> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Input And Output Schemas

> Serve two AgentOS agents: a HackerNews agent with a Pydantic input_schema and a movie agent with a MovieScript output_schema.

Demonstrates AgentOS agents that use input and output schemas.

```python agent_schemas.py theme={null}
"""
Agent Input And Output Schemas
==============================

Demonstrates AgentOS agents that use input and output schemas.
"""

from typing import List

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.os import AgentOS
from agno.tools.hackernews import HackerNewsTools
from pydantic import BaseModel, Field

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------
input_schema_db = SqliteDb(
    session_table="agent_session",
    db_file="tmp/agent.db",
)

output_schema_db = SqliteDb(
    session_table="movie_agent_sessions",
    db_file="tmp/agent_output_schema.db",
)


class ResearchTopic(BaseModel):
    """Structured research topic with specific requirements."""

    topic: str
    focus_areas: List[str] = Field(description="Specific areas to focus on")
    target_audience: str = Field(description="Who this research is for")
    sources_required: int = Field(description="Number of sources needed", default=5)


class MovieScript(BaseModel):
    """Structured movie script output."""

    title: str = Field(..., description="Movie title")
    genre: str = Field(..., description="Movie genre")
    logline: str = Field(..., description="One-sentence summary")
    main_characters: List[str] = Field(..., description="Main character names")


# ---------------------------------------------------------------------------
# Create Agents
# ---------------------------------------------------------------------------
hackernews_agent = Agent(
    name="Hackernews Agent",
    model=OpenAIChat(id="gpt-5.2"),
    tools=[HackerNewsTools()],
    role="Extract key insights and content from Hackernews posts",
    input_schema=ResearchTopic,
    db=input_schema_db,
)

movie_agent = Agent(
    name="Movie Script Agent",
    id="movie-agent",
    model=OpenAIChat(id="gpt-5.2"),
    description="Creates structured outputs - default MovieScript format, but can be overridden",
    output_schema=MovieScript,
    markdown=False,
    db=output_schema_db,
)

# ---------------------------------------------------------------------------
# Create AgentOS
# ---------------------------------------------------------------------------
agent_os = AgentOS(
    id="agent-schemas-demo",
    agents=[hackernews_agent, movie_agent],
)
app = agent_os.get_app()

# ---------------------------------------------------------------------------
# Run
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent_os.serve(app="agent_schemas:app", port=7777, reload=True)
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[os]" openai
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `agent_schemas.py`, then run:

    ```bash theme={null}
    python agent_schemas.py
    ```
  </Step>
</Steps>

Full source: [cookbook/05\_agent\_os/schemas/agent\_schemas.py](https://github.com/agno-agi/agno/blob/main/cookbook/05_agent_os/schemas/agent_schemas.py)