Cisco has unveiled an answer for constructing synthetic intelligence (AI) infrastructure designed to assist workload information materials, additional enabling enterprises to securely use their information for agentic AI at enterprise-scale. With this new answer, the Cisco Safe AI Manufacturing facility with NVIDIA expands to new use instances, together with the acceleration of retrieval-augmented era (RAG) pipelines with sooner information extraction and retrieval. This new functionality ensures AI brokers have prompt, safe entry to the information they want, once they want it.
Cisco AI PODs, the AI Infrastructure constructing blocks of the Safe AI Manufacturing facility, are actually obtainable with VAST InsightEngine, a core functionality of VAST Information AI OS. These AI PODs ship a completely built-in answer utilizing the NVIDIA AI Information Platform reference design to rework uncooked information into AI-ready datasets. Inside the AI PODs, the Cisco UCS server portfolio with NVIDIA RTX PRO 6000 Blackwell Server Version GPUs collectively present efficiency for next-generation AI functions. RTX PRO Servers from Cisco are a number of the first techniques to ship the NVIDIA AI Information Platform reference design.
NVIDIA accelerated computing and AI software program ensures low-latency mannequin interplay, and Cisco’s high-performance ethernet networking connects compute and information. This unified answer permits AI brokers to function with near-real-time enterprise insights, backed by the safety, governance and suppleness of the Cisco Safe AI Manufacturing facility with NVIDIA structure. By means of this structure, prospects can acquire distinctive visibility into their environments with Splunk, and apply security and safety guardrails to each token utilizing Cisco AI Defence.
“Agentic AI has the potential to unlock the worth of AI for enterprises all over the world. Shifting past chatbots to brokers that may assist resolve true enterprise challenges is revolutionary, however provided that enterprises can successfully leverage the appropriate information on the proper occasions. Cisco, NVIDIA and VAST are working collectively to present prospects a easy path to unlocking the worth of their information,” mentioned Jeremy Foster, the senior vp and normal supervisor at Cisco Compute. “We’re designing the structure for a way the enterprise will construct the subsequent era of AI factories.”
“The following wave of agentic AI might be fuelled by enterprise information, enabling brokers to faucet into enterprise data throughout inference for exact, up-to-date insights,” mentioned Justin Boitano, the vp of enterprise AI at NVIDIA. “Bringing collectively Cisco Safe AI Manufacturing facility with NVIDIA and VASTInsightEngine creates an built-in platform for working highly effective AI brokers at scale.”
“By integrating the VAST Information InsightEngine into the Cisco Safe AI Manufacturing facility with NVIDIA, we’re giving enterprises the primary built-in design for RAG acceleration at scale,” mentioned John Mao, the vp of strategic alliances at VAST Information. “This collaboration with Cisco and NVIDIA represents a serious milestone within the evolution of enterprise AI. The combination of the VAST InsightEngine into the Safe AI Manufacturing facility structure units the stage for a brand new period the place clever brokers can function securely, collaboratively, and at unprecedented scale.”
An Structure for enterprise Agentic AI
Agentic AI workloads place distinctive calls for on IT infrastructure. Enterprises throughout industries wish to deploy AI brokers that may talk with data employees and different AI brokers to unravel complicated challenges. Nonetheless, this requires assist for workload information materials that take away information bottlenecks and decrease latency, so brokers have entry to the appropriate information, whereas offering the safety and governance needed to make sure organisations keep protected.
The brand new capabilities unveiled at present supply prospects a safe AI infrastructure answer for quick information extraction and retrieval to unlock agentic AI use instances. VAST Information would be the first vendor to combine with Cisco AI PODs to supply enterprise prospects an NVIDIA AI Information Platform reference design. Clients can now expertise:
- Quicker time to insights by decreasing RAG pipeline latency from minutes to seconds for near-real-time AI responses.
- Agentic AI at enterprise scale by enabling AI brokers to function constantly, be taught dynamically and ship contextualised enterprise outcomes. The excessive throughput of information unlocks multi-step reasoning, and the structure is designed for scale by supporting a number of brokers and workloads concurrently.
- Safety and governance are on the core, designed to guard delicate information whereas additionally accelerating AI innovation. With role-based entry management and compliance and audit readiness, enterprises can belief their infrastructure to maintain delicate info protected.
Cisco AI PODs with VAST InsightEngine, providing an NVIDIA AI Information Platform answer, are orderable from Cisco now. The AI POD designed for RAG acceleration with NVIDIA and VAST is the primary in a sequence of AI companies PODs constructed to assist the rising variety of use instances within the enterprise.
Touch upon this text by way of X: @IoTNow_ and go to our homepage IoT Now
