Sequential Workflows

Linear, deterministic processes where each step depends on the output of the previous step.

Example Flow: Research → Data Processing → Content Creation → Final Review

Sequential workflows ensure predictable execution order and clear data flow between steps.

sequential_workflow.py

from agno.workflow import Workflow, StepOutput

def data_preprocessor(step_input):
    # Custom preprocessing logic

    # Or you can also run any agent/team over here itself
    # response = some_agent.run(...)
    return StepOutput(content=f"Processed: {step_input.input}") # <-- Now pass the agent/team response in content here

workflow = Workflow(
    name="Mixed Execution Pipeline",
    steps=[
        research_team,      # Team
        data_preprocessor,  # Function
        content_agent,      # Agent
    ]
)

workflow.print_response("Analyze the competitive landscape for fintech startups", markdown=True)

For more information on how to use custom functions, refer to the Workflow with custom function step page.

See Example:

• Sequence of Functions and Agents - Complete workflow with functions and agents

StepInput and StepOutput provide standardized interfaces for data flow between steps. If you use a custom function as an executor for a step, make sure its input and output types are compatible with StepInput and StepOutput so it integrates with the workflow system.

Take a look at the schemas for StepInput and StepOutput.