BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Silicon Valley Engineering Council - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://svec.org
X-WR-CALDESC:Events for Silicon Valley Engineering Council
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:-07:00
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=-07:00:20260715T190000
DTEND;TZID=-07:00:20260715T210000
DTSTAMP:20260422T154648
CREATED:20260420T210319Z
LAST-MODIFIED:20260420T210319Z
UID:78271-1784142000-1784149200@svec.org
SUMMARY:Multi-Agent Systems at Scale as a Shared Platform for the enterprises
DESCRIPTION:AI Agent Infrastructure as a Shared Platform: Patterns for Multi-Agent Systems at Scale for the enterprise. \nLOCATION ADDRESS (Hybrid\, in person or by zoom\, you choose)\nValley Research Park\n319 North Bernardo Avenue\nMountain View\, CA CA 93043\nDon’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. \nIf you want to join remotely\, you can submit questions via Zoom Q&A. The zoom link:\n[Zoom](https://acm-org.zoom.us/j/92225957844?pwd=E1L50oEkTFvwai73PYfGoqsPdi9xIL.1) (updated 6:55 pm)\nJoin via YouTube:\nhttps://www.youtube.com/watch?v=pO72Hb30fKw \nAGENDA\n6:30 Door opens\, food and networking (we invite honor system contributions)\n7:00 SFBayACM upcoming events\, introduce the speaker\n7:15 Speaker presents.\n8:30 – 8:45 finish\, depending on Q&A \nJoin SF Bay ACM Chapter for an insightful discussion on: \n### **Abstract & Overview** \nAn agent is simple: Prompt + Tools + Model + Boilerplate. The first three are where product teams create value. The last one—state management\, history compression\, streaming\, cancellation\, tracing\, memory\, persistence—is 80% of the code but 0% of the differentiation.\nAt ThoughtSpot\, we built an Agent Platform that draws a hard line between agent logic and agent infrastructure\, letting product teams ship customer-facing agents faster by owning only what matters: their prompts and their tools.\nThis talk covers the infrastructure patterns behind that separation:\n**State management across tool calls.** Stateless tools (state on the agent\, passed as arguments) give you testability and let the LLM reason about state. Stateful tools (state in the tool service) avoid serialization overhead. I’ll walk through flow diagrams\, show how we propagate state via tool response metadata\, and discuss when each pattern fits.\n**Configuration-driven agent definitions.** Agents defined entirely through config—templated prompts\, tool endpoints\, sub-agent rules\, compression strategies. Teams ship agents without writing orchestration code.\n**Inter-agent communication.** Two patterns: agents-as-tools (sub-agent called like any tool\, returns structured output) and agent handoff (full conversation transfer). The platform handles routing and context—teams just declare delegation rules.\n**Shared memory across agents.** Memory in the platform\, not individual agents\, means knowledge accumulates across agent boundaries. Tiered scoping (tenant\, org\, user) with retrieval that surfaces relevant context regardless of which agent captured it.\n**Tool protocol design.** MCP as the base\, with patterns layered on top: cancellation semantics\, progress streaming\, context variable propagation\, and adapters for existing services.\nBuilding for customer-facing scale adds constraints—high concurrency\, encryption\, tenant isolation\, auditability—that shaped our API design throughout.\n**Takeaways:** \n* Mental model for separating agent value from infrastructure\n* State patterns: agent-side vs. tool-side tradeoffs\n* Inter-agent communication: tools vs. handoff\n* Shared memory architecture across agent boundaries\n* MCP extensions for production systems. \nSpeaker Bio\nAshish Shubham is Fellow/Vice President of Engineering at ThoughtSpot\, where he leads the architecture of enterprise-scale AI and embedded analytics platforms used by Fortune 500 organizations. He is the author of *Architecting AI Data Systems* and an inventor on multiple U.S. patents in natural-language-to-SQL\, generative AI interfaces\, and intelligent analytics. Ashish is an IEEE Senior Member and an active reviewer and committee contributor for leading IEEE and ACM conferences and workshops. His work bridges academic research and real-world deployment\, with a focus on building scalable\, trustworthy\, and developer-centric AI systems for production environments.\n[https://linkedin.com/in/ashubham](https://linkedin.com/in/ashubham) \n—\nValley 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. \nAs 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.\nhttps://www.valleyresearchpark.com/
URL:https://svec.org/event/multi-agent-systems-at-scale-as-a-shared-platform-for-the-enterprises/
LOCATION:Valley Research Park\, 319 N Bernardo Ave\, Mountain View\, CA\, 94043\, United States
ATTACH;FMTTYPE=image/jpeg:https://svec.org/wp-content/uploads/2026/04/1024x576-GLjUV3.jpg
END:VEVENT
END:VCALENDAR