> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Building Workflows

> Define steps, loops, conditions, and parallel execution in workflows.

Workflows orchestrate your agents and teams as a series of steps executed in a flow that you control.

## Building Blocks

1. **`Workflow`** manages the run and executes its configured steps.
2. **`Step`** wraps exactly one executor: an `Agent`, a `Team`, a custom Python function, or a nested `Workflow`.
3. **`Steps`** groups steps into a named sequential unit.
4. **`Loop`** repeats one or more steps until an end condition succeeds or the iteration cap is reached.
5. **`Parallel`** runs independent steps concurrently and aggregates their outputs.
6. **`Condition`** runs its steps when a boolean evaluator passes and an optional else branch when it fails.
7. **`Router`** picks which step or steps run next from its choices.

<Note>
  When using a custom Python function as an executor for a step, `StepInput` and
  `StepOutput` provide standard interfaces for data flow between steps.
</Note>

<img className="block dark:hidden" src="https://mintcdn.com/phidatainc/JUdd69R_GtzOgSkJ/images/workflows-step-io-flow-light.png?fit=max&auto=format&n=JUdd69R_GtzOgSkJ&q=85&s=7586168a3162325a150797c105d2b9b2" alt="Workflows step IO flow diagram" width="2001" height="756" data-path="images/workflows-step-io-flow-light.png" />

<img className="hidden dark:block" src="https://mintcdn.com/phidatainc/JUdd69R_GtzOgSkJ/images/workflows-step-io-flow.png?fit=max&auto=format&n=JUdd69R_GtzOgSkJ&q=85&s=3e5e53288d9c3dc03bc332d4150fa2f7" alt="Workflows step IO flow diagram" width="2001" height="756" data-path="images/workflows-step-io-flow.png" />

## Your First Workflow

You can mix agents, teams, and functions as steps in the same workflow:

```python mixed_workflow.py theme={null}
from agno.agent import Agent
from agno.team import Team
from agno.workflow import StepInput, StepOutput, Workflow

research_team = Team(
    name="Research Team",
    members=[
        Agent(
            name="Researcher",
            instructions="Research the requested market and list the main competitors.",
        )
    ],
)

content_agent = Agent(
    name="Writer",
    instructions="Turn the supplied research into a concise competitive analysis.",
)


def data_preprocessor(step_input: StepInput) -> StepOutput:
    research = step_input.previous_step_content or "No research was returned."
    return StepOutput(content=f"Research to analyze:\n{research}")

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

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

## Install

```bash theme={null}
uv pip install -U agno openai
```

<Snippet file="set-openai-key.mdx" />

## Next Steps

| Task                                  | Guide                                                                                       |
| ------------------------------------- | ------------------------------------------------------------------------------------------- |
| Execute a workflow and process events | [Running Workflows](/workflows/running-workflows)                                           |
| Choose a control-flow primitive       | [Workflow Patterns](/workflows/workflow-patterns/overview)                                  |
| Implement a function executor         | [Custom Functions in Workflows](/workflows/workflow-patterns/custom-function-step-workflow) |