BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-london-2026//talk//JFJFQX
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-JFJFQX@pretalx.com
DTSTART;TZID=GMT:20260606T161500
DTEND;TZID=GMT:20260606T170000
DESCRIPTION:Multi-agent GenAI systems don’t fail because models lack inte
 lligence\, they fail because they lack memory.\n\nAs LLM applications move
  from demos to production\, semantic memory becomes the defining systems c
 hallenge. Agents must remember user preferences\, share context across rol
 es\, preserve conversational state across sessions\, and evolve over time\
 , all without exploding token costs or losing observability.\n\nIn this ta
 lk\, I’ll explore semantic memory as a data engineering problem rather t
 han a prompt engineering trick. Drawing on real-world experience from the 
 Azure Cosmos DB engineering team\, we’ll examine how to design layered m
 emory for multi-agent systems in Python: short-term conversational state\,
  episodic event logs\, declarative and procedural memory\, and retrieval-d
 riven personalization.\n\nUsing a practical multi-agent travel planner bui
 lt with LangGraph\, we’ll implement patterns such as session-level versu
 s per-turn persistence\, hybrid retrieval design (structured filters plus 
 semantic signals)\, memory lifecycle management (write\, retrieve\, summar
 ize\, supersede\, expire)\, and checkpointed workflows for reproducibility
  and debugging.\n\nYou’ll leave with practical design heuristics for bui
 lding agent systems that become more reliable\, more efficient\, and more 
 explainable over time.\n\nAll demonstrations will be in Python and applica
 ble to production-scale systems.
DTSTAMP:20260602T223338Z
LOCATION:Hardwick Hub
SUMMARY:Designing Semantic Memory for Multi-Agent Systems with Python - The
 o van Kraay
URL:https://pretalx.com/pydata-london-2026/talk/JFJFQX/
END:VEVENT
END:VCALENDAR