BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-amsterdam2026//speaker//APPN3U
BEGIN:VTIMEZONE
TZID:Europe/Amsterdam
BEGIN:DAYLIGHT
DTSTART:20250910T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T030000
RDATE:20261025T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T030000
RDATE:20270328T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:A/B Testing Plenary Debates in the Dutch Parliament with Multi-Age
 nt AI using LangGraph - Jeroen Nelen
DTSTART;TZID=Europe/Amsterdam:20260910T142500
DTEND;TZID=Europe/Amsterdam:20260910T145500
DTSTAMP:20260911T153631Z
UID:pretalx-pydata-amsterdam2026-Z87GCU@pretalx.com
DESCRIPTION:How do you test systemic democratic reforms when you can’t r
 un live experiments on a\nnational parliament?\n\nIn collaboration with Du
 tch think-tank DenkWerk for their report “Democracy in Revision”\, we
 \nbuilt a multi-agent digital twin of the Dutch House of Representatives. 
 By configuring 15\nparty agents\, a chairperson\, and a minister\, we simu
 lated parliamentary debates to evaluate\nstructural reforms\, such as intr
 oducing electoral thresholds.\nIn this talk\, we break down the engineerin
 g and data science setup behind this multi-agent\narchitecture to simulate
  a debate. We’ll cover how we translated parliamentary procedure\ninto a
  LangGraph state machine\, grounded agents using party-filtered RAG\, and 
 set up an\nexperimental framework to A/B test systemic reforms across 238 
 simulated debates and five\nlegislative bills.
LOCATION:The Grid
URL:https://pretalx.com/pydata-amsterdam2026/talk/Z87GCU/
END:VEVENT
END:VCALENDAR