Skip to main content
This example demonstrates how to provide instructions to an agent via a function that can access the agent’s properties, enabling dynamic and personalized instruction generation.

​
Code

instructions_via_function.py
from typing import List

from agno.agent import Agent


def get_instructions(agent: Agent) -> List[str]:
    return [
        f"Your name is {agent.name}!",
        "Talk in haiku's!",
        "Use poetry to answer questions.",
    ]


agent = Agent(
    name="AgentX",
    instructions=get_instructions,
    markdown=True,
)
agent.print_response("Who are you?", stream=True)

​
Usage

1

Create a Python file

Create instructions_via_function.py with the code above.
2

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
3

Install dependencies

uv pip install -U agno openai
4

Export your OpenAI API key

export OPENAI_API_KEY="your_openai_api_key_here"
5

Run Agent

python instructions_via_function.py