BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-cz-2026//talk//NF8ZMZ
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-NF8ZMZ@pretalx.devconf.info
DTSTART;TZID=CET:20260618T113500
DTEND;TZID=CET:20260618T115000
DESCRIPTION:We contribute to open source JupyterLab extensions (Kale\, Elyr
 a) that transform notebooks into production ML pipelines. This talk explor
 es our technical platform and our path to programming integrated AI archit
 ecture within our developer tools.\n\nOur community’s TypeScript/React f
 rontends and Python backends map data flows into Directed Acyclic Graphs (
 DAGs)\, extracting metadata and compiling user code into pipeline server m
 anifests. The architecture streamlines the transition from experimentation
  to orchestration and is ideal for supporting integrated AI tools.\n\nThe 
 talk will include a demo of Notebook-to-Pipeline conversion\, plus our AI 
 roadmap — AI-assisted coding with Kubeflow APIs\, LLM-based pipeline opt
 imization\, and an integrated genAI development environment.\n\nThis sessi
 on is ideal for IDE developers\, MLOps engineers\, and data scientists\, o
 r anyone who wants to learn about building and utilizing LLM-ready Jupyter
 Lab extension architectures.
DTSTAMP:20260430T125127Z
LOCATION:A113 (capacity 64)
SUMMARY:Building AI-Ready JupyterLab Extensions: Architecture for LLM-Power
 ed Developer Tools - Hannah Marie Tosi\, William
URL:https://pretalx.devconf.info/devconf-cz-2026/talk/NF8ZMZ/
END:VEVENT
END:VCALENDAR