BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2025//talk//PARJXL
BEGIN:VTIMEZONE
TZID:EST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T070000Z
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T080000Z
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-devconf-us-2025-PARJXL@pretalx.devconf.info
DTSTART;TZID=EST:20250919T104000
DTEND;TZID=EST:20250919T111500
DESCRIPTION:Why do so many LLM-based AI agents break down in real-world set
 tings? Despite their increasing popularity\, many are fragile\, hard to sc
 ale\, and tightly coupled to specific toolchains. We set out to build a mo
 dular\, cloud-native agent stack using open source components—and one co
 mponent that stood out was the Model Context Protocol (MCP).\n\nMCP is an 
 open standard that enables AI assistants and agents to seamlessly connect 
 with real data sources—content repositories\, business tools\, developme
 nt environments\, and more. Think of it as a USB-C port for AI application
 s—rather than building custom integrations for every tool\, MCP simplifi
 es connectivity\, authentication\, and data flow\, ensuring seamless inter
 operability between AI models and external systems.\n\nIn this talk\, we
 ’ll walk through how we integrated MCP into an open AI agent architectur
 e leveraging:\n1) vLLM for efficient model inference\n2) Llama Stack as th
 e open source agent framework\n3) MCP to handle tool invocation and data f
 low\n4) Kubernetes for scalable\, cloud-native deployment\n\nWe’ll walk 
 through the architecture\, demo the system in action\, and share lessons l
 earned along the way. You’ll gain a solid understanding of how MCP works
 \, its role in the AI ecosystem\, and whether it’s just hype or a game-c
 hanger. Whether you're an AI researcher\, open source contributor\, develo
 per\, or architect\, you'll walk away with practical insights on using MCP
  to build more dynamic and efficient AI applications.
DTSTAMP:20260315T084930Z
LOCATION:Ladd Room (Capacity 170)
SUMMARY:Putting AI Agents to Work: A New Era of Open Source Connectivity wi
 th MCP - Hema Veeradhi\, Yu An
URL:https://pretalx.devconf.info/devconf-us-2025/talk/PARJXL/
END:VEVENT
END:VCALENDAR