> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Sequence of functions and agents

> This example demonstrates how to use a sequence of functions and agents in a workflow.

This example demonstrates **Workflows 2.0** combining custom functions with agents and teams
in a sequential execution pattern. This shows how to mix different component types for
maximum flexibility in your workflow design.

**When to use**: Linear processes where you need custom data preprocessing between AI agents,
or when combining multiple component types (functions, agents, teams) in sequence.

```python sequence_of_functions_and_agents.py theme={null}
from textwrap import dedent

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.storage.sqlite import SqliteStorage
from agno.team import Team
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.hackernews import HackerNewsTools
from agno.workflow.v2.types import StepInput, StepOutput
from agno.workflow.v2.workflow import Workflow

# Define agents
web_agent = Agent(
    name="Web Agent",
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[DuckDuckGoTools()],
    role="Search the web for the latest news and trends",
)
hackernews_agent = Agent(
    name="Hackernews Agent",
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[HackerNewsTools()],
    role="Extract key insights and content from Hackernews posts",
)

writer_agent = Agent(
    name="Writer Agent",
    model=OpenAIChat(id="gpt-4o-mini"),
    instructions="Write a blog post on the topic",
)


def prepare_input_for_web_search(step_input: StepInput) -> StepOutput:
    topic = step_input.message
    return StepOutput(
        content=dedent(f"""\
	I'm writing a blog post on the topic
	<topic>
	{topic}
	</topic>
	
	Search the web for atleast 10 articles\
	""")
    )


def prepare_input_for_writer(step_input: StepInput) -> StepOutput:
    topic = step_input.message
    research_team_output = step_input.previous_step_content

    return StepOutput(
        content=dedent(f"""\
	I'm writing a blog post on the topic:
	<topic>
	{topic}
	</topic>
    
	Here is information from the web:
	<research_results>
	{research_team_output}
	<research_results>\
	""")
    )


# Define research team for complex analysis
research_team = Team(
    name="Research Team",
    mode="coordinate",
    members=[hackernews_agent, web_agent],
    instructions="Research tech topics from Hackernews and the web",
)


# Create and use workflow
if __name__ == "__main__":
    content_creation_workflow = Workflow(
        name="Blog Post Workflow",
        description="Automated blog post creation from Hackernews and the web",
        storage=SqliteStorage(
            table_name="workflow_v2",
            db_file="tmp/workflow_v2.db",
            mode="workflow_v2",
        ),
        steps=[
            prepare_input_for_web_search,
            research_team,
            prepare_input_for_writer,
            writer_agent,
        ],
    )
    content_creation_workflow.print_response(
        message="AI trends in 2024",
        markdown=True,
    )
```

This was a synchronous non-streaming example of this pattern. To checkout async and streaming versions, see the cookbooks-

* [Sequence of functions and agents (sync streaming)](https://github.com/agno-agi/agno/tree/main/cookbook/workflows_2/sync/01_basic_workflows/sequence_of_functions_and_agents_stream.py)
* [Sequence of functions and agents (async non-streaming)](https://github.com/agno-agi/agno/tree/main/cookbook/workflows_2/async/01_basic_workflows/sequence_of_functions_and_agents.py)
* [Sequence of functions and agents (async streaming)](https://github.com/agno-agi/agno/tree/main/cookbook/workflows_2/async/01_basic_workflows/sequence_of_functions_and_agents_stream.py)