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

# Basic Workflow Factory -- per-tenant content pipeline

> Demonstrates a WorkflowFactory that builds a multi-step workflow with tenant-specific instructions.

Demonstrates a WorkflowFactory that builds a multi-step workflow with tenant-specific instructions. The workflow steps are constructed fresh on each request.

```python basic_workflow_factory.py theme={null}
"""Basic Workflow Factory -- per-tenant content pipeline.

Demonstrates a WorkflowFactory that builds a multi-step workflow
with tenant-specific instructions. The workflow steps are constructed
fresh on each request.

Run:
    .venvs/demo/bin/python cookbook/05_agent_os/factories/workflow/01_basic_workflow_factory.py

Test:
    curl -X POST http://localhost:7777/workflows/content-pipeline/runs \
        -F 'message=Write a blog post about sustainable energy' \
        -F 'user_id=tenant_42' \
        -F 'stream=false'
"""

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.factory import RequestContext
from agno.models.openai import OpenAIResponses
from agno.os import AgentOS
from agno.workflow.factory import WorkflowFactory
from agno.workflow.step import Step
from agno.workflow.workflow import Workflow

# ---------------------------------------------------------------------------
# Database
# ---------------------------------------------------------------------------

db = PostgresDb(
    id="workflow-factory-db",
    db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
)

# ---------------------------------------------------------------------------
# Factory
# ---------------------------------------------------------------------------


def build_content_pipeline(ctx: RequestContext) -> Workflow:
    """Build a content pipeline workflow tailored to the calling tenant."""
    user_id = ctx.user_id or "anonymous"

    drafter = Agent(
        name="Drafter",
        model=OpenAIResponses(id="gpt-5.4"),
        instructions=(
            f"You are a content drafter for tenant {user_id}. "
            "Write a first draft based on the topic. Keep it focused and concise."
        ),
    )

    editor = Agent(
        name="Editor",
        model=OpenAIResponses(id="gpt-5.4"),
        instructions=(
            f"You are an editor for tenant {user_id}. "
            "Review the draft for clarity, grammar, and structure. Output the final version."
        ),
    )

    return Workflow(
        name="Content Pipeline",
        description="Draft then edit content",
        db=db,
        steps=[
            Step(name="draft", description="Write the first draft", agent=drafter),
            Step(name="edit", description="Edit and finalize", agent=editor),
        ],
    )


content_pipeline_factory = WorkflowFactory(
    db=db,
    id="content-pipeline",
    name="Content Pipeline",
    description="Builds a draft-then-edit content workflow per tenant",
    factory=build_content_pipeline,
)

# ---------------------------------------------------------------------------
# AgentOS
# ---------------------------------------------------------------------------

agent_os = AgentOS(
    id="workflow-factory-demo",
    description="Demo: basic workflow factory",
    workflows=[content_pipeline_factory],
)
app = agent_os.get_app()

# ---------------------------------------------------------------------------
# Run
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    agent_os.serve(app="01_basic_workflow_factory:app", port=7777, reload=True)
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[os]" fastmcp openai psycopg-binary starlette
    ```
  </Step>

  <Step title="Export your API keys">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export JWT_VERIFICATION_KEY="your_jwt_verification_key_here"
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:JWT_VERIFICATION_KEY="your_jwt_verification_key_here"
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Snippet file="run-pgvector-step.mdx" />

  <Step title="Run the example">
    Save the code above as `basic_workflow_factory.py`, then run:

    ```bash theme={null}
    python basic_workflow_factory.py
    ```
  </Step>
</Steps>

Full source: [cookbook/05\_agent\_os/factories/workflow/01\_basic\_workflow\_factory.py](https://github.com/agno-agi/agno/blob/main/cookbook/05_agent_os/factories/workflow/01_basic_workflow_factory.py)