# Run from a workflow

> Use your agent as one step in a bigger, repeatable process.

Source: https://cotera.co/docs/deploy/run-from-a-workflow

---

A single agent answers a question. A workflow chains agents and tools into a process: fetch the new signups, enrich each one, score them, post the hot ones to Slack. If your agent is one step of something bigger, put it in a workflow.

## Build it

1. Go to **Workflows** and create a new workflow, or describe the process to Coco and let it draft the workflow for you.
2. Add your agent as a node. Its structured output becomes the input available to downstream nodes. This is why [defining structured output](https://cotera.co/docs/quickstart.md#5-define-the-output) matters.
3. Connect the steps: tool nodes for direct actions (no LLM needed), agent nodes where judgment is required, filters and branches for control flow.
4. Add a trigger: [a schedule](https://cotera.co/docs/deploy/run-on-a-schedule.md), [a webhook](https://cotera.co/docs/deploy/kick-off-from-a-webhook.md), or run it manually while you iterate.

![](https://cotera.co/media/docs/deploy/deploy-workflow-canvas.png)

## Agent step or tool step?

1. Use a **tool node** when the action is deterministic: append a row, send a message, fetch a URL. It's faster and costs nothing in model usage.
2. Use an **agent node** when the step needs to read, judge, or write.

A good workflow is mostly tool nodes, with agents only where thinking happens.

## Watch it run

Every run has a detail view showing each node's input, output, and timing. When a run does something surprising, the trail is all there.