BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//program.berlinbuzzwords.de//bbuzz26//talk//H9UL7Y
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-bbuzz26-H9UL7Y@program.berlinbuzzwords.de
DTSTART;TZID=CET:20260609T140000
DTEND;TZID=CET:20260609T144000
DESCRIPTION:Many so-called “agent failures” are actually context failur
 es in disguise. In this session\, we’ll explore how to tell whether your
  agent truly saw and used the right context\, using techniques like tracin
 g and attribution\, golden datasets for context-aware evaluation\, and tar
 geted probes to test retrieval quality.
DTSTAMP:20260525T083223Z
LOCATION:Frannz Salon
SUMMARY:How to Tell If Your Agent Used the Right Stuff - Apurva Misra
URL:https://program.berlinbuzzwords.de/bbuzz26/talk/H9UL7Y/
END:VEVENT
END:VCALENDAR