> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Response as Variable

This example shows how to use the response of an agent as a variable.

## Code

```python cookbook/agent_concepts/other/response_as_variable.py theme={null}
from typing import Iterator
from rich.pretty import pprint
from agno.agent import Agent, RunResponse
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    tools=[
        DuckDuckGoTools(
            search=True,
            news=True,
        )
    ],
    instructions=["Use tables where possible"],
    show_tool_calls=True,
    markdown=True,
)

run_response: RunResponse = agent.run("What are the latest developments in artificial intelligence?")
pprint(run_response)

# run_response_strem: Iterator[RunResponse] = agent.run("What are the latest developments in artificial intelligence?", stream=True)
# for response in run_response_strem:
#     pprint(response)
```

## Usage

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

  <Step title="Set your API key">
    ```bash theme={null}
    export OPENAI_API_KEY=xxx
    ```
  </Step>

  <Step title="Install libraries">
    ```bash theme={null}
    pip install -U openai agno ddgs rich
    ```
  </Step>

  <Step title="Run Agent">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/agent_concepts/other/response_as_variable.py
      ```

      ```bash Windows theme={null}
      python cookbook/agent_concepts/other/response_as_variable.py
      ```
    </CodeGroup>
  </Step>
</Steps>