SAS Expands Viya with New AI Assistants and Agent Infrastructure
SAS has introduced new AI assistants and agentic AI tools for its SAS Viya platform, announced in a press release. The updates include the SAS Viya Copilot, Model Context Protocol (MCP) Server, and Agentic AI Accelerator, designed to help organizations move from isolated generative AI projects to governed, production-scale intelligence.
SAS Viya Copilot is a conversational AI assistant embedded across the analytics life cycle. It supports natural language interaction for data analysis, model building, and decision-making within the Viya environment. Current capabilities include code generation, model pipeline guidance, and visual analysis. Industry-specific copilots are already available for financial risk and clinical data discovery, with more planned for 2026.
The SAS Viya MCP Server uses the open MCP standard to make Viya analytics and decisioning tools available to external AI agents. This allows organizations to integrate SAS analytics within their own AI systems while maintaining governance. The SAS Agentic AI Accelerator offers a curated framework to help teams design and deploy AI agents using no-code, low-code, or developer tools.
SAS also introduced the Retrieval Agent Manager, a no-code retrieval augmented generation solution that converts unstructured data into context-aware AI responses. It will be integrated into Viya in the future to expand grounding capabilities for AI assistants and agents.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Enterprise AI Brief or Daily AI Brief.
Also, consider following us on social media:
More from Enterprise
Oct 16 BOC Group Adds AI Assistant to ADOIT 21 Oct 16 Huawei Brings Upgraded Stellar Network Solution to Europe Oct 16 Element to Manage Waymo's Toronto Fleet for 2028 Launch Oct 16 CTM and Huawei Plan AI Network Security Upgrades in Macao Oct 16 Huawei and 14 partners form Global AI CITY allianceEnterprise AI Brief
Weekly report on AI business applications, enterprise software releases, automation tools, and industry implementations.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
SAS Named a Leader in IDC Decision Intelligence Assessment
SAS and NC State Launch AI Research Partnership
Market Logic Launches DeepSights MCP for AI Assistants
TrendAI Adds Vision One Security to NVIDIA Agent Safety Platform
Zensai Previews AI Employee Coach for Microsoft 365
Daily AI Brief: the AI news that matters, in your inbox.