Step with function

This example demonstrates how to use named steps with custom function executors.

Give a named Step a custom function as its executor. You keep the clear naming and tracking of steps while the function handles custom data processing.

When to use: When you need named step organization but want custom logic that goes beyond what agents/teams provide. Ideal for complex data processing, multi-step operations, or when you need to orchestrate multiple agents within a single step.

Install dependencies:

uv pip install agno openai yfinance sqlalchemy

step_with_function.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.yfinance import YFinanceTools
from agno.workflow.step import Step, StepInput, StepOutput
from agno.workflow.workflow import Workflow

# Define agents
hackernews_agent = Agent(
    name="Hackernews Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[HackerNewsTools()],
    instructions="Extract key insights and content from Hackernews posts",
)

finance_agent = Agent(
    name="Finance Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[YFinanceTools()],
    instructions="Get stock prices and financial data",
)

# Define research team for complex analysis
research_team = Team(
    name="Research Team",
    members=[hackernews_agent, finance_agent],
    instructions="Analyze content and create comprehensive social media strategy",
)

content_planner = Agent(
    name="Content Planner",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions=[
        "Plan a content schedule over 4 weeks for the provided topic and research content",
        "Ensure that I have posts for 3 posts per week",
    ],
)


def custom_content_planning_function(step_input: StepInput) -> StepOutput:
    """
    Custom function that does intelligent content planning with context awareness
    """
    message = step_input.input
    previous_step_content = step_input.previous_step_content

    # Create intelligent planning prompt
    planning_prompt = f"""
        STRATEGIC CONTENT PLANNING REQUEST:

        Core Topic: {message}

        Research Results: {previous_step_content[:500] if previous_step_content else "No research results"}

        Planning Requirements:
        1. Create a comprehensive content strategy based on the research
        2. Leverage the research findings effectively
        3. Identify content formats and channels
        4. Provide timeline and priority recommendations
        5. Include engagement and distribution strategies

        Please create a detailed, actionable content plan.
    """

    try:
        response = content_planner.run(planning_prompt)

        enhanced_content = f"""
            ## Strategic Content Plan

            **Planning Topic:** {message}

            **Research Integration:** {"Research-based" if previous_step_content else "No research foundation"}

            **Content Strategy:**
            {response.content}

            **Custom Planning Enhancements:**
            - Research Integration: {"High" if previous_step_content else "Baseline"}
            - Strategic Alignment: Optimized for multi-channel distribution
            - Execution Ready: Detailed action items included
        """.strip()

        return StepOutput(content=enhanced_content)

    except Exception as e:
        return StepOutput(
            content=f"Custom content planning failed: {str(e)}",
            success=False,
        )


# Define steps using different executor types

research_step = Step(
    name="Research Step",
    team=research_team,
)

content_planning_step = Step(
    name="Content Planning Step",
    executor=custom_content_planning_function,
)


# Define and use examples
if __name__ == "__main__":
    content_creation_workflow = Workflow(
        name="Content Creation Workflow",
        description="Automated content creation with custom execution options",
        db=SqliteDb(
            session_table="workflow_session",
            db_file="tmp/workflow.db",
        ),
        # Define the sequence of steps
        # First run the research_step, then the content_planning_step
        # You can mix and match agents, teams, and even regular python functions directly as steps
        steps=[research_step, content_planning_step],
    )
    content_creation_workflow.print_response(
        input="AI trends in 2024",
        markdown=True,
    )

    print("\n" + "=" * 60 + "\n")