articles-about-evaluating-apps-with-Azure-AI-Evaluation-SDK

Author: LHL407

articles/ai-foundry/how-to/develop/agent-evaluate-sdk.md

@@ -1,16 +1,18 @@
+---
 title: Agent Evaluation with the Azure AI Evaluation SDK
 titleSuffix: Azure AI Foundry
 description: This article provides instructions on how to evaluate an AI agent with the Azure AI Evaluation SDK.
 Manager: scottpolly
 ms.service: azure-ai-foundry
-ms.custom: build-2025, references_regions
+ms.custom: 
+- build-2025
+- references_regions
 ms.topic: how-to
 ms.date: 04/04/2025
 ms.reviewer: changliu2
 author:
 ms.author: lagayhar
 author: lgayhardt
-
 ---
 
 # Evaluate your AI agents locally with the Azure AI Evaluation SDK (preview)
@@ -308,7 +310,7 @@ After the URI, you'll be redirected to Foundry to view your evaluation results i
 
 With the Azure AI Evaluation SDK client library, you can seamlessly evaluate your Azure AI agents via our converter support, which enables observability and transparency into agentic workflows.
 
-## Evaluate other agents
+## <a name = "evaluating-other-agents"></a> Evaluate other agents
 
 If you're using agents outside of Azure AI Foundry Agent Service, you can still evaluate them by preparing the right data for the evaluators of your choice.
 

articles/ai-foundry/how-to/develop/cloud-evaluation.md

@@ -13,6 +13,7 @@ ms.reviewer: changliu2
 ms.author: lagayhar
 author: lgayhardt
 ---
+
 # Run evaluations in the cloud by using the Azure AI Foundry SDK (preview)
 
 [!INCLUDE [feature-preview](../../includes/feature-preview.md)]
@@ -73,7 +74,7 @@ project_client = AIProjectClient(
 )
 ```
 
-## Upload evaluation data
+## <a name = "uploading-evaluation-data"></a> Upload evaluation data
 
 ```python
 # Upload a local JSONL file (skip if you already have a Dataset registered)

articles/ai-foundry/how-to/develop/simulator-interaction-data.md

@@ -403,6 +403,8 @@ The `AdversarialSimulator` supports a range of scenarios, hosted in the service,
 
 ### Simulate jailbreak attacks
 
+## <a name = "simulating-jailbreak-attacks"></a> Simulate Jailbreak Attacks
+
 Evaluating vulnerability towards the following types of jailbreak attacks is supported:
 
 - **Direct attack jailbreak**: This type of attack, also known as a user prompt injected attack (UPIA), injects prompts in the user role turn of conversations or queries to generative AI applications.

articles/ai-foundry/how-to/evaluate-generative-ai-app.md

@@ -5,7 +5,7 @@ description: Evaluate your generative AI models and applications by using Azure
 manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom: ignite-2023, references_regions, build-2024, ignite-2024
-ms.topic: how-toi-
+ms.topic: how-to
 ms.date: 05/19/2025
 ms.reviewer: mithigpe
 ms.author: lagayhar