:
days:
days:
daysAccelerate Gen AI Deployment with Cisco AI Infrastructure
As Generative AI moves from innovation to enterprise imperative, the biggest question is no longer “why” but “how.”Join Cisco, NVIDIA, and SoftServe for a hands-on Gen AI Test Drive that goes beyond theory—equipping your team with the technical know-how, infrastructure insights, and scalable patterns to move from prototype to production.
This full-day virtual workshop is designed for AI architects, engineers, data scientists, and IT leaders tasked with operationalizing AI responsibly and at scale. You’ll explore how to deploy real-world Gen AI applications on Cisco AI Infrastructure, powered by NVIDIA NIM and enterprise-ready microservices.
Through demos, labs, and guided sessions, you’ll walk away with a deep dive understanding for enterprise-grade deployment—from model selection and prompting strategies to monitoring, security, and CI/CD pipelines.
AI in Action: Live Use Cases & Demos
Experience how Talk-to-Data applications work using Retrieval-Augmented Generation (RAG) and large language models deployed on Cisco AI Pods. Learn how different prompting techniques and model tuning impact accuracy, performance, and user outcomes.
From Ideation to Production: The Gen AI Lifecycle
Get an end-to-end view of how Gen AI solutions are built—from use case selection and data preparation to pipeline orchestration and rollout. We’ll dive into lifecycle stages, challenges, and governance guardrails you need to adopt AI responsibly.
NVIDIA AI Enterprise & Blueprints
Discover how NVIDIA’s AI software stack, microservices, and curated blueprints simplify the development of scalable AI workloads—whether on-premise, in hybrid environments, or in regulated industries.
Cisco Secure AI Factory
Explore how Cisco secures the AI stack at every layer—from application-level protection with Cisco AI Defense, to workload and infrastructure security using Hypershield, NVIDIA BlueField, and hybrid mesh firewalls.
Observability & Monitoring for AI
Learn how to integrate logging, monitoring, and observability into your Gen AI stack from day one. We’ll walk through best practices using Cisco Intersight and OpenShift for scalable, secure, and accountable AI.
TIME | SESSION TOPIC |
9:00 – 9:30 AM: |
AI Trends & Terminology – Market shifts, foundational concepts, and enterprise readiness |
9:30 – 10:15 AM: |
AI in Action – Talk-to-Data demo, real-world RAG use cases |
10:30 – 11:00 AM: |
Gen AI Lifecycle – From prompt to pipeline |
11:00 – 11:30 AM: |
NVIDIA Enterprise Stack – Accelerators, microservices, deployment patterns |
11:30 – 12:00 PM: |
Cisco Secure AI Factory – Securing applications, workloads, and infrastructure |
12:10 – 1:00 PM: |
Hands-On Lab – Build & test Talk-to-Data on Cisco AI Pods |
2:00 – 3:45 PM: |
Deployment & Observability – Live demo + architecture walk-through |
3:45 – 4:00 PM: |
Q&A & Wrap-Up – Key takeaways, feedback, and next steps |