> For the complete documentation index, see [llms.txt](https://documentation.astera.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://documentation.astera.com/astera-studio/automations/creating-an-automation.md).

# Creating an Automation

Creating an automation in Astera Studio is a guided 5-step wizard. You can access it from the **Manage > Automations** page by clicking **+ New automation** in the top-right corner. The wizard walks you through: naming the automation, choosing what it runs, setting when it fires, configuring optional run behaviour, and reviewing before saving.

### Basics

Enter a meaningful **Name** (for example, *vm-creation-check* or *daily-sales-refresh*) and an optional **Description**.

<figure><img src="/files/vMQrXF6TNvyDB0ShNf5R" alt=""><figcaption></figcaption></figure>

### Action

There are two action types to choose from:

<figure><img src="/files/xE2POI69dh8QxfrCQ1Ea" alt=""><figcaption></figcaption></figure>

#### **Catalog item**&#x20;

Runs a published artifact from the resource catalog. Clicking in the *Select a catalog item to schedule* area opens up a catalog item path selector. You can search or browse to locate the item. This is the standard option for scheduling existing catalog items for example dashboards and dataprep files.

<figure><img src="/files/LnXOvkGoNE70wAzjc317" alt=""><figcaption></figcaption></figure>

#### **AI task**&#x20;

Runs a prompt-driven pipeline powered by an AI model with access to MCP tools and catalog skills. Selecting this option reveals two configuration sections:

<figure><img src="/files/eKbZAJkp6c7UvmjQoIrg" alt=""><figcaption></figcaption></figure>

* **Essentials** (required): An **Instructions** text field where you describe in plain language what the AI should do when the automation fires (e.g., "Pull the latest sales data and email a summary to the team"). A **Model** dropdown lets you select the AI model to use — the default is GPT-4o.
* **Enhancements** (optional): Three sub-options that extend what the AI can access.&#x20;

  * **Skills** lets you attach catalog skills that brief the AI with relevant context or data.&#x20;

  <figure><img src="/files/0ZOMjcx8sTJIJTiqMQhN" alt=""><figcaption></figcaption></figure>

  * **Tools** lets you select functions the AI may call during its run.&#x20;

  <figure><img src="/files/gaAnpkwOylg55vB7i5h1" alt=""><figcaption></figcaption></figure>

  * **Response format** controls how the AI's reply is shaped.

    * **Free-Form:** The AI replies with whatever shape it judges appropriate.

    <figure><img src="/files/qgtcORQrZGfqtnFhkX5A" alt=""><figcaption></figcaption></figure>

    * **Fields:** When the response will be consumed by a downstream system which requires a structured output. Define the schema field-by-field.

    <figure><img src="/files/s62J3Q6gMzWOTJHPLPnY" alt=""><figcaption></figcaption></figure>

    * **JSON Schema:** Paste a full JSON Schema fragment when the field builder isn't expressive enough. mostly useful in case of API Responses.

    <figure><img src="/files/jZnENeS9vXy9Wpw6jWt2" alt=""><figcaption></figcaption></figure>

### Trigger

Clicking "Choose a trigger" opens the **trigger picker** modal, which lists all available trigger types organized into four categories.&#x20;

<figure><img src="/files/klqfDcU4z1dKbBFZ52C0" alt=""><figcaption></figcaption></figure>

You can search by name or vendor using the search field or browse by category in the left sidebar. You can change the trigger at any time later.

<figure><img src="/files/wy9COw8ASeuOMdrktEZd" alt=""><figcaption></figcaption></figure>

* **Time-based triggers** fire on a clock. They are the most common kind — *every Monday at 8 AM*, *every 15 minutes*, *on the 1st of each quarter*.
* **Event-based triggers** fire when something happens, not when the clock ticks. They are ideal for reactive pipelines — process the file as soon as it lands, respond to the webhook the moment your vendor sends it.
* **Webhook triggers** fire when a third-party service posts an event to a URL you give them. Astera Studio ships templates for popular vendors and supports custom webhooks for anything else.
* **Continuous triggers** fire as soon as the previous run completes — a hot loop with configurable wait times. Use this for near-real-time pipelines where you always want the freshest pass.
* **Manual trigger** has no configuration. The automation never fires by itself; it only runs when you click *Run*. Useful for automations that act as named playbooks — saved, audited, and reusable, but not scheduled.

After selecting a trigger type, the modal closes and the trigger's configuration fields appear directly on the Trigger step.

<figure><img src="/files/H1WGmUu946rlKs8e7Hj6" alt=""><figcaption></figcaption></figure>

### Options

The Options step has three cards side by side and a fourth section below.

<figure><img src="/files/l0vnNJDAHv8U7v84Y7JP" alt=""><figcaption></figcaption></figure>

Turn on *Trace Job* if you want every run to capture a detailed execution trace; add email notifications; set *Skip if already running*; fill in default job parameters for catalog items.

### Review

Astera Studio checks every step. If anything is missing, the *Save* button stays disabled and a tooltip lists the blockers (e.g. *Missing: Name, Catalog item, Trigger*).

<figure><img src="/files/8lOddSg87kYVpSw77HQP" alt=""><figcaption></figcaption></figure>

### After Saving

Click *Save automation*. The new automation appears in the list and starts firing immediately based on its trigger.

<figure><img src="/files/U4LEtUsDO7GR1OGyh3OF" alt=""><figcaption></figcaption></figure>

To activate the automation, click the status badge or toggle on the list page. You can also trigger a manual run immediately using the **Run now** button in the top-right of the detail page.


---

# 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://documentation.astera.com/astera-studio/automations/creating-an-automation.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.
