Conditional Workflow

Execute steps based on content analysis or business logic.

This example demonstrates Workflows 2.0 conditional execution pattern. Shows how to conditionally execute steps based on content analysis, providing intelligent selection of steps based on the actual data being processed.

When to use: When you need intelligent selection of steps based on content analysis rather than simple input parameters or some other business logic. Ideal for quality gates, content-specific processing, or adaptive workflows that respond to intermediate results.

condition_steps_workflow_stream.py

from agno.agent import Agent
from agno.tools.hackernews import HackerNewsTools
from agno.workflow.condition import Condition
from agno.workflow.step import Step
from agno.workflow.types import StepInput
from agno.workflow.workflow import Workflow

# === BASIC AGENTS ===
researcher = Agent(
    name="Researcher",
    instructions="Research the given topic and provide detailed findings.",
    tools=[HackerNewsTools()],
)

summarizer = Agent(
    name="Summarizer",
    instructions="Create a clear summary of the research findings.",
)

fact_checker = Agent(
    name="Fact Checker",
    instructions="Verify facts and check for accuracy in the research.",
    tools=[HackerNewsTools()],
)

writer = Agent(
    name="Writer",
    instructions="Write a comprehensive article based on all available research and verification.",
)

# === CONDITION EVALUATOR ===


def needs_fact_checking(step_input: StepInput) -> bool:
    """Determine if the research contains claims that need fact-checking"""
    summary = step_input.previous_step_content or ""

    # Look for keywords that suggest factual claims
    fact_indicators = [
        "study shows",
        "research indicates",
        "according to",
        "statistics",
        "data shows",
        "survey",
        "report",
        "million",
        "billion",
        "percent",
        "%",
        "increase",
        "decrease",
    ]

    return any(indicator in summary.lower() for indicator in fact_indicators)


# === WORKFLOW STEPS ===
research_step = Step(
    name="research",
    description="Research the topic",
    agent=researcher,
)

summarize_step = Step(
    name="summarize",
    description="Summarize research findings",
    agent=summarizer,
)

# Conditional fact-checking step
fact_check_step = Step(
    name="fact_check",
    description="Verify facts and claims",
    agent=fact_checker,
)

write_article = Step(
    name="write_article",
    description="Write final article",
    agent=writer,
)

# === BASIC LINEAR WORKFLOW ===
basic_workflow = Workflow(
    name="Basic Linear Workflow",
    description="Research -> Summarize -> Condition(Fact Check) -> Write Article",
    steps=[
        research_step,
        summarize_step,
        Condition(
            name="fact_check_condition",
            description="Check if fact-checking is needed",
            evaluator=needs_fact_checking,
            steps=[fact_check_step],
        ),
        write_article,
    ],
)

if __name__ == "__main__":
    print("Running Basic Linear Workflow Example")
    print("=" * 50)

    try:
        basic_workflow.print_response(
            input="Recent breakthroughs in quantum computing",
            stream=True,
        )
    except Exception as e:
        print(f"Error: {e}")
        import traceback

        traceback.print_exc()