# Run on a Schedule

Once you've published a Workflow, you can schedule it to run on a repeat basis via the UI. The same Workflow can have multiple schedules tied to it.

## Configuring a Schedule

To set a schedule, simply navigate to the Workflow's view page, and select the "Run" dropdown shown below:

{% @arcade/embed url="<https://app.arcade.software/share/FndJpKSqTPBW9Y0g6yfU>" flowId="FndJpKSqTPBW9Y0g6yfU" %}

Depending upon the inputs and outputs of your Workflow, some of the fields in the scheduling options will change.

{% hint style="info" %}
When creating your schedule, make sure to select the proper version of your Workflow to run. If you make a mistake, you can edit it from the Schedule UI.
{% endhint %}

## Maintaining State

One of the challenges with creating scheduled workflows is maintaining a "working memory" of previous decisions made by the LLM. For example, if you want to create an LLM workflow that checks a website for "recent news" to generate content ideas, you will need to implement a way of retrieving previous ideas to avoid reptition.

[Knowledge Bases](/context/memory-stores.md) can we help with this. By implementing the following framework you can solve this issue :

Before starting, create a new, empty Knowledge Base. Then, in your workflow, add the following :

1. **Knowledge Base Search** **Step -** Search Knowledge Bases for today's date. It will retrieve the most recent entries added to that Knowledge Base.
2. **LLM Step -** Provide \~5-10 outputs from the **Knowledge Base Search Step** to your model with a prompt like "Here are outputs you have provided previously, please do not repeat any of these ideas:"
3. **Knowledge Base Write Step** - Write to the Knowledge Base with today's date (see [Liquid docs](https://shopify.github.io/liquid/filters/date/) for more info) in the search column and add the output in a metadata column. This will mean that only the date will be used when the Knowledge Base is searched.

Any question, please contact us.


---

# Agent Instructions: 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:

```
GET https://docs.airops.com/actions/run-once/schedule.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.