Merge pull request #40 from MicrosoftDocs/repo_sync_working_branch

Resolve syncing conflicts from repo_sync_working_branch to main

Author: jasonjoh

.acrolinx-config.edn

@@ -1,5 +1,5 @@
 {
-  :allowed-branchname-matches ["main" "live"]
+  :allowed-branchname-matches ["main" "live" "build.*"]
   :allowed-filename-matches ["(?i)(?!(^.*/p|^p)osts-api\\.yml$|(^.*/r|^r)eadme\\.md$)^docs/.*$"] ;; Can be overridden in repo-specific edn file. This is an allow list that identifies which folders contain the files Acrolinx will check. Separate multiple folders as follows ["folder/" "folder2"]
 
   :use-gh-statuses true

.vscode/settings.json

@@ -7,5 +7,8 @@
   ],
   "yaml.schemas": {
     "https://json.schemastore.org/github-issue-config.json": ".github/ISSUE_TEMPLATE/config.yml"
-  }
+  },
+  "cSpell.words": [
+    "preconfigured"
+  ]
 }

docs/TOC.yml

@@ -95,7 +95,14 @@
     - name: Write instructions for agents with API plugins
       href: instructions-api-plugins.md
     - name: Add capabilities and knowledge sources
-      href: add-agent-capabilities.md
+      expanded: false
+      items:
+        - name: Code interpreter
+          href: code-interpreter.md
+        - name: Image generator
+          href: image-generator.md          
+        - name: Knowledge sources
+          href: knowledge-sources.md    
     - name: Optimize SharePoint content retrieval
       href: optimize-sharepoint-content.md
     - name: Document interaction
@@ -104,7 +111,7 @@
       href: localize-agents.md
     - name: Test and debug agents
       href: debugging-copilot-agent.md
-    - name: RAI validation
+    - name: Responsible AI validation
       href: rai-validation.md
   - name: Build a custom engine agent
     expanded: false

docs/add-agent-capabilities.md

@@ -0,0 +1,69 @@
+---
+title: Code Interpreter Capability for Declarative Agents for Microsoft 365 Copilot.
+description: Learn about the code interpreter capability and how to add it to your declarative agents.
+author: kmkoenen   
+ms.author: v-koenenkaty
+ms.topic: concept-article
+ms.localizationpriority: medium
+ms.date: 5/09/2025
+---
+
+# Add the code interpreter capability to your agent
+
+You can enhance the user experience of your declarative agent for Microsoft 365 Copilot by adding the code interpreter capability. The [**capabilities** element](/microsoft-365-copilot/extensibility/declarative-agent-manifest-1.3#capabilities-object) in the manifest reference and the **Capabilities** section in the Copilot Studio agent builder provide several options for you to unlock features for your users. This article describes the code interpreter capability and how to add it to your declarative agents.
+
+Code interpreter is an advanced tool designed to solve complex tasks via Python code. It uses the reasoning model to write and run code, enabling users to solve complex math problems, analyze data, generate visualizations, and more. After the code runs, code interpreter outputs the results and generated code. It can also produce images or files based on the scenario, and accepts files as input for modifications and analysis.
+
+The code interpreter capability is available to Copilot Chat users with no metered usage or Microsoft 365 Copilot license.
+
+> [!NOTE]
+> Support for in-context agents that have code interpreter enabled varies by host.
+
+## Code interpreter examples
+
+### Data graphing
+
+The user prompt "Graph the first 20 numbers in a Fibonacci sequence" generates both a line graph and, when the user clicks the `</> Code` button, provides the corresponding Python code.
+
+The following images show examples of the results of a data graphing request.
+
+:::image type="content" source="assets/images/code-interpreter-python-1.png" alt-text="Graph response to the user prompt":::
+
+:::image type="content" source="assets/images/code-interpreter-python-2.png" alt-text="Python code response to the user prompt":::
+
+### Data visualization
+
+The user prompt "Create a word cloud of top pet names" generates a word cloud that includes the top names, as shown in the following example.
+
+:::image type="content" source="assets/images/code-interpreter-pet-word-cloud.png" alt-text="Word cloud response to the user prompt":::
+
+### Enable code interpreter
+
+**Agents Toolkit**
+If you're using [Agents Toolkit and Visual Studio Code](build-declarative-agents.yml) to create your agent, to enable code interpreter, add the `CodeInterpreter` value to the **capabilities** property in your manifest file, as shown in the following example.
+
+> [!NOTE]
+> You must be using [version 1.2](declarative-agent-manifest-1.2.md) or later of the declarative agent manifest schema to add the `CodeInterpreter` capability.
+
+```json
+{
+  "capabilities": [
+    {
+      "name": "CodeInterpreter"
+    }
+  ]
+}
+```
+
+**Copilot Studio agent builder**
+If you're using [Copilot Studio agent builder](copilot-studio-agent-builder.md) to create your agent, on the **Configure** tab, under **Capabilities**, choose the toggle next to **Code interpreter**.
+
+:::image type="content" source="assets/images/capabilities-toggle.png" alt-text="Screenshot of the Capabilities section of the agent builder":::
+
+## Related content
+
+- [Declarative agents overview](overview-declarative-agent.md)
+- [Declarative agent manifest reference](declarative-agent-manifest-1.3.md)
+- [Add the image generator capability to your agent](image-generator.md)
+- [Add knowledge sources to your declarative agent](knowledge-sources.md)
+

docs/code-interpreter.md

@@ -14,7 +14,7 @@ This article provides information about Copilot Studio regional availability and
 
 ## Regional availability
 
-Copilot Studio agent builder is available if your [Power Platform default environment](/power-platform/admin/environments-overview#default-environment) is in any of the following countries or regions:   
+Copilot Studio agent builder is available if your [Power Platform default environment](/power-platform/admin/environments-overview#default-environment) is in any of the following countries or regions:
 
 - Asia Pacific
 - Australia

docs/copilot-studio-agent-builder-availability.md

@@ -51,7 +51,7 @@ The following table describes the fields that make up the agent.
 | **Description**     | The description helps the Large Language Model (LLM) identify and use your agent for a specific task or situation. Make it as short, precise, and simple as possible. It's also displayed in the app file for use in the app catalog. Character limit of 1,000 characters. |
 | **Instructions**    | Specific instructions to the LLM that you want to use to extend the capabilities of Microsoft 365 Copilot. They direct the behavior of the agent, including its tasks and how it completes them. If you're using the **Describe** tab, they're autogenerated for you. Character limit of 8,000 characters. For more information, see [Write effective instructions](declarative-agent-instructions.md).|
 | **Knowledge**       | You can specify up to 20 knowledge sources (including SharePoint sites, folders, and files) or Microsoft Graph connectors. For details, see the [Add knowledge sources](#add-knowledge-sources) section. |
-| **Capabilities** | You can enhance the user experience of your declarative agent by adding capabilities. For details, see [Add capabilities to your declarative agent](add-agent-capabilities.md). |
+| **Capabilities** | You can enhance the user experience of your declarative agent by adding capabilities. |
 | **Starter Prompts** | Starter prompts help other users understand commonly supported scenarios by your agent. Each starter prompt comes with a name and description. There's no minimum number of starter prompts. |
 <!-- markdownlint-enable MD033 -->
 
@@ -140,8 +140,8 @@ If at least one connector is enabled, you can add it to your agent. Your agent i
 
 In the **Capabilities** section of the **Configure** tab, you can choose to add the following capabilities to your agent:
 
-- [Code interpreter](add-agent-capabilities.md#code-interpreter) - Uses Python code to solve complex math problems, analyze data, and generate visualizations.
-- [Image generator](add-agent-capabilities.md#image-generator) - Generates images base on user prompts.
+- [Code interpreter](code-interpreter.md) - Uses Python code to solve complex math problems, analyze data, and generate visualizations.
+- [Image generator](image-generator.md) - Generates images base on user prompts.
 
 To add one or more capabilities to your agent, choose the toggle next to the capability you want to enable.
 

docs/copilot-studio-agent-builder-build.md

@@ -114,4 +114,3 @@ Enter a message, including the #extensibility tag, in the text box.
 
 - [Build a declarative agent with Visual Studio Code](/microsoft-365-copilot/extensibility/build-declarative-agents)
 - [Build agents with Copilot Studio agent builder](copilot-studio-agent-builder-build.md)
-- [Add capabilities and knowledge sources to your agent](add-agent-capabilities.md)

docs/debugging-copilot-agent.md

@@ -23,7 +23,7 @@ For example, a user is working on a job description document, and wants to add a
 
 :::image type="content" source="assets/images/declarative-agents/add-document-selection.png" alt-text="A screenshot of Copilot in Word showing the Add selection option" lightbox="assets/images/declarative-agents/add-document-selection.png":::
 
-The user selects **Add selection** then asks the agent to [generate an image](add-agent-capabilities.md#image-generator) based on the selection.
+The user selects **Add selection** then asks the agent to [generate an image](image-generator.md) based on the selection.
 
 :::image type="content" source="assets/images/declarative-agents/document-selection-prompt.png" alt-text="A screenshot of Copilot in Word showing the user prompt including the document selection" lightbox="assets/images/declarative-agents/document-selection-prompt.png":::
 

docs/declarative-agent-document-interaction.md

@@ -221,7 +221,7 @@ The connection object contains the following properties.
 
 #### Graphic art object
 
-Indicates that the declarative agent can create images and art based on the text input from the user. For more information, see [Image generator](add-agent-capabilities.md#image-generator).
+Indicates that the declarative agent can create images and art based on the text input from the user. For more information, see [Image generator](image-generator.md).
 
 The graphic art object contains the following properties.
 
@@ -231,7 +231,7 @@ The graphic art object contains the following properties.
 
 #### Code interpreter object
 
-Indicates that the declarative agent can generate and execute Python code to solve complex math problems, analyze data, generate visualizations, and more. For more information, see [Code interpreter](add-agent-capabilities.md#code-interpreter).
+Indicates that the declarative agent can generate and execute Python code to solve complex math problems, analyze data, generate visualizations, and more. For more information, see [Code interpreter](code-interpreter.md).
 
 The code interpreter object contains the following properties.
 

docs/declarative-agent-manifest-1.2.md

@@ -257,7 +257,7 @@ The connection object contains the following properties.
 
 #### Graphic art object
 
-Indicates that the declarative agent can create images and art based on the text input from the user. For more information, see [Image generator](add-agent-capabilities.md#image-generator).
+Indicates that the declarative agent can create images and art based on the text input from the user. For more information, see [Image generator](image-generator.md).
 
 The graphic art object contains the following properties.
 
@@ -267,7 +267,7 @@ The graphic art object contains the following properties.
 
 #### Code interpreter object
 
-Indicates that the declarative agent can generate and execute Python code to solve complex math problems, analyze data, generate visualizations, and more. For more information, see [Code interpreter](add-agent-capabilities.md#code-interpreter).
+Indicates that the declarative agent can generate and execute Python code to solve complex math problems, analyze data, generate visualizations, and more. For more information, see [Code interpreter](code-interpreter.md).
 
 The code interpreter object contains the following properties.
 

docs/declarative-agent-manifest-1.3.md

@@ -0,0 +1,69 @@
+---
+title: Image Generator Capability for Declarative Agents for Microsoft 365 Copilot
+description: Learn about the image generator capability and how to add it to your declarative agents.
+author: kmkoenen   
+ms.author: v-koenenkaty
+ms.topic: concept-article
+ms.localizationpriority: medium
+ms.date: 5/09/2025
+---
+
+# Add the image generator capability to your agent
+
+The image generator capability enables declarative agents for Microsoft 365 Copilot to generate images based on user prompts. Image generator uses the existing [Designer](https://designer.microsoft.com/) functionality to create visually appealing and contextually relevant graphics, and includes the following features: 
+
+- **Multiple image generation**: For each user prompt, the agent generates four images.
+- **Interactive image options**: Users can select each generated image to view it in full size. They can download, copy, or view content credentials for the full-size image. They can also select the side arrow to scroll through the four images.
+- **Image modification**: Users can follow up with subsequent prompts to modify the original images without losing context. For example, first prompt: "Create a photo of a happy puppy running around in a yard." Second prompt: "Include a tennis ball."
+- **Feedback mechanism**: Users can provide feedback on the generated images by giving a thumbs up or thumbs down. This feedback helps improve the quality of future image generations.
+- **Clipboard and sharing**: Users can copy the generated images to their clipboard to paste into other applications, or they can share the generated images directly from the interface.
+
+ The image generator capability is available to Copilot Chat users with no metered usage or Microsoft 365 Copilot license.  
+
+## Image generator examples
+
+The following examples show what users can do with the image generation capability in your agent.
+
+**User prompt**: Create an image of a serene beach at sunset with palm trees and gentle waves.
+
+The following image shows the result.
+
+:::image type="content" source="assets/images/image-gen-beach-prompt.png" alt-text="Beach image response to the user prompt":::
+
+**User prompt**: Design a flyer for a summer music festival and add a date for May 15, 2024.
+
+The following image shows the result.
+
+:::image type="content" source="assets/images/image-gen-flier-prompt.png" alt-text="Festival flyer image response to the user prompt":::
+
+## Enable image generator
+
+If you're using [Teams Toolkit and Visual Studio Code](build-declarative-agents.yml) to create your agent, to enable image generator in your agent, add the `GraphicArt` value to the **capabilities** property in your manifest file, as shown in the following example.
+
+> [!NOTE]
+> You must be using [version 1.2](declarative-agent-manifest-1.2.md) or later of the declarative agent manifest schema to add the `GraphicArt` capability.
+
+
+```json
+{
+  "capabilities": [
+    {
+      "name": "GraphicArt"
+    }
+  ]
+}
+```
+
+If you're using [Copilot Studio agent builder](copilot-studio-agent-builder.md) to create your agent, on the **Configure** tab, under **Capabilities**, choose the toggle next to **Image generator**.
+
+:::image type="content" source="assets/images/capabilities-toggle.png" alt-text="Screenshot of the Capabilities section of the agent builder":::
+
+> [!NOTE]
+> The image generator doesn't currently work in the test pane in Copilot Studio agent builder.
+
+## Related content
+
+- [Declarative agents overview](overview-declarative-agent.md)
+- [Declarative agent manifest reference](declarative-agent-manifest-1.3.md)
+- [Add the code interpreter capability to your agent](code-interpreter.md)
+- [Add knowledge sources to your declarative agent](knowledge-sources.md)

docs/image-generator.md

@@ -4,7 +4,7 @@ ms.localizationpriority: medium
 
 <!-- markdownlint-disable MD041 -->
 
-In this section, you add the [people capability](../../add-agent-capabilities.md#people-knowledge) to the declarative agent. The people capability allows you to scope your agent to answer questions about individuals in an organization.
+In this section, you add the [people capability](../../knowledge-sources.md#people-knowledge) to the declarative agent. The people capability allows you to scope your agent to answer questions about individuals in an organization.
 
 1. Open the `appPackage/declarativeAgent.json` file and add the `People` entry to the `capabilities` array.
 

docs/includes/declarative-agents-walkthrough/08-add-people.md

@@ -4,7 +4,7 @@ ms.localizationpriority: medium
 
 <!-- markdownlint-disable MD041 -->
 
-In this section, you add the [email capability](../../add-agent-capabilities.md#email-knowledge) to the declarative agent. The email capability allows you to scope your agent to use email from the user's mailbox or a shared mailbox as a knowledge source.
+In this section, you add the [email capability](../../knowledge-sources.md#email-knowledge) to the declarative agent. The email capability allows you to scope your agent to use email from the user's mailbox or a shared mailbox as a knowledge source.
 
 1. Open the `appPackage/declarativeAgent.json` file and add the `Email` entry to the `capabilities` array.
 

docs/includes/declarative-agents-walkthrough/09-add-email.md

@@ -4,7 +4,7 @@ ms.localizationpriority: medium
 
 <!-- markdownlint-disable MD041 -->
 
-In this section, you add the [image generator capability](../../add-agent-capabilities.md#image-generator) to the declarative agent.
+In this section, you add the [image generator capability](../../image-generator.md) to the declarative agent.
 
 1. Open the `appPackage/declarativeAgent.json` file and add the `GraphicArt` entry to the `capabilities` array.
 

docs/includes/declarative-agents-walkthrough/10-add-graphic-art.md

@@ -4,7 +4,7 @@ ms.localizationpriority: medium
 
 <!-- markdownlint-disable MD041 -->
 
-In this section, you add the [code interpreter capability](../../add-agent-capabilities.md#code-interpreter) to the declarative agent. Code interpreter is an advanced tool designed to solve complex tasks via Python code.
+In this section, you add the [code interpreter capability](../../code-interpreter.md) to the declarative agent. Code interpreter is an advanced tool designed to solve complex tasks via Python code.
 
 1. Open the `appPackage/declarativeAgent.json` file and add the `CodeInterpreter` entry to the `capabilities` array.