BookmarkSubscribeRSS Feed

Introducing the New Scheduled Journeys Agent in SAS Customer Intelligence 360

Started 7 hours ago by
Modified 7 hours ago by
Views 48

Introduction

Copilot is an existing feature within SAS Customer Intelligence 360 available since 2025. It provides an AI-driven means of getting answers to your questions in a context-specific and easy to digest manner. I have covered this in a previous post, available here.

 

Starting in May 2026, the Copilot has been expanded to give an agentic approach to creating Scheduled Journeys!

 

 

Background

 

Marketing campaigns today span a series of connected contextual interactions across multiple channels. Each set of connected interactions is known as a Journey and has a common goal such as brand awareness, product launches, seasonal promotions, cross-selling, and more.

 

Scheduled Journeys have been available since May 2025. They allow the creation of bulk-oriented, time-driven campaigns via a drag-and-drop interface. The marketer formulates a campaign with a goal, purpose, and measurable outcome, then proceeds to build the campaign by building out the Scheduled Journey. They start with a common group of customers known as an audience, then join together existing tasks, and combine with other nodes such as wait, split, and A/B test nodes.

 

Here is an example of a Scheduled Journey for a cart abandonment campaign:

 

AP_ScheduledJourneyAgent_Screenshot1.png

Select any image to see a larger version.
Mobile users: To view the images, select the "Full" version at the bottom of the page.

 

Historically, the user needs to formulate their campaign purpose, goal and target, then manually build up this journey. Using the new Agentic Scheduled Journey builder, this can be built up using AI simply by typing in an explanation of the campaign!

 

 

Getting Started

 

We begin by going to the circular Copilot icon at the top right. Rather than selecting the Ask option to query the documentation, we choose the Agent option.

 

Here we can type in a description of what we want our campaign to do:

 

AP_ScheduledJourneyAgent_Screenshot2.png

 

I have used the following:

 

Goal: Identify Customers with Abandoned Carts

Audience: Customers who have recently added items to their cart

Journey Logic

  1. Send thank you email to those who made a purchase
  2. Send reminder email to those that did not make a purchase
  3. Allow 3 days to make a purchase

Success Metric: 10% Conversion Rate

Drop from Journey when order placed.

Holdout: 10% for testing

Run: Mon-Thu @ 10amCST

 

It does not need to be in the format I have used. Any description will be acceptable, although it does help to be as specific and unambiguous as possible.

 

The agent then returns an outline of what it will build. We then have the option to approve the plan. If the proposal is not what you need, you can also refine the request by typing more information into the text box. The agent will remember the previous request and refine based on further instructions.

 

The agent will then choose appropriate tasks and audience that already exist or create placeholders for those still to be created. It will also set appropriate purpose, goals, wait periods, splits and scheduling frequencies.

 

The agent has created my Scheduled Journey below:

 

AP_ScheduledJourneyAgent_Screenshot3.png

 

We can see that it is very similar to the one I manually created. Some items are highlighted for attention. For example, where perzonalisation variables need mapped, or where placeholders have been used. There is also the option to refine further by typing more instructions into the text box.

 

Using the attachments button, there is also the option to upload documents and images directly to the agent. The document option is useful if you have a pre-written campaign brief. The AI can simply create the Journey straight from this brief.

 

Images can be useful if there is a marketing brainstorming session and the campaign has been sketched on a whiteboard. A photograph of this whiteboard can be uploaded straight to the agent.

 

For example, a plan has been sketched out below:

 

AP_ScheduledJourneyAgent_Screenshot4.png

 

You can see that the agent has interpreted this very rough sketch and built an appropriate Journey:

 

AP_ScheduledJourneyAgent_Screenshot5.png

 

 

Responsible use of AI

 

We all know that AI can sometimes produce some unusual results! Because of this it is strongly advised to check the output and refine where necessary.

 

The user must accept the terms and conditions of using the AI and also enable the functionality. This is not enabled by default.

 

This can be done by your system administrator under general setting show here:

 

AP_ScheduledJourneyAgent_Screenshot6.png

 

 

Further Information

 

More information can be found on the SAS Customer Intelligence 360 User Guide available here. The Scheduled Journeys agent is discussed in more detail in the “Scheduled Journeys with SAS Customer Intelligence 360” course, which is part of the SAS Customer Intelligence 360 Learning Curriculum.

 

Note that this is part of a wider move to agentic approaches across multiple parts for SAS Customer Intelligence 360. We are looking to expand it out to audience creation, email design and more!

 

Please see the blog post here for more information on this strategy.

 

 

Find more articles from SAS Global Enablement and Learning here.

Contributors
Version history
Last update:
7 hours ago
Updated by:

Ready to see what SAS Viya Copilot can do?

Visit the Tips & Tricks page for setup guidance, demos, and practical examples that show how Copilot supports your workflows.

Get Started →

SAS AI and Machine Learning Courses

The rapid growth of AI technologies is driving an AI skills gap and demand for AI talent. Ready to grow your AI literacy? SAS offers free ways to get started for beginners, business leaders, and analytics professionals of all skill levels. Your future self will thank you.

Get started

Article Tags