BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//talk//EWZMJK
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20250416T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T030000
RDATE:20261025T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T030000
RDATE:20270328T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Don’t call your LLM too often! How to build your dialog graph wi
 th confidence and sleep at night. - Evgeniya Ovchinnikova\, Andrei Beliank
 ou
DTSTART;TZID=Europe/Berlin:20260416T101500
DTEND;TZID=Europe/Berlin:20260416T104500
DTSTAMP:20260814T193010Z
UID:pretalx-pyconde-pydata-2026-EWZMJK@pretalx.com
DESCRIPTION:Keywords: **Explainable AI\, enhanced RAG\, GraphRAG\, LLMOps\
 , dialog system evaluation.**\n\nDesigning reliable dialog flows for LLM-b
 ased systems remains challenging once conversations require branching\, co
 rrection\, or multi-step reasoning. Dialog graphs often evolve organically
  and accumulate structural issues: endless correction loops\, dead subpath
 s\, redundant validation steps\, overly generic catch-all branches\, or li
 near sequences that should be collapsed. Such phenomena raise operational 
 costs\, significantly increase TTFT and make the system answer less predic
 table and explainable.\n\nMany solutions try to introduce an all-fit gener
 alized RAG retrieval solution. Contrary to this\, we present our empirical
  learnings on how to enhance system speed\, lower overall costs and offer 
 a better dialog graph explainability through enhanced LLM call tracing and
  iterative enhancements for common dialog paths.\n\nWe also show that more
  elaborated knowledge retrieval strategies like GraphRAG may drastically e
 nhance overall response quality and shorten the dialog graph. We evaluate 
 several approaches and give recommendations on how to leverage more comple
 x document indexing phases for inference time benefits.\n\nOverall\, the s
 ession argues that scalable conversational systems require not only better
  prompts\, but explicit graph structures paired with rigorous tracing and 
 data-driven optimization.
LOCATION:Europium [3rd Floor]
URL:https://pretalx.com/pyconde-pydata-2026/talk/EWZMJK/
END:VEVENT
END:VCALENDAR