BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-london-2026//speaker//UK3RCM
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pydata-london-2026-RQ3FJQ@pretalx.com
DTSTART;TZID=GMT:20260606T102000
DTEND;TZID=GMT:20260606T110500
DESCRIPTION:Multi-agent AI systems promise autonomous reasoning\, but most 
 tutorials stop at prototypes. This talk shares hard-won lessons from deplo
 ying a production multi-agent RAG platform on serverless AWS \, covering a
 gent orchestration patterns\, cross-region LLM routing\, vector search cos
 t optimisation\, and the observability strategies that keep it all running
  reliably.\n\nYou'll learn concrete patterns for coordinating multiple RAG
 -enabled agents via SQS and Lambda\, the cost/latency trade-offs between m
 anaged and self-managed vector search (including how to achieve 90% storag
 e savings)\, and practical observability strategies using Langfuse and dea
 d-letter queues. Whether you're scaling your first RAG system or architect
 ing multi-agent workflows\, you'll leave with actionable patterns you can 
 apply immediately.
DTSTAMP:20260602T213632Z
LOCATION:Grand Hall 2
SUMMARY:Building Production Multi-Agent RAG Systems on Serverless AWS - Sam
 uel Jaja
URL:https://pretalx.com/pydata-london-2026/talk/RQ3FJQ/
END:VEVENT
END:VCALENDAR