SAS Adds Agentic AI at SAS Innovate

SAS at its SAS Innovate event this week in Grapevine, Texas, announced the expansion of agentic artificial intelligence capabilities within SAS Customer Intelligence 360 with specialized AI agents to work alongside marketers; within SAS Viya with new AI assistants, agent infrastructure, and acceleration tools; and within SAS Data Management.

SAS' multiagent system within SAS Customer Intelligence 360 includes specialized, context-aware agentic AI tools  to act on behalf of marketers to retrieve the right objects, make recommendations, and accelerate execution under human supervision.

The new agents include the following:

• The SAS 360 Agent, which serves as a supervisory layer, managing interactions between specialized agents such as Audience, Journey, Email, Search, and Recipes agents and orchestrating actions across customer data, marketing AI, and journey execution.
• The Journeys Agent that helps marketers create customer journeys using multi-modal inputs, including text briefs, images and conversational prompts, retrieves relevant audiences, events, and touchpoints, then assembles a journey structure aligned to best practices and the marketer’s intent. Behind the scenes, the agent generates consistent, production-ready SAS code.
• Search Agent, which enables marketers to ask operational and performance-related questions across the SAS Customer Intelligence 360 environment, starting with tasks and audiences. Users can ask questions and receive contextual answers grounded in their own data.

"Agentic AI isn't about handing control to machines," said Mike Blanchard, vice president of customer intelligence at SAS, in a statement. "It's  about creating systems that amplify human expertise, one specialized agent at a time."

In advancing SAS Viya's agentic AI features, the company added AI assistants, agent infrastructure, and acceleration tools. These new SAS Viya features include the following:

• SAS Viya Copilot, a family of AI assistants embedded across the analytics life cycle.
• SAS Viya Model Context Protocol (MCP) Server, using the open MCP standard to expose SAS Viya analytics and decisioning capabilities as tools for AI agents.
• SAS Agentic AI Accelerator, a curated framework for building, governing and deploying AI agents within SAS Viya.

SAS Viya Copilot is a governed, conversational AI assistant embedded directly into the SAS Viya platform. It helps organizations analyze data, build models, and make decisions across the analytic life cycle while maintaining enterprise-grade security and oversight.

SAS Viya Copilot integrates Microsoft Foundry. It helps data scientists, developers and business analysts generate, explain and act on insights using natural language across both coding environments and interactive visual interfaces.

Current SAS Viya Copilot capabilities include the following:

• General Q&A across core Viya applications, including data discovery, model pipeline development, model management, decision intelligence, and environment management.
• Code acceleration with AI-generated SAS and Python code, documentation and explanations.
• Model pipeline guidance with intelligent recommendations, next steps and explainability.
• Conversational dashboarding with AI-driven data enrichment, natural language dashboard creation and automated insights.
• Visual investigation with AI-assisted search and AI-powered case and alert narratives.

SAS Viya Model Context Protocol (MCP) Server provides a standardized way to expose SAS analytics, models, and decisioning capabilities to external AI agents. By using SAS Viya MCP, organizations can embed SAS' trusted analytics, governance, and domain intelligence into their own agents from LLM interfaces, such as Claude, without duplicating logic or bypassing enterprise controls.

SAS Agentic AI Accelerator enables teams to design and operationalize AI agents with governance and trust. The accelerator provides a curated collection of code, components, interfaces, and best practices to help teams build, govern, and deploy AI agents within SAS Viya, moving from experimentation to production in a repeatable, governed way.

SAS Retrieval Agent Manager (RAM) is a no-code solution built on the retrieval augmented generation (RAG) framework for transforming raw unstructured data into context-aware AI responses. 

SAS' targeted refresh of its SAS Data Management cloud-native portfolio built on the SAS Viya data and AI platform, was designed to help organizations prepare, govern, and activate data for analytics, automation, and AI, embedding governance, lineage, and performance directly into data workflows.

New and expanded capabilities include the following:

• AI-ready data management
• Governance by design
• Agentic AI and copilots
• Cloud-native analytics acceleration

"A modern data platform is now a mission-critical requirement as organizations move toward agentic AI workflows with less human oversight," said Alyssa Farrell, senior director of data and AI strategy at SAS, in a statement. "SAS is redefining data management for the AI era by helping organizations optimize modern data estates, reduce complexity and unlock AI value, with governance and trust engineered directly into the foundation."

SAS Data Accelerator enables SAS analytics to run directly inside leading cloud data environments, including large-scale data warehouses and lakehouses. SAS Viya also supports modern embedded analytics engines such as DuckDB and open formats like  Parquet, CSV and JSON within governed workflows.

SAS Viya Copilot for Data Discovery enables natural language exploration of governed data and analytics assets.

SAS Viya Copilot for Code Assistance brings AI-assisted development directly into SAS Studio, helping developers write, understand and refine SAS and Python code using natural language.

SAS Data Maker generates high-fidelity synthetic data that reflects the statistical, relational, and temporal characteristics of real data while preserving privacy, auditability and regulatory readiness.