BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//talk//JBFGCA
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2026-JBFGCA@pretalx.com
DTSTART;TZID=CET:20260415T150000
DTEND;TZID=CET:20260415T154500
DESCRIPTION:Building an agentic system that collects and evaluates company 
 information in real time—without curated datasets—requires solving dif
 ficult challenges in data acquisition\, quality control\, and agent orches
 tration.\n\nThis talk outlines the solution design for such a system\, imp
 lemented with Python-based tooling including LangGraph\, and emerging prot
 ocols such as A2A and MCP\, within a multi-agent workflow. Because MCP and
  A2A are still new and lightly documented\, we will share implementation l
 essons and a practical example of a hub-and-spoke architecture based on a 
 recent real-world system.\n\nAttendees will learn architectural patterns f
 or multi-agent systems\, common pitfalls of using MCP/A2A in real-world sc
 enarios\, and strategies for maintaining data quality in agent-based workf
 lows.
DTSTAMP:20260523T180036Z
LOCATION:Europium [3rd Floor]
SUMMARY:Building Agentic Systems with Python\, LangGraph\, MCP\, and A2A - 
 Holger Nösekabel
URL:https://pretalx.com/pyconde-pydata-2026/talk/JBFGCA/
END:VEVENT
END:VCALENDAR