BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//scipy-2026//speaker//8MZMVC
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-scipy-2026-UHUVMM@pretalx.com
DTSTART;TZID=CST:20260716T104500
DTEND;TZID=CST:20260716T111500
DESCRIPTION:How do we build competent data analysis agents? Data analysis r
 equires a willingness to pause\, question conclusions\, and dig into subtl
 eties. Frontier LLMs\, however\, are optimized to push tasks toward comple
 tion\, not to slow down when something seems off. This tendency works well
  for coding agents\, where success is often verifiable. But for data analy
 sis\, verification is more complicated\, and autonomous work by the agent 
 can be at odds with the spirit of the discipline. Drawing on our experienc
 e building data analysis agents\, we'll share evaluations that expose wher
 e LLM-driven analysis goes wrong and design patterns that keep analyses co
 rrect\, transparent\, and reproducible.
DTSTAMP:20260715T021019Z
LOCATION:Johnson Great Room
SUMMARY:Agents for Correct\, Transparent\, and Reproducible Data Analysis -
  Sara Altman\, Simon Couch
URL:https://pretalx.com/scipy-2026/talk/UHUVMM/
END:VEVENT
END:VCALENDAR