BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Knowledge Bases for AI Agents
DTSTART:20260903T140000Z
DTEND:20260903T160000Z
DTSTAMP:20260825T200800Z
UID:indico-event-321@events.asc.ac.at
CONTACT:training@ai-at.eu
DESCRIPTION:Date: 03 September 2026\, 16:00-18:00 (CEST) Price: Free (f
 or eligible participants)Format: AI:AT Webinar\, ONLINE (Zoom) Target au
 dience: Industry\, public admin\, academiaLanguage: English Organizer:
  AI:ATLearn how to supercharge AI agents with structured knowledge bases 
 and knowledge graphs. This training explores how to build\, connect\, and 
 query knowledge representations that give LLM-based agents reliable\, up-t
 o-date\, and domain-specific information for smarter decision-making. LLM
 s are powerful\, but on their own they often struggle with domain-specific
 \, up-to-date\, or structured knowledge - leading to hallucinations\, unre
 liable and contextually irrelevant outputs. This training addresses a key 
 challenge in building effective AI agents: equipping them with external kn
 owledge bases that provide accurate\, structured\, and queryable informati
 on. Participants will explore how knowledge graphs and knowledge bases can
  serve as a persistent "memory" and factual backbone for LLM-based agents\
 , enabling them to reason over real-world entities\, relationships\, and d
 omain-specific facts rather than relying solely on pre-trained general kno
 wledge. The session covers the spectrum from lightweight approaches - suc
 h as connecting agents to curated wikis and document stores via Retrieval-
 Augmented Generation (RAG) - to more advanced architectures that integrate
  knowledge graphs with graph-based querying (e.g.\, SPARQL\, Cypher) to en
 able structured reasoning. Participants will learn how domain knowledge is
  modelled as a graph\, populate it from various data sources\, and integra
 te it with AI agents so that the agent can look up facts\, traverse relati
 onships\, and ground its responses in verified information. Whether you ar
 e building internal company knowledge assistants\, domain-specific Q&A sys
 tems\, or AI agents to work with your Personal Knowledge Graph\, this trai
 ning provides the practical patterns to get started.Target audienceThe web
 inar is aimed at everyone who wants to understand knowledge graphs and how
  to combine them with AI agents.Attendance is open and free of charge for 
 all participants from academia\, industry\, and public administration from
  EU and/or EuroHPC JU member countries.Entry level & prerequisitesBasic - 
 no prior experience required.AgendaWelcome & IntroductionKnowledge Graphs:
  Concepts\, Entities & RelationshipsAI Agents with Knowledge Bases: Connec
 ting LLMs to Obsidian-style Wikis & Document StoresBreakAI Agents with Kno
 wledge Graphs: Traversal\, Multi-hop Queries & Grounded ReasoningChoosing 
 the Right Architecture for Your Use CaseQuestions & Discussion  Speakers
 Daniel Dobriy (WU Vienna\, Bilateral AI Cluster of Excellence\, Dobriy AI 
 GmbH)       Daniel Dobriy is an AI researcher and lecturer at the I
 nstitute for Data\, Process and Knowledge Management at WU Vienna. His wor
 k bridges symbolic AI\, graph-based machine learning\, and applications in
  public governance\, finance\, education\, and scientific discovery. He is
  a Research Fellow at the Bilateral AI Cluster of Excellence\, an industry
  leader in the GOBLIN COST Action\, and an active member of the W3C RDF an
 d SPARQL Working Group. Daniel Dobriy is certified in Value-based Engineer
 ing ISO 24748-7000\, is a member of ASAI\, ÖCG\, ACM and ACL\, chairs RAG
 E-KG and serves on programme committees of leading international venues in
 cluding The Web Conference\, ISWC (International Semantic Web Conference)\
 , ESWC\, K-CAP\, HICSS\, SEMANTiCS as well as IJCKG. Daniel Dobriy is also
  the managing director of Dobriy AI GmbH (dobriy.ai). RegistrationRegistr
 ation is required\, the link to the registration form can be found on the 
 top of this page in the menu on the left. Please register with your offici
 al institutional email address to prove your affiliation.You will get the 
 Zoom link in the automatic confirmation by email (subject starting with "[
 Indico] Registration")\, please check your Spam/Junk folders). We will als
 o send 1–2 reminders before the webinar.Please do not hesitate to contac
 t us at training@ai-at.eu if you have any questions.OrganizersThis webinar
  is organized by AI Factory Austria AI:AT.AcknowledgementsAI Factory Austr
 ia AI:AT has received funding from the European High-Performance Computing
  Joint Undertaking (JU) under grant agreement No 101253078. The JU receive
 s support from the Horizon Europe Programm of the European Union and Austr
 ia (BMIMI / FFG). \n\nhttps://events.asc.ac.at/event/321/
LOCATION:Zoom (ONLINE)
URL:https://events.asc.ac.at/event/321/
END:VEVENT
END:VCALENDAR