BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//events//Events//EN
CALSCALE:GREGORIAN
X-WR-CALNAME:Oct 8 - MCP\, Agents and Skills Meetup Meetup
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
BEGIN:VEVENT
UID:event-4i4h9ext@ontown.app
DTSTAMP:20261008T212257Z
DTSTART:20261008T160000Z
SUMMARY:Oct 8 - MCP\, Agents and Skills Meetup Meetup
LOCATION:San Francisco\, United States
DESCRIPTION:SF Machine Learning Meetup\nJoin our virtual meetup to hear tal
 ks from experts on MCP\, agents and skills.\n\nDate\, Time and Location\n\
 nOct 08\, 2026\n9:00 AM - 11:00 AM PST\nOnline. Register for the Zoom! (ht
 tps://voxel51.com/events/mcp-agents-skills-meetup-october-8-2026)\n\nDesig
 ning Multi‑Agent Systems: Sequential\, Parallel\, and Beyond with ADK\n\
 nMulti‑agent systems are powerful but choosing the wrong interaction pat
 tern can quickly lead to fragile\, slow\, or expensive AI systems.\nIn thi
 s talk\, we explore the core multi‑agent design patterns enabled by ADK\
 , including sequential\, parallel\, and more advanced coordination models.
  Rather than focusing on tools alone\, we’ll look at how to think archit
 ecturally about agent collaboration.\n\nYou’ll learn:\n\n• When sequen
 tial agents are the right choice and when they become a bottleneck\n• Ho
 w parallel agents improve speed and coverage (and the trade‑offs they in
 troduce)\n• Common failure modes in poorly designed agent interactions\n
 • Practical criteria for choosing the right pattern based on task\, late
 ncy\, and reliability\n\nBy the end of the session\, you’ll have a clear
  mental model for designing multi‑agent systems that are intentional\, s
 calable\, and production‑ready.\n\nAbout the Speaker\n\nDr Roushanak Rah
 mat (https://www.linkedin.com/in/roushanakrahmat/) is an Enterprise AI Arc
 hitect\, Google Developer Expert (AI & Cloud)\, and recognized among the T
 op 100 Women in Tech (2025). With a PhD in Artificial Intelligence and ove
 r 15 years of experience\, she specializes in designing and delivering ent
 erprise-scale Generative AI\, Agentic AI\, and Deep Learning solutions tha
 t transform industries including healthcare\, finance\, energy\, and publi
 c services.\n\nPrivacy by Deployment: Architecting Agent-Driven Localizati
 on Workflows for Regulated Environments\n\nMost enterprise AI today is pri
 vate by promise - a DPA\, a SOC 2 report\, or a contract clause that says\
 , "we won't train on your data". For a regulated buyer\, these are remedie
 s after a breach\, not controls that prevent or contain one. For organizat
 ions in healthcare\, finance\, defense\, and government\, privacy often re
 quires stronger guarantees: data residency\, customer-controlled execution
 \, and\, in some cases\, operation within air-gapped environments.\n\nThis
  session demonstrates how agentic AI can automate a localization workflow 
 while operating within these constraints. Using a real-world localization 
 pipeline as an example\, we will show how agentic systems can coordinate t
 ranslation\, review\, quality assurance\, and content preparation tasks wh
 ile incorporating human checkpoints for approval and oversight.\n\nWe will
  also walk through the architectural patterns that enable these workflows 
 to run inside customer-controlled and air-gapped environments without tran
 sferring sensitive content outside the customer boundary. The session incl
 udes a live product demonstration.\n\nKey Takeaways\n\n• Architectural p
 atterns for deploying agentic AI in air-gapped and customer-controlled env
 ironments\n• How agentic systems can automate localization workflows whi
 le preserving critical human review and approval processes\n• Practical 
 considerations for operating agentic workflows in regulated environments w
 ith auditability and governance requirements\n\nAbout the Speaker\n\nShrut
 i Joshi (https://www.linkedin.com/in/28shruti) is building an AI powered s
 ecure localization stack for regulated industries such as healthcare\, leg
 al\, finance that cannot send their content to a typical hosted SaaS. She 
 brings 12+ years of engineering and architecture experience to the questio
 n this talk addresses: how do you make an agentic AI system deployable ins
 ide a regulated perimeter.\n\nMCP Is the Interface\; Skills Are the Operat
 ing Discipline\n\nThis talk shows how MCP and Agent Skills work together i
 n practical agent systems. MCP gives agents a standard interface to tools\
 , data\, and workflows\; skills encode the operating discipline that makes
  those connections reliable. Using a sanitized field-operations ledger as 
 the case study\, the talk walks through source intake\, normalized state\,
  uncertainty labels\, role prompts\, QA gates\, and share-safe status draf
 ting.\n\nAbout the Speaker\n\nChuck Hernandez (https://www.linkedin.com/in
 /chuck-hernandez/) is an AI engineering and client-delivery leader with 10
 + years across software\, data platforms\, and enterprise implementation\,
  including 3+ years shipping production GenAI systems.\n\nAgentic engineer
 ing is about good guidance.\n\nGarbage Inn. Is garbage out? This is true. 
 For many input and output processes. In biological life and in computer sy
 stems\, and equally true when working with LLM’s. The better the prompt\
 , the better the context\, the better the focus\, And the better the conte
 xtual awareness\, the better the quality of the output the LLM’s generat
 es.\nThis is the governance\, art and practice of what we like to call age
 ntic engineering\, something I've been practicing over the last year.\n\nA
 bout the Speaker\n…
URL:https://ontown.app/e/4i4h9ext-oct-8-mcp-agents-and-skills-meetup-meetup
 /
END:VEVENT
END:VCALENDAR