Structured Input for Teams

Validate input data for teams with Pydantic models.

Pass structured data to teams using Pydantic models. You can either pass a model instance directly or set input_schema to validate dictionaries automatically.

Input Format Types

Use Case	Input Format
You're building the input in code	Use Pydantic Model instance
Input comes from external sources (APIs, files, user input)	Use input_schema

Using Pydantic Models

Pass a Pydantic model instance to input:

from pydantic import BaseModel, Field
from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.yfinance import YFinanceTools

class ResearchProject(BaseModel):
    topic: str
    focus_areas: list[str] = Field(min_length=1)
    max_sources: int = Field(ge=1, le=20, default=10)

news_agent = Agent(
    name="News Researcher",
    role="Research tech news and trends",
    tools=[HackerNewsTools()]
)

finance_agent = Agent(
    name="Finance Researcher",
    role="Research financial data",
    tools=[YFinanceTools()]
)

team = Team(
    name="Research Team",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[news_agent, finance_agent],
)

# Pass the model instance directly
project = ResearchProject(
    topic="AI Agents",
    focus_areas=["multi-agent systems", "tool use"],
    max_sources=15
)

response = team.run(input=project)

Validation happens when you create the model instance. Invalid data raises a Pydantic ValidationError before the team runs.

Using input_schema

Set input_schema on the team to validate dictionaries automatically:

from pydantic import BaseModel, Field
from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.yfinance import YFinanceTools

class ResearchProject(BaseModel):
    topic: str
    focus_areas: list[str] = Field(min_length=1)
    max_sources: int = Field(ge=1, le=20, default=10)

news_agent = Agent(
    name="News Researcher",
    role="Research tech news and trends",
    tools=[HackerNewsTools()]
)

finance_agent = Agent(
    name="Finance Researcher",
    role="Research financial data",
    tools=[YFinanceTools()]
)

team = Team(
    name="Research Team",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[news_agent, finance_agent],
    input_schema=ResearchProject,
)

# Pass a dict - validated against ResearchProject
response = team.run(
    input={
        "topic": "AI Agents",
        "focus_areas": ["multi-agent systems", "tool use"],
        "max_sources": 15
    }
)

This is useful when input comes from external sources like API requests or configuration files.

Handling Invalid Input

Invalid dictionary input raises a ValueError wrapping the Pydantic error:

from pydantic import BaseModel, Field

class ResearchProject(BaseModel):
    topic: str
    focus_areas: list[str] = Field(min_length=1)

team = Team(
    model=OpenAIResponses(id="gpt-5.2"),
    members=[news_agent, finance_agent],
    input_schema=ResearchProject,
)

try:
    team.run(input={"topic": "AI", "focus_areas": []})  # Empty list
except ValueError as e:
    print(e)
    # Failed to parse dict into ResearchProject:
    # focus_areas: List should have at least 1 item

Common Patterns

Multi-Topic Research

from pydantic import BaseModel, Field

class ComparisonProject(BaseModel):
    title: str
    items_to_compare: list[str] = Field(min_length=2, max_length=5)
    comparison_criteria: list[str]
    output_format: str = Field(default="table")

team = Team(
    model=OpenAIResponses(id="gpt-5.2"),
    members=[news_agent, finance_agent],
    input_schema=ComparisonProject,
)

response = team.run(
    input={
        "title": "AI Framework Comparison",
        "items_to_compare": ["Agno", "LangChain", "CrewAI"],
        "comparison_criteria": ["performance", "ease of use", "documentation"],
        "output_format": "table"
    }
)

Scoped Analysis

from pydantic import BaseModel, Field
from datetime import date

class AnalysisScope(BaseModel):
    company: str
    analysis_type: str = Field(description="financial, competitive, or market")
    start_date: date | None = None
    end_date: date | None = None
    include_competitors: bool = True

team = Team(
    model=OpenAIResponses(id="gpt-5.2"),
    members=[news_agent, finance_agent],
    input_schema=AnalysisScope,
)

response = team.run(
    input={
        "company": "NVIDIA",
        "analysis_type": "competitive",
        "include_competitors": True
    }
)

Nested Configuration

from pydantic import BaseModel, Field

class Source(BaseModel):
    name: str
    priority: int = Field(ge=1, le=3, default=2)

class ResearchConfig(BaseModel):
    topic: str
    sources: list[Source]
    depth: int = Field(ge=1, le=10, default=5)

team = Team(
    model=OpenAIResponses(id="gpt-5.2"),
    members=[news_agent, finance_agent],
    input_schema=ResearchConfig,
)

response = team.run(
    input={
        "topic": "Quantum Computing",
        "sources": [
            {"name": "HackerNews", "priority": 1},
            {"name": "Financial Reports", "priority": 2}
        ],
        "depth": 7
    }
)

Related

• Agent Structured Input: Configure structured input for agents
• Team Structured Output: Get validated output from teams