BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//open-source-ai-workshops-2026//speaker//BAD
 DMT
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-open-source-ai-workshops-2026-SVYPLV@pretalx.com
DTSTART;TZID=CET:20260519T090000
DTEND;TZID=CET:20260519T170000
DESCRIPTION:Ever wished your AI could do more than just answer a question?\
 nWhat if you could teach it how to think\, decide\, and verify?\n\nThis wo
 rkshop introduces one of the newest and most powerful AI architectures: gr
 aph-based reasoning systems\, where AI agents follow structured decision g
 raphs to retrieve information\, reason step by step\, and produce reliable
 \, evidence-based answers.\n\nWe begin from first principles\, explaining 
 how large language models work and why they cannot be trusted on their own
 . You will then build a complete RAG pipeline that connects an open-source
  LLM to real documents\, enabling it to retrieve evidence and generate fac
 t-grounded answers instead of confident guesses.\n\nFrom there\, we move b
 eyond linear pipelines.\n\nYou will transform your RAG system into a graph
 -based AI agent: an autonomous assistant whose reasoning is explicit\, str
 uctured\, and controllable. Using a reasoning graph\, the AI learns when t
 o retrieve information\, how to combine multiple sources\, when to verify 
 results\, and when to stop. Instead of one-shot responses\, your system fo
 llows a clear decision flow that mirrors human problem-solving.\n\nBy the 
 end of the workshop\, you will have built a complete\, open-source AI assi
 stant that can read documents\, retrieve knowledge\, reason through a grap
 h\, and answer with evidence.\nNot a simple chatbot.\nA truly intelligent 
 AI agent that follows a path of thought.
DTSTAMP:20260501T115226Z
LOCATION:Raum C
SUMMARY:Designing Thinking Machines: The Future of AI with Graphs-Based AI 
 Agents - Ornella Vaccarelli
URL:https://pretalx.com/open-source-ai-workshops-2026/talk/SVYPLV/
END:VEVENT
END:VCALENDAR