BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//speaker//YPZZ3S
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-EPASS8@pretalx.com
DTSTART;TZID=CET:20260416T101500
DTEND;TZID=CET:20260416T104500
DESCRIPTION:Every week\, development in AI brings us another groundbreaking
  release\, another model version\, another must-have integration. In this 
 rapidly shifting landscape\, how does one build production systems that wo
 n’t be obsolete by the time you deploy them?\n\nWe'll explain how trusti
 ng in proven engineering principles from software development and machine 
 learning\, like separation of concerns and evaluation practices\, became o
 ur anchor in an ever-changing landscape of AI development. We share lesson
 s learned from building two MCP applications using FastMCP and PydanticAI.
  Against these challenges\, we found that fundamental engineering principl
 es provided the foundation we needed. \n\nParticipants in the process of d
 eveloping AI tools will leave with practical strategies for building AI-po
 wered systems that are flexible enough to adapt\, yet stable enough to tru
 st.
DTSTAMP:20260412T141905Z
LOCATION:Merck Plenary (Spectrum)  [1st Floor]
SUMMARY:Building MCP at the Speed of Hype: Principles That Outlast the Tren
 ds - Rahkakavee Baskaran\, Friederike Bauer
URL:https://pretalx.com/pyconde-pydata-2026/talk/EPASS8/
END:VEVENT
END:VCALENDAR