ai-agents-multi-agent-orchestr-need-to-coordinate-multiple-specialist-agents-e-g--739872a2

THEN Wrap each specialist agent using `AgentTool` from `autogen_agentchat.tools`. Create a main `AssistantAgent` that includes these tools. The main agent can then delegate tasks to specialists based on the query.

import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.tools import AgentTool
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
async def main():
    model_client = OpenAIChatCompletionClient(model="gpt-4.1")
    math_agent = AssistantAgent("math_expert", model_client=model_client, system_message="You are a math expert.")
    math_agent_tool = AgentTool(math_agent, return_value_as_last_message=True)
    chemistry_agent = AssistantAgent("chemistry_expert", model_client=model_client, system_message="You are a chemistry expert.")
    chemistry_agent_tool = AgentTool(chemistry_agent, return_value_as_last_message=True)
    agent = AssistantAgent("assistant", model_client=model_client, tools=[math_agent_tool, chemistry_agent_tool], max_tool_iterations=10)
    await Console(agent.run_stream(task="What is the integral of x^2?"))
asyncio.run(main())