SAS Agentic AI – Build Workflows in SAS Intelligent Decisioning
Welcome back, SAS Agentic AI explorers! Today, we’re going forward with Agentic AI workflows in SAS Intelligent Decisioning—focusing on the build. We'll detail how you can integrate Large Language Models (LLMs), deterministic models, code files, and custom rules into a governed, modular SAS Agentic AI workflow.
Where We Are in the Series
- In Part 1, Register and Publish Models, we introduced code-wrapped LLMs and showed how you can register them in SAS Model Manager, then how to publish them as Docker images using SAS Container Runtime (SCR).
- In Part 2, SAS Agentic AI – Deploy and Score Models – The Big Picture, we compared deployment options, costs, and performance trade-offs in Azure.
- In Part 3.1, SAS Agentic AI – Deploy and Score Models – Containers, we got our hands dirty deploying Azure Container Instances.
- In Part 3.2, SAS Agentic AI – Deploy and Score Models – Apps, we discovered Azure Container Apps and Web Apps for scalable, secure LLM deployments.
- In Part 3.3, Deploy and Score Models – Kubernetes, we deployed an open source LLM to the same Azure Kubernetes Service cluster as SAS Viya.
Why SAS Agentic AI Workflows?
Here’s a very quick overview of agentic AI workflows with SAS Viya:
SAS Agentic AI workflows give you a governed platform where LLMs, traditional machine learning, rule sets, and human review steps all play together. The Call LLM node is a key piece—it lets you connect any LLM via API. All you need is the container’s URL and a payload with prompts and options. SAS Agentic AI Accelerator standardizes the payload.
Flexibility is built-in: swap models or endpoints, run experiments with Prompt Builder, and publish workflows to containers or push them to production. SAS tracks each step with visual diagrams and versioning, so you always know which logic drove the decision.
SAS Agentic AI Workflow Lifecycle
Here’s the typical lifecycle for your Agentic AI workflow:
- Build: Assemble your decision workflow using SAS Intelligent Decisioning. Integrate LLMs (via Call LLM node), deterministic models, code files, and rule sets. To prep prompts, use either prompt models (from Prompt Builder) or code files.
- Publish: Publish your workflow as a container image.
- Deploy: Deploy it to your target cloud or on-prem environment (e.g., Azure Container Instance, Kubernetes, or VM).
- Score: Run scoring using a REST API, passing inputs (data and prompts) and retrieving LLM or model-driven decisions.
- Integrate: Connect your workflow to real-time systems or integrate in applications.
How to Build an Agent?
Let’s focus on the build with an example.
Overview
Suppose your goal is to support credit officers and make their job easier when assessing client credit requests. Their main pain point? They perform steps across multiple systems and lose time personalizing rejection emails. Templates exist, but personalization is still semi-automated. They’re considering LLMs—but messages must remain compliant and tone-appropriate.
That’s where you come in. You’re setting up a workflow that automates communication with human review checkpoints. Using SAS Intelligent Decisioning, you can build an Agentic AI workflow:
Select any image to see a larger version.
Mobile users: To view the images, select the "Full" version at the bottom of the page.
Deterministic Models
Start with their trusted, governed, versioned model to determine credit approval or rejection based on verified inputs.
Branches
Next, branch the logic: one for approval messages, one for rejection. Each branch uses different LLMs and prompts. In this context, prompts act as templates that drive the message structure, the tone.
LLMs
On the rejection branch, the credit team uses an open-source model hosted in their infrastructure.
The Call LLM node is key—it connects any LLM via API. Just provide the container’s URL llmURL and a payload llmBody with prompts and options.
How Do You Specify Prompts?
With SAS, your LLM prompts can come from:
Models: The result of Prompt Builder experiments using the LLM Portal Builder. You version your best prompt and manifest it as a portable model, ideal for governed, repeatable experiments.
Prompt Builder streamlines prompt development from experimentation to deployment. With project organization, experiment tracking, and integration, teams can confidently develop, test, and operationalize LLM prompts in their business processes. We will discuss the Prompt Builder in a future post.
Code File: A Python script that defines your prompt inline. Quick and direct, great for prototyping. You can swap it out later for a full model.
Either way, connect them to the Call LLM node, which handles the API call to your deployed LLM endpoint. See deploy the LLM to a Private Azure Container Instance, or deploy the LLM to a Kubernetes pod, the choice is in your hands.
Flexibility is built-in: swap models or endpoints, run experiments, and push workflows to production. SAS tracks each step with visual diagrams and versioning, so you always know which logic drove the decision.
Evaluate Output
Would you blindly trust the LLM output? No. Especially when the outcome is sensitive or could damage the client relationship.
You could use a SAS sentiment analysis model to evaluate the LLM-generated message and make the user’s job easier.
Human in the Loop
Depending on the detected sentiment, add rule sets to determine whether human review is needed, or if the message can be sent as-is.
Test Before You Deploy
Before going live, score records and review LLM outputs to ensure they meet business requirements. This gives you full control over quality and output, no surprises in production.
Visual Path Tracking: See What’s Happening
SAS Intelligent Decisioning provides visual diagrams that show how records flow through your workflow. You’ll see:
- Which LLM processed each case.
- Where automation succeeded.
- Where human review was triggered.
It’s transparency and governance, built in.
Summary
- SAS Intelligent Decisioning lets you build Agentic AI workflows that combine models, rules, and LLMs.
- Modular design supports rule sets, prompt engineering, and flexible deployment.
- The Prompt Builder user interface allows you to save your most successful prompt engineering experiment as a model.
- The Call LLM node makes it easy to integrate any language model via API. The node is part of the SAS Agentic AI Accelerator and tailored to work with models registered from the SAS Model Manager LLM Model Project.
- Workflows are fully testable and traceable—ready for production.
Discussion
SAS is well-positioned to be a significant player in the Agentic AI space. The SAS Viya platform is already trusted by a wide range of companies and users, providing a solid foundation to build upon. In my view, our greatest potential lies in developing workflows specifically tailored to address distinct customer business problems and solving them exceptionally well. While generative AI models are widely accessible, SAS’s value is in being model agnostic, integrating these models within our robust, trusted platform. This allows customers to leverage cutting-edge AI in their existing environments, alongside traditional Machine Learning models developed over the years.
What Should You Do Next?
- Stay tuned for upcoming posts detailing SAS Agentic AI Workflow Lifecycle, about publishing, deploying, scoring and integrating Agentic AI workflows in enterprise applications.
- Share your workflow stories, experiments, and best tips in the comments below!
- Try deploying LLMs and building an Agentic AI workflow using the recently updated Agentic AI – How to with SAS® Viya® workshop.
If you liked this guide, give it a thumbs up!
Acknowledgment
Thanks to David Weik and Xin Ru Lee for sharing their time and resources.
Additional Resources
- SAS Agentic AI Accelerator – Register and Publish Models.
- SAS Agentic AI – Deploy and Score Models – The Big Picture.
- SAS Agentic AI – Deploy and Score Models – Containers.
- SAS Agentic AI – Deploy and Score Models – Apps.
- SAS Agentic AI - Deploy and Score Models – Kubernetes.
- SAS Container Runtime – SAS Documentation.
Want More Hands-On Guidance?
SAS offers a full workshop with step-by-step exercises for deploying and scoring models using Agentic AI and SAS Viya on Azure.
Access it on learn.sas.com in the SAS Decisioning Learning Subscription. This workshop environment provides step-by-step guidance and a bookable environment for creating agentic AI workflows.
For further guidance, reach out for assistance.
Find more articles from SAS Global Enablement and Learning here.
