BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-cz-2026//talk//8GLDTE
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-2026-8GLDTE@pretalx.devconf.info
DTSTART;TZID=CET:20260618T101500
DTEND;TZID=CET:20260618T105000
DESCRIPTION:As open-source projects grow\, governance becomes a bottleneck.
  Tracking enhancement proposals across repositories\, enforcing deadlines\
 , ensuring process compliance - these don't scale with volunteer maintaine
 rs.\n\nEnter the VEP Police Agent - an AI agent built with LangGraph\, MCP
 \, and LLMs for KubeVirt\, a CNCF project for running VMs on Kubernetes. I
 t autonomously monitors the enhancement proposal lifecycle: discovering pr
 oposals across GitHub\, tracking compliance in parallel\, performing cross
 -domain risk analysis\, and delivering prioritized alerts via Slack and em
 ail.\n\nWe'll dive into the architecture: a LangGraph state machine with p
 arallel nodes\, a two-tier LLM strategy (fast models for MCP tool-calling\
 , powerful models for reasoning)\, and phase-aware analysis that keeps ale
 rts context-sensitive. A live demo will show the agent catching real gover
 nance issues in real time.\n\nWhile built for KubeVirt\, the patterns appl
 y to any project facing governance growing pains.
DTSTAMP:20260430T125128Z
LOCATION:D105 (capacity 300)
SUMMARY:The VEP Police: An AI Agent That Governs an Open-Source Project - I
 tamar Holder\, Vladik Romanovsky
URL:https://pretalx.devconf.info/devconf-cz-2026/talk/8GLDTE/
END:VEVENT
END:VCALENDAR