SAS Viya agentic AI capabilities expanded on May 18, 2026, when SAS introduced new artificial intelligence assistants and agent infrastructure designed to help organizations move from experimental AI use cases to governed, production-ready intelligence. The announcements were made at SAS Innovate, the company’s annual data and AI conference, held in Dubai.

New SAS Viya Features

The platform now includes three core additions. SAS Viya Copilot is a family of conversational AI assistants embedded across the analytics workflow, enabling users to analyze data, build models and make decisions using natural language. The system integrates Microsoft Foundry to operate within analytics workflows rather than as a standalone chat interface.

SAS Viya Model Context Protocol (MCP) Server uses the open MCP standard to expose analytics and decisioning capabilities as tools for external AI agents. This allows organizations to embed SAS analytics and governance into agents from any LLM interface, such as Claude, without duplicating logic or bypassing enterprise controls.

The SAS Agentic AI Accelerator provides a framework for teams at all skill levels to design, build, govern and deploy AI agents within SAS Viya. The accelerator includes curated code, components, interfaces and best practices to help teams move from experimentation to production in a repeatable manner.

SAS Viya Copilot Capabilities

Current Copilot features span multiple use cases. Users can perform 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 and explainability
  • Conversational dashboarding with AI-driven data enrichment and natural language dashboard creation
  • Visual investigation with AI-assisted search and automated case and alert narratives

Two industry-specific Copilot capabilities are available today. SAS Asset and Liability Management (ALM) Copilot guides analysts through scenario configuration, execution and interpretation for financial risk workflows. SAS Health Clinical Data Discovery Copilot accelerates clinical data discovery and analysis by guiding users through data exploration and cohort creation using natural language.

Industry Expansion Plans and Human-Centered Design

SAS plans to expand Viya Copilot for additional industries in 2026, including financial crime prevention in banking and intelligent planning and supply chain optimization for manufacturing.

Jared Peterson, Senior Vice President of Global Engineering at SAS, stated: “The role of human expertise in operationalizing agentic AI is not diminished by automation; it’s elevated. With SAS Viya, organizations can pair copilots and agents with human judgment, trusted data and enterprise governance, so AI doesn’t just generate outputs but drives responsible, real-world decisions.”

SAS Retrieval Agent Manager (RAM) complements these tools as a no-code solution built on the retrieval augmented generation (RAG) framework. Currently available as a standalone product, SAS plans to integrate RAM capabilities into Viya, enabling agents and assistants to ground responses in enterprise context for accurate, trusted decision-making.

Platform Integration and Enterprise Focus

The updates position SAS Viya as a governed, enterprise-ready platform for agentic AI, supporting AI assistants and intelligent agents working together to transform trusted insights into real-world decisions at scale. These capabilities are available to current Viya users through GitHub.

The announcement occurred at SAS Innovate as the company celebrates 50 years of innovation. The event included support from partner sponsors Microsoft, Intel and AWS.