Merge pull request #49858 from buzahid/sk-agents-updates

Modules/M05-orchestrate-sk-multi-agent-solution Added unit, updated content

Author: JamesJBarnett

learn-pr/wwl-data-ai/.openpublishing.redirection.wwl-data-ai.json

@@ -5020,6 +5020,26 @@
     {
       "source_path_from_root": "/learn-pr/wwl-data-ai/get-started-ai-fundamentals/8b-knowledge-check.yml",
       "redirect_url": "/training/modules/get-started-ai-fundamentals/8-knowledge-check"
+    },
+    {
+      "source_path_from_root": "/learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/3-design-agent-selection-strategy.yml",
+      "redirect_url": "/training/modules/orchestrate-semantic-kernel-multi-agent-solution/4-design-agent-selection-strategy"
+    },
+    {
+      "source_path_from_root": "/learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/4-define-chat-termination-strategy.yml",
+      "redirect_url": "/training/modules/orchestrate-semantic-kernel-multi-agent-solution/5-define-chat-termination-strategy"
+    },
+    {
+      "source_path_from_root": "/learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/5-exercise.yml",
+      "redirect_url": "/training/modules/orchestrate-semantic-kernel-multi-agent-solution/6-exercise"
+    },
+    {
+      "source_path_from_root": "/learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/6-knowledge-check.yml",
+      "redirect_url": "/training/modules/orchestrate-semantic-kernel-multi-agent-solution/7-knowledge-check"
+    },
+    {
+      "source_path_from_root": "/learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/7-summary.yml",
+      "redirect_url": "/training/modules/orchestrate-semantic-kernel-multi-agent-solution/8-summary"
     }
   ]
 }

learn-pr/wwl-data-ai/develop-ai-agent-with-semantic-kernel/6-knowledge-check.yml

@@ -12,17 +12,17 @@ durationInMinutes: 3
 content: |
 quiz:
   questions:
-  - content: "What is the main purpose of the AzureAIAgent class in Semantic Kernel?"
+  - content: "What are the key steps to create an AzureAIAgent?"  
     choices:  
-      - content: "To provide a low-level interface for directly managing AI models"  
+      - content: "Initialize the agent by defining an LLM model in the AzureAIAgentThread constructor."  
         isCorrect: false  
-        explanation: "Incorrect. The AzureAIAgent class is built on top of Azure AI Agent Service and streamlines its features rather than providing a low-level interface."  
-      - content: "To simplify the use of Azure AI Agent Service by abstracting complex operations"  
+        explanation: "Incorrect. The agent definition specifies the model, not the thread constructor." 
+      - content: "Create an Azure AI agents client, create an agent definition, and instantiate the agent."  
         isCorrect: true  
-        explanation: "Correct. The AzureAIAgent class is designed to streamline the usage of Azure AI Agent Service, reducing the complexity of setting up and managing AI agents."  
-      - content: "To replace the need for prompt templates in AI workflows"  
+        explanation: "Correct. These steps ensure that the agent is correctly defined and can interact with Azure AI Foundry services."  
+      - content: "Deploy a custom AI model before creating an AzureAIAgentSettings object."  
         isCorrect: false  
-        explanation: "Incorrect. AzureAIAgent enhances agent interactions but doesn't replace prompt templates, which are useful for defining structured AI behavior."  
+        explanation: "Incorrect. AzureAIAgent does not require deploying a custom AI model before setup."   
   - content: "Which component in the Agent Framework manages conversation state and stores messages?"  
     choices:  
       - content: "Agent threads"  

learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/3-create-agent-group-chat.yml

@@ -0,0 +1,13 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.orchestrate-sk-multi-agent-solution.create-agent-group-chat
+title: Create an agent group chat
+metadata:
+  title: Create an agent group chat
+  description: Learn how to create an agent group chat for multi-agent collaboration.
+  author: buzahid
+  ms.author: buzahid
+  ms.date: 03/14/2025
+  ms.topic: unit
+durationInMinutes: 6
+content: |
+  [!include[](includes/3-create-agent-group-chat.md)]

learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/3-design-agent-selection-strategy.yml renamed to learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/4-design-agent-selection-strategy.yml

@@ -10,4 +10,4 @@ metadata:
   ms.topic: unit
 durationInMinutes: 1
 content: |
-  [!include[](includes/3-design-agent-selection-strategy.md)]
+  [!include[](includes/4-design-agent-selection-strategy.md)]

learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/4-define-chat-termination-strategy.yml renamed to learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/5-define-chat-termination-strategy.yml

@@ -10,4 +10,4 @@ metadata:
   ms.topic: unit
 durationInMinutes: 6
 content: |
-  [!include[](includes/4-define-chat-termination-strategy.md)]
+  [!include[](includes/5-define-chat-termination-strategy.md)]

learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/5-exercise.yml renamed to learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/6-exercise.yml

@@ -10,4 +10,4 @@ metadata:
   ms.topic: unit
 durationInMinutes: 30
 content: |
-  [!include[](includes/5-exercise.md)]
+  [!include[](includes/6-exercise.md)]

learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/6-knowledge-check.yml renamed to learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/7-knowledge-check.yml

@@ -1,8 +1,8 @@
 ### YamlMime:ModuleUnit
 uid: learn.wwl.orchestrate-sk-multi-agent-solution.knowledge-check
-title: Module assessment
+title: Knowledge check
 metadata:
-  title: Module assessment
+  title: Knowledge check
   description: This unit contains a knowledge check which can help learners reinforce their understanding of the material.
   author: buzahid
   ms.author: buzahid
@@ -12,25 +12,25 @@ durationInMinutes: 3
 content: |
 quiz:
   questions:
-  - content: "Which of the following options best describes an agent in the Semantic Kernel Agent Framework?" 
-    choices:
-      - content: "A human-controlled interface for interacting with AI models" 
-        isCorrect: false 
-        explanation: "Incorrect. Agents in the framework aren't human-controlled; they're autonomous systems designed to process input and complete tasks."
-      - content: "A storage system used to manage user data" 
-        isCorrect: false 
-        explanation: "Incorrect. Agents don't function as data storage systems; they perform tasks based on user interaction and intent."
-      - content: "An autonomous system that interacts with users and performs specific tasks based on user input and intent." 
-        isCorrect: true 
-        explanation: "Correct. In the Semantic Kernel Agent Framework, agents are autonomous systems that interact with users, interpret input, and perform tasks tailored to the user's needs."
-  - content: "How does the Semantic Kernel Agent Framework select the right agent for a task?" 
+  - content: "Which statement best describes AgentGroupChat in the Semantic Kernel AgentChat framework?"  
+    choices:  
+      - content: "It only supports interactions between agents of the same type."  
+        isCorrect: false  
+        explanation: "Incorrect. AgentGroupChat allows agents of different types, such as ChatCompletionAgent and OpenAIAssistantAgent, to work together."  
+      - content: "It is an abstract class that must be subclassed to enable multi-agent interactions."  
+        isCorrect: false  
+        explanation: "Incorrect. AgentGroupChat is a concrete implementation of AgentChat, not an abstract class."  
+      - content: "It enables interaction between multiple agents and uses strategy-based approaches to manage conversation dynamics."  
+        isCorrect: true  
+        explanation: "Correct. AgentGroupChat allows multiple agents to collaborate using strategy-based conversation management."  
+  - content: "In an agent group chat, how does the Semantic Kernel Agent Framework select the right agent for a task?" 
     choices:  
       - content: "By random selection" 
         isCorrect: false 
         explanation: "Incorrect. Agent selection isn't random; it's based on analyzing user intent and routing according to specific rules."
-      - content: "Based on the user's intent and predefined rules" 
+      - content: "Using the specified selection strategy" 
         isCorrect: true 
-        explanation: "Correct. The framework uses intent recognition and predefined rules to route queries to the most relevant agent."
+        explanation: "Correct. The framework uses the defined selection strategy to determin which agent should respond."
       - content: "By the agent's physical location" 
         isCorrect: false 
         explanation: "Incorrect. Agent selection isn't based on physical location but on task relevance and expertise."

learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/7-summary.yml renamed to learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/8-summary.yml

@@ -10,4 +10,4 @@ metadata:
   ms.topic: unit
 durationInMinutes: 2
 content: |
-  [!include[](includes/7-summary.md)]
+  [!include[](includes/8-summary.md)]

learn-pr/wwl-data-ai/orchestrate-semantic-kernel-multi-agent-solution/includes/3-create-agent-group-chat.md

@@ -0,0 +1,60 @@
+A key feature of the Semantic Kernel Agent Framework is its ability to facilitate interactions between multiple agents. Using `AgentGroupChat`, developers can create dynamic, multi-agent conversations where different types of agents collaborate to generate responses. 
+
+The `AgentGroupChat` class extends the AgentChat framework, providing a structured way to manage multi-agent collaboration. It offers built-in mechanisms to control conversation flow, define collaboration strategies, and support both single-turn and multi-turn interactions.
+
+To create the `AgentGroupChat`, you can initialize the chat object with a predefined set of agents. For example:
+
+```python
+# Define agents
+agent_writer = AzureAIAgent(...)
+agent_reviewer = AzureAIAgent(...)
+
+# Create chat with participating agents
+chat = AgentGroupChat(agents=[agent_writer, agent_reviewer])
+```
+
+Or you can start with an empty chat and add agents dynamically. For example:
+
+```python
+# Create an empty chat
+chat = AgentGroupChat()
+
+# Add agents to an existing chat
+chat.add_agent(agent=agent_writer)
+chat.add_agent(agent=agent_reviewer)
+```
+
+## Add messages to the chat
+
+Once your chat is created, you can create a `ChatMessageContent` object and add it to the chat thread. The `ChatMessageContent` object takes a role parameter in addition to the content. For example:
+
+```python
+chat_message = ChatMessageContent(role=AuthorRole.USER, content="This is the message content.")
+await chat.add_chat_message(message=chat_message)
+```
+
+### Conversation Modes in AgentGroupChat
+
+Agent group chats can operate in two distinct modes, depending on the conversation requirements:
+
+In **single-turn conversations**, a designated agent provides a response based on user input. 
+
+- You can invoke a response from a single-turn chat by using `AgentGroupChat.invoke` and specifying the agent that should respond. For example:
+
+        ```python
+        async for message in chat.invoke(agent)
+            # process message response(s)
+        ```
+
+In **multi-turn conversations**, multiple agents take turns responding, continuing the conversation until a termination condition is met.
+
+- Agent responses are returned asynchronously as they are generated, allowing the conversation to unfold in real-time.
+
+- You can invoke a response from a multi-turn chat by using `AgentGroupChat.invoke`. For example:
+
+        ```python
+        async for message in chat.invoke()
+            # process message response(s)
+        ```
+
+Both modes allow agents to collaborate by building on each other's responses, resulting in dynamic, intelligent interactions.