Skip to main content
Agents accept input and generate output in many formats, from simple strings to validated Pydantic models. Start with strings, add structure when you need validation.

​
Format Types Usage

Use CaseFormat
Prototyping, chat interfacesStrings work fine
Data extraction, classificationStructured output
API responses, pipelinesStructured input and output

​
String I/O

String in, string out: 
from agno.agent import Agent
from agno.models.openai import OpenAIResponses

agent = Agent(model=OpenAIResponses(id="gpt-5.2"))

response = agent.run("What's the capital of France?")
print(response.content)  # "The capital of France is Paris."

​
Structured I/O

Use Pydantic models to validate what goes in and what comes back: 
from pydantic import BaseModel, Field
from agno.agent import Agent
from agno.models.openai import OpenAIResponses

class ReviewInput(BaseModel):
    text: str
    product_id: str

class SentimentResult(BaseModel):
    sentiment: str = Field(description="positive, negative, or neutral")
    confidence: float = Field(ge=0, le=1)
    summary: str = Field(description="One sentence summary")

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    output_schema=SentimentResult,
)

response = agent.run(
    input=ReviewInput(text="Love this product!", product_id="SKU-123")
)

result: SentimentResult = response.content
print(result.sentiment)   # "positive"
print(result.confidence)  # 0.95

​
Guides

Structured Input

Validate data passed to agents and teams.

Structured Output

Get validated Pydantic objects instead of text.

​
Advanced I/O Features

Multimodal I/O

Pass images, audio, video, and files to agents.

Output Model

Use a secondary model for better writing or cost savings.