Schedule your workflow to run on a recurring basis

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

The scheduler supports both Workflows and Chat Agents.

Configuring a Schedule

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

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

When creating your schedule, make sure to select the proper version of your application to run. If you make a mistake, you can edit it from the Schedule UI.

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.

Memory Stores can we help with this. By implementing the following framework you can solve this issue :

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

  1. Memory Store Search Step - Search Memory Stores for today's date. It will retrieve the most recent entries added to that Memory Store.

  2. LLM Step - Provide ~5-10 outputs from the Memory Store 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. Memory Store Write Step - Write to the Memory Store with today's date (see Liquid docs 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 Memory Store is searched.

Any question, please contact us.

Last updated