Merge pull request #3921 from minthigpen/patch-6

Update evaluation-approach-gen-ai.md

Author: prmerger-automator[bot]

articles/ai-foundry/concepts/evaluation-approach-gen-ai.md

@@ -57,17 +57,17 @@ The pre-production stage acts as a final quality check, reducing the risk of dep
 
 - Bring your own data: You can evaluate your AI applications in pre-production using your own evaluation data with Azure AI Foundry or [Azure AI Evaluation SDK’s](../how-to/develop/evaluate-sdk.md) supported evaluators, including [generation quality, safety,](./evaluation-metrics-built-in.md) or [custom evaluators](../how-to/develop/evaluate-sdk.md#custom-evaluators), and [view results via the Azure AI Foundry portal](../how-to/evaluate-results.md).
 - Simulators and AI red teaming agent (preview): If you don’t have evaluation data (test data), Azure AI [Evaluation SDK’s simulators](..//how-to/develop/simulator-interaction-data.md) can help by generating topic-related or adversarial queries. These simulators test the model’s response to situation-appropriate or attack-like queries (edge cases).
-    - The [adversarial simulator](../how-to/develop/simulator-interaction-data.md#generate-adversarial-simulations-for-safety-evaluation) injects queries that mimic potential safety risks or security attacks such as or attempt jailbreaks, helping identify limitations and preparing the model for unexpected conditions.  
+    - [Adversarial simulators](../how-to/develop/simulator-interaction-data.md#generate-adversarial-simulations-for-safety-evaluation) injects static queries that mimic potential safety risks or security attacks such as or attempt jailbreaks, helping identify limitations and preparing the model for unexpected conditions.  
     - [Context-appropriate simulators](../how-to/develop/simulator-interaction-data.md#generate-synthetic-data-and-simulate-non-adversarial-tasks) generate typical, relevant conversations you’d expect from users to test quality of responses. With context-appropriate simulators you can assess metrics such as groundedness, relevance, coherence, and fluency of generated responses.
-    - [AI red teaming agent](../how-to/develop/run-scans-ai-red-teaming-agent.md) (preview) simulates adversarial attacks against your proactively stress-test models and applications against broad range of safety and security attacks using Microsoft’s open framework for Python Risk Identification Tool or [PyRIT](https://github.com/Azure/PyRIT). Automated scans using the AI red teaming agent enhances pre-production risk assessment by systematically testing AI applications for vulnerabilities. This process involves simulated attack scenarios to identify weaknesses in model responses before real-world deployment. By running AI red teaming scans, you can detect and mitigate potential security risks before deployment. This tool is recommended to be used in conjunction with human-in-the-loop processes such as conventional AI red teaming probing to help accelerate risk identification and aid in the assessment by a human expert.
+    - [AI red teaming agent](../how-to/develop/run-scans-ai-red-teaming-agent.md) (preview) simulates complex adversarial attacks against your AI system using a broad range of safety and security attacks using Microsoft’s open framework for Python Risk Identification Tool or [PyRIT](https://github.com/Azure/PyRIT). Automated scans using the AI red teaming agent enhances pre-production risk assessment by systematically testing AI applications for risks. This process involves simulated attack scenarios to identify weaknesses in model responses before real-world deployment. By running AI red teaming scans, you can detect and mitigate potential safety issues before deployment. This tool is recommended to be used in conjunction with human-in-the-loop processes such as conventional AI red teaming probing to help accelerate risk identification and aid in the assessment by a human expert.
 
-Alternatively, you can also use [Azure AI Foundry’s evaluation widget](../how-to/evaluate-generative-ai-app.md) for testing your generative AI applications.  
+Alternatively, you can also use [Azure AI Foundry portal's evaluation widget](../how-to/evaluate-generative-ai-app.md) for testing your generative AI applications.  
 
 Once satisfactory results are achieved, the AI application can be deployed to production.
 
 ## Post-production monitoring
 
-After deployment, the AI application enters the post-production evaluation phase, also known as online evaluation or monitoring. At this stage, the model is embedded within a real-world product and responds to actual user queries. Monitoring ensures that the model continues to behave as expected and adapts to any changes in user behavior or content.
+After deployment, the AI application enters the post-production evaluation phase, also known as online evaluation or monitoring. At this stage, the model is embedded within a real-world product and responds to actual user queries in production. Monitoring ensures that the model continues to behave as expected and adapts to any changes in user behavior or content.
 
 - **Ongoing performance tracking**: Regularly measuring AI application’s response using key metrics to ensure consistent output quality.
 - **Incident response**: Quickly responding to any harmful, unfair, or inappropriate outputs that might arise during real-world use.