BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//programme.europython.eu//europython-2026//speaker//EE9T8
 A
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-europython-2026-RC7ALD@programme.europython.eu
DTSTART;TZID=CET:20260716T114500
DTEND;TZID=CET:20260716T121500
DESCRIPTION:Deploying machine learning models should be predictable\, repea
 table\, and auditable—not a leap of faith. This talk breaks the deployme
 nt lifecycle into clear\, actionable steps and demonstrates pragmatic choi
 ces for containerization\, serverless and platform-based deployments\, mon
 itoring\, and scaling. It also introduces the Model Context Protocol MCP a
 s a practical pattern for giving deployed models secure\, auditable access
  to external data and tools. Attendees will leave with concrete patterns\,
  a checklist to avoid common pitfalls\, and reproducible workflows they ca
 n apply the next day to move models from experimentation into reliable pro
 duction services.
DTSTAMP:20260624T081843Z
LOCATION:S4
SUMMARY:No More “It Works on My Notebook”!: From Notebook to Production
 -Ready Model - Ariane Djeupang
URL:https://programme.europython.eu/europython-2026/talk/RC7ALD/
END:VEVENT
END:VCALENDAR