Microsoft Agent Framework Workflows Orchestrations - Group Chat

Set Up the Azure OpenAI Client

using System;
using System.Collections.Generic;
using System.Threading.Tasks;
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI.Workflows;
using Microsoft.Extensions.AI;
using Microsoft.Agents.AI;

// Set up the Azure OpenAI client
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ??
    throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
var client = new AzureOpenAIClient(new Uri(endpoint), new AzureCliCredential())
    .GetChatClient(deploymentName)
    .AsIChatClient();

Define Your Agents

Create specialized agents for different roles in the group conversation:

// Create a copywriter agent
ChatClientAgent writer = new(client,
    "You are a creative copywriter. Generate catchy slogans and marketing copy. Be concise and impactful.",
    "CopyWriter",
    "A creative copywriter agent");

// Create a reviewer agent
ChatClientAgent reviewer = new(client,
    "You are a marketing reviewer. Evaluate slogans for clarity, impact, and brand alignment. " +
    "Provide constructive feedback or approval.",
    "Reviewer",
    "A marketing review agent");

Configure Group Chat with Round-Robin Orchestrator

Build the group chat workflow using AgentWorkflowBuilder:

// Build group chat with round-robin speaker selection
// The manager factory receives the list of agents and returns a configured manager
var workflow = AgentWorkflowBuilder
    .CreateGroupChatBuilderWith(agents =>
        new RoundRobinGroupChatManager(agents)
        {
            MaximumIterationCount = 5  // Maximum number of turns
        })
    .AddParticipants(writer, reviewer)
    .Build();

Run the Group Chat Workflow

Execute the workflow and observe the iterative conversation:

// Start the group chat
var messages = new List<ChatMessage> {
    new(ChatRole.User, "Create a slogan for an eco-friendly electric vehicle.")
};

StreamingRun run = await InProcessExecution.StreamAsync(workflow, messages);
await run.TrySendMessageAsync(new TurnToken(emitEvents: true));

await foreach (WorkflowEvent evt in run.WatchStreamAsync().ConfigureAwait(false))
{
    if (evt is AgentResponseUpdateEvent update)
    {
        // Process streaming agent responses
        AgentResponse response = update.AsResponse();
        foreach (ChatMessage message in response.Messages)
        {
            Console.WriteLine($"[{update.ExecutorId}]: {message.Text}");
        }
    }
    else if (evt is WorkflowOutputEvent output)
    {
        // Workflow completed
        var conversationHistory = output.As<List<ChatMessage>>();
        Console.WriteLine("\n=== Final Conversation ===");
        foreach (var message in conversationHistory)
        {
            Console.WriteLine($"{message.AuthorName}: {message.Text}");
        }
        break;
    }
}

Sample Interaction

[CopyWriter]: "Green Dreams, Zero Emissions" - Drive the future with style and sustainability.

[Reviewer]: The slogan is good, but "Green Dreams" might be a bit abstract. Consider something
more direct like "Pure Power, Zero Impact" to emphasize both performance and environmental benefit.

[CopyWriter]: "Pure Power, Zero Impact" - Experience electric excellence without compromise.

[Reviewer]: Excellent! This slogan is clear, impactful, and directly communicates the key benefits.
The tagline reinforces the message perfectly. Approved for use.

[CopyWriter]: Thank you! The final slogan is: "Pure Power, Zero Impact" - Experience electric
excellence without compromise.

Set Up the Chat Client

from agent_framework.azure import AzureOpenAIChatClient
from azure.identity import AzureCliCredential

# Initialize the Azure OpenAI chat client
chat_client = AzureOpenAIChatClient(credential=AzureCliCredential())

Define Your Agents

Create specialized agents with distinct roles:

from agent_framework import ChatAgent

# Create a researcher agent
researcher = ChatAgent(
    name="Researcher",
    description="Collects relevant background information.",
    instructions="Gather concise facts that help answer the question. Be brief and factual.",
    chat_client=chat_client,
)

# Create a writer agent
writer = ChatAgent(
    name="Writer",
    description="Synthesizes polished answers using gathered information.",
    instructions="Compose clear, structured answers using any notes provided. Be comprehensive.",
    chat_client=chat_client,
)

Configure Group Chat with Simple Selector

Build a group chat with custom speaker selection logic:

from agent_framework import GroupChatBuilder, GroupChatState

def round_robin_selector(state: GroupChatState) -> str:
    """A round-robin selector function that picks the next speaker based on the current round index."""

    participant_names = list(state.participants.keys())
    return participant_names[state.current_round % len(participant_names)]


# Build the group chat workflow
workflow = (
    GroupChatBuilder()
    .with_select_speaker_func(round_robin_selector)
    .participants([researcher, writer])
    # Terminate after 4 turns (researcher → writer → researcher → writer)
    .with_termination_condition(lambda conversation: len(conversation) >= 4)
    .build()
)

Configure Group Chat with Agent-Based Orchestrator

Alternatively, use an agent-based orchestrator for intelligent speaker selection. The orchestrator is a full ChatAgent with access to tools, context, and observability:

# Create orchestrator agent for speaker selection
orchestrator_agent = ChatAgent(
    name="Orchestrator",
    description="Coordinates multi-agent collaboration by selecting speakers",
    instructions="""
You coordinate a team conversation to solve the user's task.

Guidelines:
- Start with Researcher to gather information
- Then have Writer synthesize the final answer
- Only finish after both have contributed meaningfully
""",
    chat_client=chat_client,
)

# Build group chat with agent-based orchestrator
workflow = (
    GroupChatBuilder()
    .with_agent_orchestrator(orchestrator_agent)
    # Set a hard termination condition: stop after 4 assistant messages
    # The agent orchestrator will intelligently decide when to end before this limit but just in case
    .with_termination_condition(lambda messages: sum(1 for msg in messages if msg.role == Role.ASSISTANT) >= 4)
    .participants([researcher, writer])
    .build()
)

Run the Group Chat Workflow

Execute the workflow and process events:

from typing import cast
from agent_framework import AgentResponseUpdateEvent, Role, WorkflowOutputEvent

task = "What are the key benefits of async/await in Python?"

print(f"Task: {task}\n")
print("=" * 80)

final_conversation: list[ChatMessage] = []
last_executor_id: str | None = None

# Run the workflow
async for event in workflow.run_stream(task):
    if isinstance(event, AgentResponseUpdateEvent):
        # Print streaming agent updates
        eid = event.executor_id
        if eid != last_executor_id:
            if last_executor_id is not None:
                print()
            print(f"[{eid}]:", end=" ", flush=True)
            last_executor_id = eid
        print(event.data, end="", flush=True)
    elif isinstance(event, WorkflowOutputEvent):
        # Workflow completed - data is a list of ChatMessage
        final_conversation = cast(list[ChatMessage], event.data)

if final_conversation:
    print("\n\n" + "=" * 80)
    print("Final Conversation:")
    for msg in final_conversation:
        author = getattr(msg, "author_name", "Unknown")
        text = getattr(msg, "text", str(msg))
        print(f"\n[{author}]\n{text}")
        print("-" * 80)

print("\nWorkflow completed.")

Sample Interaction

Task: What are the key benefits of async/await in Python?

================================================================================

[Researcher]: Async/await in Python provides non-blocking I/O operations, enabling
concurrent execution without threading overhead. Key benefits include improved
performance for I/O-bound tasks, better resource utilization, and simplified
concurrent code structure using native coroutines.

[Writer]: The key benefits of async/await in Python are:

1. **Non-blocking Operations**: Allows I/O operations to run concurrently without
   blocking the main thread, significantly improving performance for network
   requests, file I/O, and database queries.

2. **Resource Efficiency**: Avoids the overhead of thread creation and context
   switching, making it more memory-efficient than traditional threading.

3. **Simplified Concurrency**: Provides a clean, synchronous-looking syntax for
   asynchronous code, making concurrent programs easier to write and maintain.

4. **Scalability**: Enables handling thousands of concurrent connections with
   minimal resource consumption, ideal for high-performance web servers and APIs.

--------------------------------------------------------------------------------

Workflow completed.

• Centralized Manager: Group chat uses a manager to coordinate speaker selection and flow
• AgentWorkflowBuilder.CreateGroupChatBuilderWith(): Creates workflows with a manager factory function
• RoundRobinGroupChatManager: Built-in manager that alternates speakers in round-robin fashion
• MaximumIterationCount: Controls the maximum number of agent turns before termination
• Custom Managers: Extend RoundRobinGroupChatManager or implement custom logic
• Iterative Refinement: Agents review and improve each other's contributions
• Shared Context: All participants see the full conversation history

• Flexible Orchestrator Strategies: Choose between simple selectors, agent-based orchestrators, or custom logic
• GroupChatBuilder: Creates workflows with configurable speaker selection
• with_select_speaker_func(): Define custom Python functions for speaker selection
• with_agent_orchestrator(): Use an agent-based orchestrator for intelligent speaker coordination
• GroupChatState: Provides conversation state for selection decisions
• Iterative Collaboration: Agents build upon each other's contributions
• Event Streaming: Process AgentResponseUpdateEvent and WorkflowOutputEvent in real-time
• list[ChatMessage] Output: All orchestrations return a list of chat messages

You can implement custom manager logic by creating a custom group chat manager:

public class ApprovalBasedManager : RoundRobinGroupChatManager
{
    private readonly string _approverName;

    public ApprovalBasedManager(IReadOnlyList<AIAgent> agents, string approverName)
        : base(agents)
    {
        _approverName = approverName;
    }

    // Override to add custom termination logic
    protected override ValueTask<bool> ShouldTerminateAsync(
        IReadOnlyList<ChatMessage> history,
        CancellationToken cancellationToken = default)
    {
        var last = history.LastOrDefault();
        bool shouldTerminate = last?.AuthorName == _approverName &&
            last.Text?.Contains("approve", StringComparison.OrdinalIgnoreCase) == true;

        return ValueTask.FromResult(shouldTerminate);
    }
}

// Use custom manager in workflow
var workflow = AgentWorkflowBuilder
    .CreateGroupChatBuilderWith(agents =>
        new ApprovalBasedManager(agents, "Reviewer")
        {
            MaximumIterationCount = 10
        })
    .AddParticipants(writer, reviewer)
    .Build();

You can implement sophisticated selection logic based on conversation state:

def smart_selector(state: GroupChatState) -> str:
    """Select speakers based on conversation content and context."""
    conversation = state.conversation

    last_message = conversation[-1] if conversation else None

    # If no messages yet, start with Researcher
    if not last_message:
        return "Researcher"

    # Check last message content
    last_text = last_message.text.lower()

    # If researcher finished gathering info, switch to writer
    if "I have finished" in last_text and last_message.author_name == "Researcher":
        return "Writer"

    # Else continue with researcher until it indicates completion
    return "Researcher"

workflow = (
    GroupChatBuilder()
    .with_select_speaker_func(smart_selector, orchestrator_name="SmartOrchestrator")
    .participants([researcher, writer])
    .build()
)