BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//program.berlinbuzzwords.de//bbuzz26//talk//PLNTP9
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-PLNTP9@program.berlinbuzzwords.de
DTSTART;TZID=CET:20260608T140000
DTEND;TZID=CET:20260608T144000
DESCRIPTION:Relevance feedback loops used to take months. AI agents can now
  compress the process to seconds. This talk explores agentic retrieval: sy
 stems where agents adjust scoring models\, schema\, and indexing in real t
 ime. Learn how to build retrieval infrastructure with verifiable APIs that
  enable agents to optimize their own search context.
DTSTAMP:20260525T082933Z
LOCATION:Kesselhaus
SUMMARY:Agentic Retrieval: Building Self-Optimizing Search Systems - Skip E
 verling\, Jo Kristian Bergum
URL:https://program.berlinbuzzwords.de/bbuzz26/talk/PLNTP9/
END:VEVENT
END:VCALENDAR