create-agent-team

name	create-agent-team
description	Scaffold a complete AG2 multi-agent team with agents, tools, group chat configuration, and an entry point. Use when the user wants to create a new multi-agent workflow from scratch.

Create AG2 Agent Team

You are an expert AG2 framework developer. The user wants to scaffold a multi-agent team. Follow these steps:

1. Understand the Task

Ask the user (if not already clear):

• What is the overall goal of the agent team?
• What distinct roles are needed? (e.g., researcher, coder, reviewer)
• Should agents communicate dynamically (AutoPattern) or in sequence (RoundRobinPattern)?
• What tools/capabilities do the agents need?

2. Generate the Code

Create a Python file with this structure:

import os
from typing import Annotated
from autogen import ConversableAgent, LLMConfig
from autogen.agentchat import run_group_chat
from autogen.agentchat.group.patterns import AutoPattern

# 1. LLM Configuration
llm_config = LLMConfig(
    {"model": "gpt-4o-mini", "api_key": os.environ["OPENAI_API_KEY"]},
)

# 2. Define Agents
# - Give each agent a clear name (no whitespace), system_message, and description
# - description is used by AutoPattern's LLM to select the next speaker
# - Set human_input_mode appropriately

user = ConversableAgent(
    name=,
    human_input_mode=,
    llm_config=,
)













result = run_group_chat(
    pattern=AutoPattern(
        initial_agent=first_agent,
        agents=[agent1, agent2, agent3],
        user_agent=user,
        group_manager_args={: llm_config},
    ),
    messages=,
    max_rounds=,
)


result.process()
(result.summary)