Skip to main content
A Workflow orchestrates agents, teams, and functions as a collection of steps. Steps can run sequentially, in parallel, in loops, or conditionally based on results. Output from each step flows to the next, creating a predictable pipeline for complex tasks. Workflows flow diagram

​
Your First Workflow

Here’s a simple workflow that takes a topic, researches it, and writes an article: 
from agno.agent import Agent
from agno.workflow import Workflow
from agno.tools.hackernews import HackerNewsTools

researcher = Agent(
    name="Researcher",
    instructions="Find relevant information about the topic",
    tools=[HackerNewsTools()]
)

writer = Agent(
    name="Writer",
    instructions="Write a clear, engaging article based on the research"
)

content_workflow = Workflow(
    name="Content Creation",
    steps=[researcher, writer]
)

content_workflow.print_response("Write an article about AI trends", stream=True)

​
When to Use Workflows

Use a workflow when:
  • You need predictable, repeatable execution
  • Tasks have clear sequential steps with defined inputs and outputs
  • You want audit trails and consistent results across runs
Use a Team when you need flexible, collaborative problem-solving where agents coordinate dynamically.

​
What Can Be a Step?

Step TypeDescription
AgentIndividual AI executor with specific tools and instructions
TeamCoordinated group of agents for complex sub-tasks
FunctionCustom Python function for specialized logic

​
Controlling Workflows

Workflows support conditional logic, parallel execution, loops, and conversational interactions. See the guides below for details.

​
Guides

Build Workflows

Define steps, inputs, and outputs.

Run Workflows

Execute workflows and handle responses.

Conversational Workflows

Enable chat interactions on your workflows.

​
Developer Resources