> 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/playbooks/artifacts.md).

# Artifacts and Collaboration

Artifacts are the persistent outputs a Playbook produces. Use an Artifact when a result needs to be reviewed, shared, reused in another process, or published after the Playbook run ends.

## How to Configure an Artifact

1. Open the Playbook editor.
2. Open **Artifacts** from the header chip row and add an Artifact.
3. Give the Artifact a clear name and select its type.
4. In the Section that should create the output, type `/` and insert the Artifact into the instructions.
5. Describe what the Section should write to the Artifact, including the expected structure or format.

Add a separate Artifact for each output that needs its own review or downstream use.

## Artifacts and Sessions

Every Playbook run creates a Session. The Session records the Inputs, execution details, Human Review status, and Artifacts created during that run.

Content that is not written to an Artifact remains in the Session context. Declare an Artifact when you need a durable output, such as a brief, article, report, structured dataset, or image.

Supported Artifact types include:

* Markdown
* HTML
* JSON
* CSV
* PNG
* JPG
* GIF

Give each Artifact a clear, stable name so it is easy to reference in Playbook instructions and downstream steps. Each generated Artifact also has a stable deep link that you can use to return to it or share it with teammates who have access.

## Review and edit an Artifact

Open an Artifact from its Session or from a linked Artifact cell in a Grid. You can collaborate on the output without changing the Playbook that produced it:

* **Comments:** Highlight part of an Artifact and leave a question or feedback.
* **Suggestions:** Propose an edit that a reviewer can accept or reject.
* **Mentions:** Tag a teammate in a comment or suggestion thread when their review is needed.
* **Edit with AI:** Highlight content and describe how you want that selection revised.

Comments and suggestions remain attached to the Artifact, keeping the review discussion with the output it refers to.

{% hint style="info" %}
Editing an Artifact changes that Session output. It does not update the Playbook instructions. To change future runs, edit and publish the Playbook.
{% endhint %}

For automated checks of AI Discoverability and Brand Adherence, see [Content Review and Quality Scores](/actions/grids/review-content-in-the-grid/content-review.md).

## Compare or recover versions

Artifact version history preserves earlier versions as the output changes.

Open version history to:

* See when each version was created.
* Compare an earlier version with the current content.
* Return to an earlier version when you need to recover overwritten or unwanted changes.

Use version history before publishing when several people or AI-assisted edits have changed the same output.

## Use Artifacts in Grids

An Artifact column links a Grid cell to the Playbook Artifact in its Session. The link is bidirectional:

* An edit made from the Session appears in the Grid cell.
* An edit opened from the Grid cell updates the same Session Artifact.

This lets teams search and sort outputs in a Grid, use an Artifact as an Input to a downstream Playbook or Workflow, and carry the reviewed output into CMS publishing without copying it into a separate content column.

See [Add Columns in the Grid](/actions/grids/add-columns-in-the-grid.md#artifact-columns) to add and use an Artifact column.


---

# 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/playbooks/artifacts.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.