---
title: 'Automations'
description: 'Create repeatable AI work with explicit instructions, authority, and triggers.'
---

# Automations

An automation combines instructions, a model, visibility, mutation policy, attachments, and triggers. Start with a small task in a development project before enabling unattended execution.



## Create your first automation

1. Open **AI → Automations → New Automation**.
2. Give it a clear name, such as `Review catalog quality`.
3. Choose the appropriate visibility: personal, project, or a permitted space.
4. Write bounded instructions: “Inspect the tutorial products, identify missing category links, and summarize them. Do not change records.”
5. Select a model and retain **Mutations: Require approval** for the first exercise.
6. Attach any required skills or custom tools. Only attached custom tools are callable; discovering the catalog is not enough.
7. Save the configuration. New automations start **Inactive**; enable configured triggers deliberately after testing.
8. Use the manual run action, then inspect [Run History](/docs/automations/runs) and the summary.

Manual execution is separate from the **Add Trigger** menu. The configured trigger choices are Scheduled, Webhook Triggered, and Entity Events.

```mermaid
flowchart TD
  A[Manual run or configured trigger] --> B[Run with instructions and attached capabilities]
  B --> C{Proposed GraphQL mutation}
  C -->|Approval required| D[Review the proposed change]
  D -->|Approved| E[Execute the change]
  D -->|Rejected| F[Inspect run history and summary]
  C -->|Allowed by policy| E
  B -->|Read-only work| F
  E --> F
```

Custom tools can have external effects outside this GraphQL approval flow. Review their authorization and behavior separately.

## Add capabilities incrementally

Attach [skills](/docs/ai/skills) for repeatable instructions and [custom tools](/docs/automations/custom-tools) for server-side code. Attached skills are loaded; other visible skills can be discovered. Tool availability is narrower: the automation must have the custom tool attached.

After a read-only run works, test a small proposed change and its [approval flow](/docs/automations/approvals). Then configure [triggers](/docs/automations/triggers). Check credits and [loop protection](/docs/automations/loop-protection) before enabling entity-event work.

Use list filters for status, visibility, and credit context when locating an automation. A successful execution badge must be read together with its task summary.

If a run reports that the API cannot aggregate or rank the data the instructions require, treat that as a [schema iteration](/docs/schema/iterating-your-schema) rather than an automation failure.

For the complete exercise, follow [Create an automation](/docs/automations/create).


---

[View full sitemap](/docs/sitemap.md)