> ## 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.

# Instructions With State

> Pass a callable as instructions to build the agent's system message from session_state on every run.

Build run-specific agent instructions from `RunContext.session_state` with an instructions callable.

```python instructions_with_state.py theme={null}
"""
Instructions With State
=============================

Example demonstrating how to use a function as instructions for an agent.
"""

from textwrap import dedent

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.run import RunContext


# This will be our instructions function
def get_run_instructions(run_context: RunContext) -> str:
    """Build instructions for the Agent based on the run context."""
    if not run_context.session_state:
        return "You are a helpful game development assistant that can answer questions about coding and game design."

    game_genre = run_context.session_state.get("game_genre", "")
    difficulty_level = run_context.session_state.get("difficulty_level", "")

    return dedent(
        f"""
        You are a specialized game development assistant.
        The team is currently working on a {game_genre} game.
        The current project difficulty level is set to {difficulty_level}.
        Please tailor your responses to match this genre and complexity level when providing
        coding advice, design suggestions, or technical guidance."""
    )


# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
game_development_agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    instructions=get_run_instructions,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    game_development_agent.print_response(
        "What genre are we working on and what should I focus on for the core mechanics?",
        session_state={"game_genre": "platformer", "difficulty_level": "hard"},
    )
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno 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 `instructions_with_state.py`, then run:

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

Full source: [cookbook/02\_agents/03\_context\_management/instructions\_with\_state.py](https://github.com/agno-agi/agno/blob/main/cookbook/02_agents/03_context_management/instructions_with_state.py)