refactor

Author: alexwolfmsft

docs/ai/quickstarts/includes/connect-prompt/semantic-kernel.md

@@ -25,6 +25,7 @@
     ```bash
     code .
     ```
+
 [!INCLUDE [create-ai-service](../create-ai-service.md)]
 
 ## Add the app code
@@ -54,4 +55,4 @@ The app uses the [`Microsoft.SemanticKernel`](https://www.nuget.org/packages/Mic
 
     :::code language="csharp" source="../../snippets/prompt-completion/semantic-kernel/openai/program.cs" range="22-24":::
 
-    Customize the text content of the `benefits.md` file or the length of the summary to see the differences in the responses.
+    Customize the text content of the `benefits.md` file or the length of the summary to see the differences in the responses.

docs/ai/quickstarts/quickstart-openai-summarize-text.md

@@ -12,45 +12,86 @@ zone_pivot_groups: dotnet-ai-library
 
 # Connect to and prompt an AI model using .NET
 
-:::zone target="docs" pivot="microsoft-extensions-ai"
 
 In this quickstart, learn how to create a .NET console chat app to connect to and prompt an OpenAI or Azure OpenAI model. The app uses the [`Microsoft.Extensions.AI`](https://www.nuget.org/packages/Microsoft.Extensions.AI) library so you can write code using AI abstractions rather than a specific SDK. AI abstractions enable you to change the underlying AI model with minimal code changes.
 
+## Prerequisites
+
+:::zone target="docs" pivot="openai"
+
+[!INCLUDE [azure-openai-prereqs](includes/prerequisites-azure-openai.md)]
+
 :::zone-end
 
-:::zone target="docs" pivot="semantic-kernel"
+:::zone target="docs" pivot="azure-openai"
 
-In this quickstart, learn how to create a .NET console chat app to connect to and prompt an OpenAI or Azure OpenAI model using [`Semantic Kernel`](/semantic-kernel/overview). Semantic Kernel is a lightweight, open-source development kit that lets you easily build AI agents and integrate the latest AI models into your C#, Python, or Java codebase. It serves as an efficient middleware that enables rapid delivery of enterprise-grade solutions.
+[!INCLUDE [openai-prereqs](includes/prerequisites-openai.md)]
 
 :::zone-end
 
-## Prerequisites
+## Clone the sample repository
 
-# [Azure OpenAI](#tab/azure-openai)
+[!INCLUDE [clone-sample-repo](includes/clone-sample-repo.md)]
 
-[!INCLUDE [azure-openai-prereqs](includes/prerequisites-azure-openai.md)]
+## Create the app
 
-# [OpenAI](#tab/openai)
+1. In an empty directory on your computer, use the `dotnet new` command to create a new console app:
 
-[!INCLUDE [openai-prereqs](includes/prerequisites-openai.md)]
+    ```dotnetcli
+    dotnet new console -o ExtensionsAI
+    ```
 
----
+1. Change directory into the app folder:
 
-## Clone the sample repository
+    ```dotnetcli
+    cd ExtensionsAI
+    ```
 
-[!INCLUDE [clone-sample-repo](includes/clone-sample-repo.md)]
+1. Install the required packages:
 
-:::zone target="docs" pivot="microsoft-extensions-ai"
+    ```bash
+    dotnet add package Microsoft.SemanticKernel
+    dotnet add package Microsoft.Extensions.Configuration
+    dotnet add package Microsoft.Extensions.Configuration.UserSecrets
+    ```
 
-[!INCLUDE [extensions-ai](includes/connect-prompt/extensions-ai.md)]
+1. Open the app in Visual Studio code or your editor of choice
 
-:::zone-end
+    ```bash
+    code .
+    ```
 
-:::zone target="docs" pivot="semantic-kernel"
+[!INCLUDE [create-ai-service](../create-ai-service.md)]
 
-[!INCLUDE [semantic-kernel](includes/connect-prompt/semantic-kernel.md)]
+## Add the app code
 
-:::zone-end
+The app uses the [`Microsoft.SemanticKernel`](https://www.nuget.org/packages/Microsoft.SemanticKernel) package to send and receive requests to the OpenAI service.
+
+1. In the **Program.cs** file, add the following code to connect and authenticate to the AI model.
+
+    <!-- markdownlint-disable MD023 -->
+    # [Azure OpenAI](#tab/azure-openai)
+
+    :::code language="csharp" source="./snippets/prompt-completion/semantic-kernel/azure-openai/program.cs" range="6-14":::
+
+    > [!NOTE]
+    > `DefaultAzureCredential` searches for credentials from  your local tooling. If you are not using the `azd` template to provision the Azure OpenAI resource, you'll need to assign the `Azure AI Developer` role to the account you used to sign-in to Visual Studio or the Azure CLI.
+
+    # [OpenAI](#tab/openai)
+
+    :::code language="csharp" source="./snippets/prompt-completion/semantic-kernel/openai/program.cs" range="5-13":::
+
+    ---
+
+1. Read the `benefits.md` file content and use it to create a `prompt` for model. The prompt instructs the model to summarize the file text content.
+
+    :::code language="csharp" source="./snippets/prompt-completion/semantic-kernel/openai/program.cs" range="15-20":::
+
+1. Call the `InvokePromptAsync` function to send the `prompt` to the model to generate a response.
+
+    :::code language="csharp" source="./snippets/prompt-completion/semantic-kernel/openai/program.cs" range="22-24":::
+
+    Customize the text content of the `benefits.md` file or the length of the summary to see the differences in the responses.
 
 ## Clean up resources