BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//workshop-tage-2026//talk//QEE8KS
BEGIN:VTIMEZONE
TZID:Europe/Zurich
BEGIN:DAYLIGHT
DTSTART:20250908T000000
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:Designing Thinking Machines: The Future of AI with Graphs-Based AI
  Agents - Ornella Vaccarelli
DTSTART;TZID=Europe/Zurich:20260908T090000
DTEND;TZID=Europe/Zurich:20260908T170000
DTSTAMP:20260812T142747Z
UID:pretalx-workshop-tage-2026-QEE8KS@pretalx.com
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 w
 orkshop introduces one of the newest and most powerful AI architectures: g
 raph-based reasoning systems\, where AI agents follow structured decision 
 graphs to retrieve information\, reason step by step\, and produce reliabl
 e\, evidence-based answers.\n\nWe begin from first principles\, explaining
  how large language models work and why they cannot be trusted on their ow
 n. You will then build a complete RAG pipeline that connects an open-sourc
 e LLM to real documents\, enabling it to retrieve evidence and generate fa
 ct-grounded answers instead of confident guesses.\n\nFrom there\, we move 
 beyond linear pipelines.\n\nYou will transform your RAG system into a grap
 h-based AI agent: an autonomous assistant whose reasoning is explicit\, st
 ructured\, and controllable. Using a reasoning graph\, the AI learns when 
 to retrieve information\, how to combine multiple sources\, when to verify
  results\, and when to stop. Instead of one-shot responses\, your system f
 ollows 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 ass
 istant that can read documents\, retrieve knowledge\, reason through a gra
 ph\, and answer with evidence.\nNot a simple chatbot.\nA truly intelligent
  AI agent that follows a path of thought.
LOCATION:Room J91
URL:https://pretalx.com/workshop-tage-2026/talk/QEE8KS/
END:VEVENT
END:VCALENDAR