Learn to build, deploy, and monitor Agentic AI LLM-based applications using SAS Viya and the SAS Agentic AI Accelerator.
Learn How To
Register, publish, deploy, and monitor large language models (LLMs) and Agentic AI workflows (intelligent decision flows). Combine proprietary and open-source LLMs with deterministic models in decision-making workflows.Govern, version, and scale LLM usage in enterprise applications. Who Should Attend
Data Scientists and AI Engineers, Cloud Architects, Developers, Decision Science Professionals, Enterprise Application Teams, and AI Strategists
Prerequisites
Before taking this course, you should ;
Understand LLMs. Be familiar with Python for model registration and management. Know SAS Model Manager and ModelOps, SAS Intelligent Decisioning, and SAS Container Runtime. Know basic deployment techniques (e.g., YAML for Kubernetes, SAS Container Runtime). Be familiar with Azure Cloud fundamentals (Azure CLI, cloud concepts). SAS Products Covered
SAS Model Manager;SAS Intelligent Decisioning
Course Outline
Foundational Model Repository
Introduction to SAS Foundational Model Repository. Standardizing inputs, outputs, and options using Python wrappers. Register proprietary and open-source models in SAS Model Manager. ModelOps - Managing LLMsPublish models as Docker images to Azure Container Registry. Deploy models to Azure containers using scripts. Score deployed models using SAS, Python, or bash scripts. DecisionOps - Building Intelligent Decision FlowsCreate decision flows with non-deterministic LLMs (e.g., GPT-4o-mini, QWEN) and deterministic models (e.g., gradient boosting). Publish and deploy decision flows to Azure. Modify LLM configurations, update prompts, and version decision flows. Integration with Enterprise ApplicationsIntegrate workflows into Azure AI Assistants for execution and enhanced functionality. Demonstrate integration of Agentic AI workflows into enterprise applications. 