From Prompt Grounding to Edge Delivery: Agentic AI at Scale

Architecting and operating multi-tenant agentic AI platforms with CDN-backed delivery, security, and governance

LOCATION ADDRESS (Hybrid, in person or by zoom, you choose)
Valley Research Park
319 North Bernardo Avenue
Mountain View, CA CA 93043
Don't use the front door. When facing the front door, turn right along the front of the building. Turn left around the building corner. The 2nd door should be open and have a banner and event registration.

If you want to join remotely, you can submit questions via Zoom Q&A. The zoom link:
https://acm-org.zoom.us/
Join via YouTube:
https://youtube.com/live/

AGENDA
6:30 Door opens, food and networking (we invite honor system contributions)
7:00 SFBayACM upcoming events, introduce the speaker
7:15 Part 1: Enterprise Prompt Engineering: Grounding, RAG Pipelines, and Tool-Driven Agents
7:55 Part 2: AI Delivery and Control at the Edge
8:30 - 8:45 finish, depending on Q&A

Join SF Bay ACM Chapter for an insightful discussion on:

### Abstract & Overview

As enterprises adopt Generative AI, the challenge shifts from building isolated models to engineering multi-tenant AI platforms that are secure, grounded, and operationally reliable. This session explores the architecture of prompt-grounded, agentic AI systems that combine prompt engineering, retrieval-based grounding, and tool orchestration with cloud and CDN-based delivery to enable contextual intelligence at scale.

Kumar Kasimala and Venkata Gopi Kolla share design patterns and operational insights from real-world enterprise platforms integrating Prompt Builder frameworks, RAG pipelines, AgentOps, and edge-optimized generative delivery. Attendees will learn how to build scalable, compliant, and high-performance AI systems that operate reliably across cloud and edge environments.

### Keynote Summary

This 90-minute session covers how to build enterprise-grade, multi-tenant AI platforms using prompt grounding, data retrieval, and tool orchestration, combined with CDN and edge-based delivery for low-latency, secure, and scalable AI execution. The talk connects AI reasoning and grounding with real-world platform, security, and delivery concerns, showing how agentic systems can be operated reliably across cloud and edge environments.

### Keynote Takeaways

• Learn how prompt engineering and grounding form the foundation of enterprise agentic AI.
• Explore RAG pipelines, tool orchestration patterns of scalable reasoning & action
• Understand tenant isolation, security, compliance in multi-tenant AI platforms.
• Prominence of Edge in AI evolution: Discover how CDNs and edge networks enable low-latency, secure, and resilient generative AI delivery.
• See practical use cases and live demos of inference running at the Edge.

### Why This Talk Is Different

Most ACM Bay Area talks focus on LLM scaling, agent safety, or model behavior. This session goes deeper into how enterprise AI systems are actually built and operated — connecting prompt grounding, tool orchestration, and edge-native delivery to bridge the gap between model capability and real-world, internet-scale deployment.

Distinctive elements:

• Focus on prompt grounding not just prompt design, to ensure correctness & trust.
• Real-world tool orchestration and AgentOps frameworks for production AI workflows.

Integration of multi-tenant architecture with CDN-backed, edge-optimized AI delivery, enabling low-latency, secure, and scalable inference.

• Balance between platform architecture, engineering implementation, and operational control, from cloud LLMs to edge enforcement.

Speaker Bios:
Kumar Kasimala - Software Engineering Architect, leading the AI Cloud Prompt Builder and Agentic AI Platform. With over 15 years of experience building scalable AI and cloud systems, Kumar has architected key frameworks such as Prompt Templates, Unified Runtime Data Resolution Engine, and Agentforce Integrations. His expertise spans prompt engineering, RAG pipelines, and multi-tenant orchestration frameworks.
https://www.linkedin.com/in/kumarkasimala/

Venkata Gopi Kolla - Software Engineer at with 10 years of experience in distributed systems, and large-scale multi-tenant infrastructure, global CDN and edge platforms, where he has led traffic routing, security enforcement, caching, and performance optimization across Akamai, Cloudflare, and CloudFront to deliver reliable, high-throughput enterprise SaaS at internet scale. He is currently focused on edge-optimized delivery and security for generative and agentic AI workloads.
https://www.linkedin.com/in/venkata-gopi-kolla-8265a427/
---
Valley Research Park is a coworking research campus of 104,000 square feet hosting 60+ life science and technology companies. VRP has over 100 dry labs, wet labs, and high power labs sized from 125-15,000 square feet. VRP manages all of the traditional office elements: break rooms, conference rooms, outdoor dining spaces, and recreational spaces.

As a plug-and-play lab space, once companies have secured their next milestone and are ready to expand, VRP has 100+ labs ready to expand into.
https://www.valleyresearchpark.com/