Instructions via Function

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

   Mac

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

   uv venv --python 3.12
   .venv\Scripts\activate
   
3. Install dependencies

   uv pip install -U agno openai
   
4. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
5. Run Agent

   python instructions_via_function.py