BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//haystack-us-2026//speaker//7YHL8S
BEGIN:VTIMEZONE
TZID:EST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T070000Z
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T080000Z
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-haystack-us-2026-HRG9BY@pretalx.com
DTSTART;TZID=EST:20260507T110000
DTEND;TZID=EST:20260507T114500
DESCRIPTION:Purpose-built rerankers are faster and cheaper\, but are they b
 etter? We argue LLM rerankers win on what matters most in production: inst
 ruction-following and iteration speed\, with more-than-acceptable tradeoff
 s on cost and latency. Our discussion is backed by a case study from Super
 human's production hybrid email search system.
DTSTAMP:20260502T102649Z
LOCATION:Main Stage
SUMMARY:LLMs as Rerankers: A Case Study on Hybrid Email Search - William Ba
 rber\, Agustín Bernardo
URL:https://pretalx.com/haystack-us-2026/talk/HRG9BY/
END:VEVENT
END:VCALENDAR