BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//euroscipy-2026//talk//J3XDU9
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-euroscipy-2026-J3XDU9@pretalx.com
DTSTART;TZID=CET:20260721T160000
DTEND;TZID=CET:20260721T162000
DESCRIPTION:Reproducibility remains one of the most persistent challenges i
 n scientific computing. Despite excellent tools like conda\, pixi\, and Ju
 pyter\, studies continue to show that a significant fraction of published 
 computational results cannot be reproduced  often due to undocumented depe
 ndencies\, hidden notebook state\, or fragile glue code between pipeline s
 tages.\n\nMeanwhile\, AI agents  autonomous systems that can reason\, plan
 \, and execute multi-step tasks  have matured rapidly in industry settings
 . Frameworks like smolagents\, PydanticAI\, and DSPy now make it feasible 
 to build agents that inspect environments\, trace data lineage\, and verif
 y computational workflows with minimal human intervention.\n\nThis talk br
 idges these two worlds. Drawing on practical experience building productio
 n AI agent systems\, I will present concrete design patterns for agents th
 at serve as "reproducibility assistants" in scientific Python workflows. T
 he talk covers three actionable areas: \n(1) automated environment auditin
 g  agents that detect undeclared dependencies and version conflicts\n(2) n
 otebook-to-pipeline conversion  agents that analyze Jupyter notebooks for 
 hidden state and generate deterministic scripts\n(3) result verification  
 agents that re-execute computational steps and flag numerical divergence. 
 A live demo will show an agent auditing a real scientific Python project e
 nd to end.
DTSTAMP:20260603T195654Z
LOCATION:Room 2.41 (First Floor\, Turing)
SUMMARY:From Industry AI Agents to Open Science: Lessons and Patterns for R
 eproducible Research in the Scientific Python Ecosystem - Nitish Agarwal
URL:https://pretalx.com/euroscipy-2026/talk/J3XDU9/
END:VEVENT
END:VCALENDAR