Post-review fixes

Author: GraemeMalcolm

learn-pr/paths/create-custom-copilots-ai-studio/index.yml

@@ -11,7 +11,7 @@ metadata:
   ms.custom: [copilot-learning-hub]
 title: Develop generative AI apps in Azure
 prerequisites: |
-  Before starting this module, you should be familiar with fundamental AI concepts and services in Azure. You should also be proficient in programming with Python or Microoft C#.
+  Before starting this module, you should be familiar with fundamental AI concepts and services in Azure. You should also be proficient in programming with Python or Microsoft C#.
 summary: |
   Generative Artificial Intelligence (AI) is becoming more accessible through comprehensive development platforms like Azure AI Foundry. Learn how to build generative AI applications that use language models to chat with your users.
 iconUrl: /training/achievements/generic-badge.svg

learn-pr/wwl-data-ai/evaluate-models-azure-ai-studio/6-knowledge-check.yml

@@ -36,7 +36,7 @@ quiz:
       explanation: "Incorrect. "
   - content: "Which evaluator metric uses an AI model to judge the structure and logical flow of ideas in a response?"
     choices:
-    - content: "ACoherence"
+    - content: "Coherence"
       isCorrect: true
       explanation: "Correct. "
     - content: "F1 Score"

learn-pr/wwl-data-ai/evaluate-models-azure-ai-studio/includes/3b-automated-evaluations.md

@@ -10,5 +10,5 @@ To evaluate a model, you need a dataset of prompts and responses (and optionally
 
 Automated evaluation enables you to choose which *evaluators* you want to assess your model's responses, and which metrics those evaluators should calculate. There are evaluators that help you measure:
 
-- **AI Quality**: The quality of your model's responses are measured by using AI models to evaluate them for metrics like *coherence* and *relevance* and by using standard NLP metrics like F1 score, BLEU, METEOR, and ROUGE based on ground truth (in the form of expected response text)
+- **AI Quality**: The quality of your model's responses is measured by using AI models to evaluate them for metrics like *coherence* and *relevance* and by using standard NLP metrics like F1 score, BLEU, METEOR, and ROUGE based on ground truth (in the form of expected response text)
 - **Risk and safety**: evaluators that assess the responses for content safety issues, including violence, hate, sexual content, and content related to self-harm.

learn-pr/wwl-data-ai/evaluate-models-azure-ai-studio/includes/7-summary.md

@@ -5,4 +5,4 @@ In this module, you learned to:
 - Perform automated evaluations.
 
 > [!TIP]
-> Fr more information about evaluating models in Azure AI Foundry, see [Observability in generative AI](/azure/ai-foundry/concepts/observability).
+> For more information about evaluating models in Azure AI Foundry, see [Observability in generative AI](/azure/ai-foundry/concepts/observability).