BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//program.berlinbuzzwords.de//bbuzz26//speaker//UR3N3L
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-ZY3Y9U@program.berlinbuzzwords.de
DTSTART;TZID=CET:20260609T145000
DTEND;TZID=CET:20260609T153000
DESCRIPTION:Coding agents succeed in verifiable loops (compiler + tests)\, 
 but large repos still expose retrieval weaknesses. \nThis session explores
  how lexical\, structural\, and semantic search can provide cleaner contex
 t for LLMs. We compare tradeoffs and evaluation approaches to improve reli
 ability without inflating token cost.
DTSTAMP:20260525T075447Z
LOCATION:Kesselhaus
SUMMARY:Beyond Grep: Search for Reliable Coding Agents - Amine GANI\, Roudy
  Khoury
URL:https://program.berlinbuzzwords.de/bbuzz26/talk/ZY3Y9U/
END:VEVENT
END:VCALENDAR