SAS has announced expansions to SAS Viya that advance the platform’s agentic AI features, introducing new AI assistants, agent infrastructure and acceleration tools designed to help organisations move from isolated generative AI use cases to governed, production-ready intelligence at scale.
The announcement was made at SAS Innovate, the company’s global data and AI conference, as SAS marks 50 years of operation. New features include SAS Viya Copilot, a family of embedded AI assistants; a SAS Viya Model Context Protocol (MCP) Server exposing SAS analytics as tools for AI agents; and the SAS Agentic AI Accelerator, a framework for building and governing AI agents within Viya.
Copilots embedded, not bolted on
SAS Viya Copilot is designed to work alongside human experts inside production-grade analytics workflows rather than as a standalone chat interface, integrating Microsoft Foundry to help data scientists, developers and business analysts generate, explain and act on insights in natural language. Current capabilities span data discovery, model pipeline development, code acceleration, conversational dashboarding and AI-assisted visual investigation.
Two industry-specific copilots are already available: the SAS Asset and Liability Management (ALM) Copilot for financial risk workflows, and the SAS Health Clinical Data Discovery Copilot for clinical data exploration. SAS plans to expand Viya Copilot to financial crime prevention in banking and supply chain optimisation for manufacturing later in 2026.
From copilots to governed agents
Beyond embedded assistants, SAS Viya now provides infrastructure to build, connect and govern AI agents at scale. The SAS Viya MCP Server lets organisations embed SAS analytics, governance and domain intelligence into their own agents from the large language model interface of their choice, including Claude, without duplicating logic or bypassing enterprise controls. The SAS Agentic AI Accelerator offers a curated collection of code, components and best practices for teams at all skill levels to build and deploy governed AI agents.
“The role of human expertise in operationalising agentic AI is not diminished by automation; it’s elevated,” said Jared Peterson, Senior Vice President, Global Engineering at SAS. “With SAS Viya, organisations 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.”
Grounding responses in enterprise context
SAS Retrieval Agent Manager (RAM), a no-code retrieval-augmented generation solution, is currently available as a standalone product, with SAS planning to integrate its capabilities into Viya to help agents and assistants ground responses in enterprise context.
“With SAS Viya, organisations 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,” said Jared Peterson, Senior Vice President, Global Engineering, SAS.
