SAS is expanding its SAS Viya data and AI platform with new AI assistants, agent infrastructure and acceleration tools.
“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.”
Governed AI assistants and agentic AI capabilities
The enhancements include the following:
- SAS Viya Copilot, a family of conversational AI assistants embedded across the analytics lifecycle
- SAS Viya Model Context Protocol (MCP) Server, which allows external AI agents to access SAS analytics, models and decisioning capabilities through the open MCP standard
- SAS Agentic AI Accelerator, a framework for designing, governing and deploying AI agents within SAS Viya.
SAS Viya Copilot
SAS Viya Copilot is designed to work alongside human experts within production analytics workflows rather than operate as a standalone chatbot.
Its capabilities include:
- General Q&A across core Viya applications.
- Code accelerationÂ
- Model pipeline guidance
- Conversational dashboardingÂ
- Visual investigation
Beyond copilots, SAS provides infrastructure for organisations to build and connect AI agents across systems and business processes, including:
- SAS Viya Model Context Protocol (MCP) Server provides a standardised way to expose SAS analytics, models and decisioning capabilities to external AI agents.
- SAS Agentic AI Accelerator enables teams across all skill levels (no-code, low-code and developers) to design and operationalise AI agents with governance and trust.
- SAS Retrieval Agent Manager (RAM) is a no-code solution built on the retrieval-augmented generation (RAG) framework that streamlines the process of transforming raw unstructured data into context-aware AI responses.
SAS also plans to integrate its Retrieval Agent Manager into Viya, enabling agents to ground responses in enterprise data through retrieval-augmented generation.
