Dynamic Instructions

This example demonstrates how to create dynamic instructions that change based on session state, allowing personalized agent behavior for different users.

Code

dynamic_instructions.py

from agno.agent import Agent
from agno.run import RunContext

def get_instructions(run_context: RunContext):
    if not run_context.session_state:
        run_context.session_state = {}

    if run_context.session_state.get("current_user_id"):
        return f"Make the story about {run_context.session_state.get('current_user_id')}."

    return "Make the story about the user."


agent = Agent(instructions=get_instructions)
agent.print_response("Write a 2 sentence story", user_id="john.doe")

Usage

1. Create a Python file

   Create dynamic_instructions.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 dynamic_instructions.py