Conditional Workflow

Deterministic branching based on input analysis or business rules

Example Use-Cases: Content type routing, topic-specific processing, quality-based decisions

Conditional workflows provide predictable branching logic while maintaining deterministic execution paths.

How It Works

The Condition class evaluates a function and executes different steps based on the result:

• If branch (steps): Executes when the evaluator returns True
• Else branch (else_steps): Executes when the evaluator returns False (optional)

If the condition is False and no else_steps are provided, the condition is skipped and the workflow continues to the next step.

Basic Example

conditional_workflow.py

from agno.workflow import Condition, Step, Workflow

def is_tech_topic(step_input) -> bool:
    topic = step_input.input.lower()
    return any(keyword in topic for keyword in ["ai", "tech", "software"])

workflow = Workflow(
    name="Conditional Research",
    steps=[
        Condition(
            name="Tech Topic Check",
            evaluator=is_tech_topic,
            steps=[Step(name="Tech Research", agent=tech_researcher)]
        ),
        Step(name="General Analysis", agent=general_analyst),
    ]
)

workflow.print_response("Comprehensive analysis of AI and machine learning trends", markdown=True)

If/Else Branching

Use else_steps to define an alternative execution path when the condition is False:

condition_with_else.py

from agno.workflow import Condition, Step, Workflow

def is_technical_issue(step_input) -> bool:
    text = (step_input.input or "").lower()
    tech_keywords = ["error", "bug", "crash", "not working", "api", "timeout"]
    return any(kw in text for kw in tech_keywords)

workflow = Workflow(
    name="Customer Support Router",
    steps=[
        Condition(
            name="TechnicalTriage",
            evaluator=is_technical_issue,
            # If branch: technical pipeline
            steps=[
                Step(name="Diagnose", agent=diagnostic_agent),
                Step(name="Engineer", agent=engineering_agent),
            ],
            # Else branch: general support
            else_steps=[
                Step(name="GeneralSupport", agent=general_support_agent),
            ],
        ),
        Step(name="FollowUp", agent=followup_agent),
    ],
)

# Technical query -> executes Diagnose, Engineer, then FollowUp
workflow.print_response("My app keeps crashing with a timeout error")

# Non-technical query -> executes GeneralSupport, then FollowUp
workflow.print_response("How do I change my shipping address?")

Developer Resources

• Condition Steps Workflow
• Condition with List of Steps

Reference

For complete API documentation, see Condition Steps Reference.