BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-cz-2026//talk//SQKC3S
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-SQKC3S@pretalx.devconf.info
DTSTART;TZID=CET:20260618T110000
DTEND;TZID=CET:20260618T113500
DESCRIPTION:I'm a developer on the Migration Toolkit for Virtualization (MT
 V) team. MTV is an Kubernetes operator that migrates workloads from platfo
 rms like vSphere and oVirt to KubeVirt on Kubernetes. I like writing CLI p
 rograms\, so when I was tasked with creating an MCP server for MTV\, I loo
 ked at how we can reuse our kubectl-mtv CLI tool code and structured outpu
 t to auto-generate the server. In this talk I'll demystify MCP servers\, e
 xplain how AI learns to use tools\, how we let it ask for help the same wa
 y a human would\, and why a CLI with clear command structure and helpful h
 elp text works well for both humans and machines. I'll cover the small gap
 s between how humans and machines read the same text and demo how we lever
 aged existing patterns of CLI design like help text\, examples and flags t
 o combine with new AI patterns and tool-chains. I'll demo the end result\,
  the kubectl-mtv MCP browsing\, planning\, and running VM migrations throu
 gh OpenShift Lightspeed.
DTSTAMP:20260430T125720Z
LOCATION:E104 (capacity 72)
SUMMARY:From CLI to MCP in 20 Minutes - Yaacov Zamir
URL:https://pretalx.devconf.info/devconf-cz-2026/talk/SQKC3S/
END:VEVENT
END:VCALENDAR