Skip to main content
Structured output ensures your agent returns data in a specific format defined by a Pydantic model. This is essential for building reliable systems where you need predictable data shapes.

​
Why structured output?

  • Type safety: Get typed objects, not strings to parse
  • Validation: Pydantic validates all fields automatically
  • Predictability: Always get the same data structure
  • Integration: Easy to store in databases or pass to other systems

​
Basic example

from agno.agent import Agent
from pydantic import BaseModel, Field

class MovieReview(BaseModel):
    title: str = Field(..., description="Movie title")
    rating: float = Field(..., ge=0, le=10, description="Rating out of 10")
    summary: str = Field(..., description="One-line summary")
    pros: list[str] = Field(..., description="What was good")
    cons: list[str] = Field(..., description="What was bad")

agent = Agent(
    output_schema=MovieReview
)

response = agent.run("Review the movie Inception")
review: MovieReview = response.content

print(f"Rating: {review.rating}/10")
print(f"Summary: {review.summary}")

​
Real-world example: Stock analysis

From the quickstart cookbook: 
from typing import List, Optional
from pydantic import BaseModel, Field
from agno.tools.yfinance import YFinanceTools

class StockAnalysis(BaseModel):
    ticker: str = Field(..., description="Stock ticker symbol")
    company_name: str = Field(..., description="Full company name")
    current_price: float = Field(..., description="Current stock price")
    market_cap: str = Field(..., description="Market cap")
    pe_ratio: Optional[float] = Field(None, description="P/E ratio")
    summary: str = Field(..., description="One-line summary")
    key_drivers: List[str] = Field(..., description="Growth drivers")
    key_risks: List[str] = Field(..., description="Key risks")
    recommendation: str = Field(
        ..., 
        description="Strong Buy, Buy, Hold, Sell, or Strong Sell"
    )

agent = Agent(
    tools=[YFinanceTools()],
    output_schema=StockAnalysis
)

analysis = agent.run("Analyze NVIDIA").content
print(f"{analysis.ticker}: {analysis.recommendation}")
print(f"Price: ${analysis.current_price}")

​
Nested schemas

class Address(BaseModel):
    street: str
    city: str
    country: str

class Company(BaseModel):
    name: str
    headquarters: Address
    employees: int
    revenue: float

agent = Agent(output_schema=Company)

​
Optional fields

from typing import Optional

class Product(BaseModel):
    name: str
    price: float
    discount: Optional[float] = None  # May not always be available
    description: Optional[str] = None

​
Using the output

# Store in database
response = agent.run("Analyze Tesla")
db.insert("analyses", response.content.model_dump())

# Build UI
analysis = agent.run("Analyze Apple").content
render_stock_card(
    ticker=analysis.ticker,
    price=analysis.current_price,
    recommendation=analysis.recommendation
)

# Compare multiple
nvda = agent.run("Analyze NVDA").content
amd = agent.run("Analyze AMD").content
if nvda.pe_ratio < amd.pe_ratio:
    print(f"{nvda.ticker} is cheaper by P/E")
See cookbook examples for more patterns.

Build docs developers (and LLMs) love

Get started for freeTalk to us