Team structured output

General
1

If two agents within a team return different schemas, I can define a schema at the Team level that is a superset of both. But how does the Team construct this combined schema—does it happen automatically?

I have defined a response_format in Team which is a superset. The agent executes correctly but doesn’t populate Team response.

from typing import Optional
from pydantic import BaseModel

class AgentOutput(BaseModel):
    name: str

class TeamOutput(BaseModel):
    agent_output: Optional[AgentOutput] = None

I’m assuming Team doesn’t know how to populate agent_output with agent response. I added it to prompt but it didnt work.

2

Hi @zzzrpagliari, thanks for reaching out and supporting Agno. I’ve shared this with the team, we’re working through all requests one by one and will get back to you soon.
If it’s urgent, please let us know. We appreciate your patience!

3

Hey @zzzrpagliari , Yes Teams can generate structured data using Pydantic models, just like individual agents. Can you checkout : Structured Output - Agno and see if we’re missing something in the config ?

4

I was asking more about agent working together. If the procuce structured output, it may be difficult for them to understand it unless they are given details in the prompt. So Perhaps should they just procude raw text and only the team returns a strcutured output?