BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CFP.DEV//CFP.DEV shortcodes//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Voxxed Days Ticino
X-WR-RELCALID:c426493a-54d4-472b-b975-6f3aaa7163fa
X-WR-TIMEZONE:Europe/Zurich
BEGIN:VEVENT
UID:cfp-1151-7708@cfp.dev
DTSTAMP:20260920T150242Z
SEQUENCE:0
STATUS:CONFIRMED
DTSTART:20250117T101500Z
DTEND:20250117T110000Z
SUMMARY:Complementing LLM with agentic AI: a Quarkus story on Artificial In
 telligence
DESCRIPTION:What AI can do nowadays is simply mind-blowing. I must admit th
 at I cannot stop being surprised and sometimes literally jumping from my s
 eat thinking: &quot\;I didn&#39\;t imagine that AI could ALSO do this!&quo
 t\;. What is a bit misleading here is that today what we tend to identify 
 with Artificial Intelligence is actually the employment of Large Language 
 Model which is only a subset of all AI technologies available: ML is a fra
 ction of the whole AI-story\, while agentic AI enables the implementation 
 of more general use cases\, for instance also involving the usage of Symbo
 lic AI to encode the business logic of a specific domain through a set of 
 human-readable and transparent rules.In fact there are many situations whe
 re being surprised is the last thing that you may want. You don&#39\;t wan
 t to jump from your seat when your bank refuses your mortgage without any 
 human understandable reason\, but only because AI said no. And even the ba
 nk may want to grant their mortgages only to applicants who are considered
  viable under their strict and well-defined business rules. Given these pr
 emises\, it is interesting to mix different complementary technologies in 
 order to overcome the limited auditability and the risk of hallucinations 
 implicit in the usage of a Large Language Model alone. In this talk we wil
 l discuss\, with practical examples\, some of the multiple patterns emergi
 ng in this field like RAG\, external tools invocation and guardrails. We w
 ill also demonstrate why this could be a winning architectural choice in m
 any common situations and how Quarkus through its langchain4j and drools e
 xtensions makes the development of applications integrating those technolo
 gies straightforward.\nSpeakers: Mario Fusco\, Daniele Zonca\nTrack: Data 
 & AI
URL:https://vdt25.voxxeddays.ch/talk/complementing-llm-with-agentic-ai-a-qu
 arkus-story-on-artificial-intelligence/
LOCATION:Room B1\nPalazzo dei Congressi\nLugano\, Switzerland
CATEGORIES:Data & AI
END:VEVENT
END:VCALENDAR