompt-tool.md b/articles/ai-foundry/how-to/prompt-flow-tools/prompt-tool.md
@@ -2,7 +2,6 @@
 title: Prompt tool for flows in Azure AI Foundry portal
 titleSuffix: Azure AI Foundry
 description: This article introduces you to the Prompt tool for flows in Azure AI Foundry portal.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2023
diff --git a/articles/ai-foundry/how-to/prompt-flow-troubleshoot.md b/articles/ai-foundry/how-to/prompt-flow-troubleshoot.md
@@ -2,7 +2,6 @@
 title: Troubleshoot guidance for prompt flow
 titleSuffix: Azure AI Foundry
 description: This article addresses frequently asked questions about prompt flow usage.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2024
diff --git a/articles/ai-foundry/how-to/use-image-models.md b/articles/ai-foundry/how-to/use-image-models.md
@@ -2,7 +2,6 @@
 title: How to use image-to-text models in the model catalog
 titleSuffix: Azure AI Foundry
 description: Learn how to use image-to-text models from the AI Foundry model catalog.
-manager: scottpolly
 author: msakande
 reviewer: frogglew
 ms.service: azure-ai-model-inference
diff --git a/articles/ai-foundry/reference/region-support.md b/articles/ai-foundry/reference/region-support.md
@@ -2,7 +2,6 @@
 title: Azure AI Foundry feature availability across clouds regions
 titleSuffix: Azure AI Foundry
 description: This article lists Azure AI Foundry feature availability across clouds regions.
-manager: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: concept-article
 ms.date: 07/30/2025
