BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-cz-2026//talk//9BS8CT
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-2026-9BS8CT@pretalx.devconf.info
DTSTART;TZID=CET:20260618T140000
DTEND;TZID=CET:20260618T143500
DESCRIPTION:Commercial LLM-based assistants such as ChatGPT or Claude can c
 all tools\, query data\, and power agents out of the box. In enterprise se
 ttings\, these products are delivered through managed external services\, 
 creating vendor lock-in and data governance risks. Small self-hosted langu
 age models offer a compelling alternative\, but require a different approa
 ch to build reliable AI assistants.\n\nIn this session\, we present the de
 sign and implementation of an AI assistant powering Red Hat AIPCC Producti
 zation’s Release Dashboard. The assistant queries internal data\, calls 
 internal tools\, and synthesizes answers without relying on external LLM p
 roviders. We show how decomposing assistant behavior into a four-layer arc
 hitecture of action classification\, tool selection\, argument generation\
 , and answer synthesis makes small\, self-hosted language models viable fo
 r building reliable AI assistants. We conclude by discussing the metrics a
 nd feedback signals used to observe and improve the system.
DTSTAMP:20260430T125156Z
LOCATION:D105 (capacity 300)
SUMMARY:Building Reliable AI Assistants with Small\, Self-Hosted Language M
 odels - Jose Angel Morena Simon
URL:https://pretalx.devconf.info/devconf-cz-2026/talk/9BS8CT/
END:VEVENT
END:VCALENDAR