BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-cz-2026//talk//ZQ99HN
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-devconf-cz-2026-ZQ99HN@pretalx.devconf.info
DTSTART;TZID=CET:20260619T101500
DTEND;TZID=CET:20260619T105000
DESCRIPTION:LLM agents look impressive in demos\, but problems arise when t
 hey hit production. They hallucinate\, break your JSON schema\, ignore sys
 tem prompts\, and occasionally decide they know better than your business 
 logic.\n\nIn this talk\, we’ll move beyond agentic “Hello World” and
  explore what it really takes to build reliable LLM agents in Java with Qu
 arkus.\n\nWe'll examine the different options for building agentic systems
 \, with a focus on architecture. You'll see how to secure both agent input
 s and outputs with guardrails\, how to make agent interactions observable\
 , and — last but not least — the testing strategies to verify your age
 nts’ functionality. Step by step\, we'll build a production-ready LLM ag
 ent so that you can understand the different problems and their solutions.
 \n\nWe can't make LLM agents fully reliable. But with the tools presented 
 in this talk\, we can at least make them predictable.
DTSTAMP:20260430T131438Z
LOCATION:E104 (capacity 72)
SUMMARY:LLM Agents Gone Wild (And How to Tame Them with Quarkus) - Martin 
 Štefanko
URL:https://pretalx.devconf.info/devconf-cz-2026/talk/ZQ99HN/
END:VEVENT
END:VCALENDAR