BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-amsterdam2026//speaker//3NJKS8
BEGIN:VTIMEZONE
TZID:Europe/Amsterdam
BEGIN:DAYLIGHT
DTSTART:20250911T000000
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:Open Weights\, Cloud Scale: Architecture Patterns for Faster and C
 heaper Production Agents - Nicolai van der Smagt
DTSTART;TZID=Europe/Amsterdam:20260911T132500
DTEND;TZID=Europe/Amsterdam:20260911T135500
DTSTAMP:20260911T153010Z
UID:pretalx-pydata-amsterdam2026-V8XH8S@pretalx.com
DESCRIPTION:Agents usually start as a simple harness around a single close
 d-model API. This architecture is convenient\, but it limits control over 
 model choice\, deployment region\, customization\, and cost. Running open-
 weight models locally offers more freedom\, but the most capable models de
 mand hardware that is difficult to provision economically\, and operating 
 production GPU infrastructure introduces complexity that most teams do not
  want to absorb.\n\nManaged cloud inference provides a middle path\, offer
 ing open-weight model access through shared model APIs or dedicated endpoi
 nts\, without requiring teams to operate the underlying GPU infrastructure
 . But realizing its full benefits requires more than replacing one API end
 point with another.\n\nThis talk presents four practical architecture patt
 erns for building faster and cheaper production agents on open-weight mode
 ls.
LOCATION:Fractal
URL:https://pretalx.com/pydata-amsterdam2026/talk/V8XH8S/
END:VEVENT
END:VCALENDAR