Convert python applications into AutoGen studio prototypes (and vice versa)?

[zhuohanl]

I am a new starter of AutoGen and I am playing up with both:

1. Using AutoGen library to create multi-agent application in Python
2. Prototyping multi-agent application in AutoGen Studio

I am wondering, is there a way to enable these two to work together?

For one direction, if I have created an app.py using AutoGen like below, is this team/agent available to be further used in AutoGen Studio?

# pip install -U autogen-agentchat autogen-ext[openai,web-surfer]
# playwright install
import asyncio
from autogen_agentchat.agents import AssistantAgent, UserProxyAgent
from autogen_agentchat.conditions import TextMentionTermination
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.agents.web_surfer import MultimodalWebSurfer

async def main() -> None:
    model_client = OpenAIChatCompletionClient(model="gpt-4o")
    assistant = AssistantAgent("assistant", model_client)
    web_surfer = MultimodalWebSurfer("web_surfer", model_client)
    user_proxy = UserProxyAgent("user_proxy")
    termination = TextMentionTermination("exit") # Type 'exit' to end the conversation.
    team = RoundRobinGroupChat([web_surfer, assistant, user_proxy], termination_condition=termination)
    await Console(team.run_stream(task="Find information about AutoGen and write a short summary."))

asyncio.run(main())

For the reverse direction (from studio to python), I know this is achievable by downloading its specification and importing in a python application using the TeamManager class:
https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/faq.html#q-can-i-export-my-agent-workflows-for-use-in-a-python-app