Iterative Workflow

Quality-driven processes requiring repetition until specific conditions are met

Example Use-Cases: Quality improvement loops, retry mechanisms, iterative refinement

Iterative workflows provide controlled repetition with deterministic exit conditions, ensuring consistent quality standards.

Example

iterative_workflow.py

from agno.workflow import Loop, Step, Workflow

def quality_check(outputs) -> bool:
    # Return True to break loop, False to continue
    return any(len(output.content) > 500 for output in outputs)

workflow = Workflow(
    name="Quality-Driven Research",
    steps=[
        Loop(
            name="Research Loop",
            steps=[Step(name="Deep Research", agent=researcher)],
            end_condition=quality_check,
            max_iterations=3
        ),
        Step(name="Final Analysis", agent=analyst),
    ]
)

workflow.print_response("Research the impact of renewable energy on global markets", markdown=True)

Iteration Output Forwarding

By default, each iteration receives the previous iteration’s output as its input (forward_iteration_output=True). This enables iterative accumulation patterns where each pass builds on the previous result. Set forward_iteration_output=False if all iterations should receive the original loop input instead.

Developer Resources

• Loop Steps Workflow
• Loop Iterative Accumulation

Reference

For complete API documentation, see Loop Steps Reference.