This example demonstrates Workflows 2.0 using a single custom execution function instead of discrete steps. This pattern gives you complete control over the orchestration logic while still benefiting from workflow features like storage, streaming, and session management. When to use: When you need maximum flexibility and control over the execution flow, similar to Workflows 1.0 approach but with a better structured approach.
function_instead_of_steps.py
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.storage.sqlite import SqliteStorage
from agno.team import Team
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.hackernews import HackerNewsTools
from agno.utils.pprint import pprint_run_response
from agno.workflow.v2.types import WorkflowExecutionInput
from agno.workflow.v2.workflow import Workflow

# Define agents
hackernews_agent = Agent(
    name="Hackernews Agent",
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[HackerNewsTools()],
    role="Extract key insights and content from Hackernews posts",
)
web_agent = Agent(
    name="Web Agent",
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[DuckDuckGoTools()],
    role="Search the web for the latest news and trends",
)

# Define research team for complex analysis
research_team = Team(
    name="Research Team",
    mode="coordinate",
    members=[hackernews_agent, web_agent],
    instructions="Research tech topics from Hackernews and the web",
)

content_planner = Agent(
    name="Content Planner",
    model=OpenAIChat(id="gpt-4o"),
    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_execution_function(
    workflow: Workflow, execution_input: WorkflowExecutionInput
):
    print(f"Executing workflow: {workflow.name}")

    # Run the research team
    run_response = research_team.run(execution_input.message)
    research_content = run_response.content

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

        Core Topic: {execution_input.message}

        Research Results: {research_content[:500]}

        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.
    """
    content_plan = content_planner.run(planning_prompt)

    # Return the content plan
    return content_plan.content


# Create and use workflow
if __name__ == "__main__":
    content_creation_workflow = Workflow(
        name="Content Creation Workflow",
        description="Automated content creation from blog posts to social media",
        storage=SqliteStorage(
            table_name="workflow_v2",
            db_file="tmp/workflow_v2.db",
            mode="workflow_v2",
        ),
        steps=custom_execution_function,
    )
    content_creation_workflow.print_response(
        message="AI trends in 2024",
    )
This was a synchronous non-streaming example of this pattern. To checkout async and streaming versions, see the cookbooks-