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

# Agentic State

> Let an agent update its own shopping list in session state based on the conversation.

Enable agentic session state so the agent updates session state on its own based on the conversation. Here the agent manages a shopping list as the user talks to it.

<Steps>
  <Step title="Create a Python file">
    ```python agentic_session_state.py theme={null}
    from agno.agent import Agent
    from agno.db.sqlite import SqliteDb
    from agno.models.openai import OpenAIResponses

    db = SqliteDb(db_file="tmp/agents.db")
    agent = Agent(
        model=OpenAIResponses(id="gpt-5.2"),
        db=db,
        session_state={"shopping_list": []},
        add_session_state_to_context=True,
        enable_agentic_state=True,
    )

    agent.print_response("Add milk, eggs, and bread to the shopping list", stream=True)

    agent.print_response("I picked up the eggs, now what's on my list?", stream=True)

    print(f"Session state: {agent.get_session_state()}")
    ```
  </Step>

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

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

  <Step title="Export your OpenAI API key">
    <Snippet file="set-openai-key.mdx" />
  </Step>

  <Step title="Run Agent">
    ```bash theme={null}
    python agentic_session_state.py
    ```
  </Step>
</Steps>