> For the complete documentation index, see [llms.txt](https://docs.airops.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.airops.com/actions/grids/run-playbooks-in-grid.md).

# Run Playbooks in the Grid

Run a published Playbook across Grid rows and review each Session and Artifact.

Use a Playbook column to run the same published Playbook across rows of structured data. Each run creates a Session, and declared Artifacts stay connected to that Session for review and editing.

## How to configure a Playbook column

1. Open the Grid.
2. Click **+ Add Column**.
3. Select the **Playbooks** tab.
4. Search for and select a published Playbook.
5. Map each Playbook Input to a Grid column, static value, or Brand Kit.
6. Save the column.

If the workspace has no published Playbooks, the **Playbooks** tab does not have a Playbook to add.

## Configuration options

| Option        | Description                                                                                                               |
| ------------- | ------------------------------------------------------------------------------------------------------------------------- |
| Playbook      | The published Playbook that runs for each selected row.                                                                   |
| Version       | **Default** follows the current published version. A pinned version keeps using the selected version until you change it. |
| Input mapping | Connect each Playbook Input to a Grid column, static value, or Brand Kit.                                                 |

{% hint style="warning" %}
When a new Playbook version changes its Inputs, update the Grid column mappings before running it at scale. Missing required Inputs can make runs fail validation or be skipped.
{% endhint %}

## Run the Playbook

Run the Playbook for one row while testing its Input mappings and output. Once the result is correct, run the Playbook column in bulk across the rows you want to process.

The Grid uses the version and Input mappings configured on the Playbook column. Edits made in a Session apply to that Session's Artifacts, not to the Playbook itself. Open the Playbook editor to change its instructions.

## Review Sessions and Artifacts

Each Playbook cell shows its current Session status. Open the cell to review the Session, including:

* The Inputs used for the run
* The execution log
* Every Artifact produced by the Playbook
* Human Review status, when the Playbook includes review blocks

You can interrupt a queued or running Session and rerun a terminal Session. When a Session used an older Playbook version, the cell shows a warning so you can rerun it on the current version.

Artifact columns store Playbook Artifacts directly in the Grid. The Grid cell and Session reference the same Artifact, so edits from either location stay in sync.

## Example

### Run a content refresh Playbook

1. Add the page URL, target prompt, and any supporting context to separate Grid columns.
2. Add a Playbook column and select your published content refresh Playbook.
3. Map the Playbook Inputs to the matching Grid columns and Brand Kit.
4. Run one row and review its Session and Artifacts.
5. Correct any Input mappings or update the Playbook instructions.
6. Run the Playbook column across the remaining rows.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.airops.com/actions/grids/run-playbooks-in-grid.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.