BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-cz-2026//speaker//B7PBWB
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-2026-9M8LKX@pretalx.devconf.info
DTSTART;TZID=CET:20260619T105500
DTEND;TZID=CET:20260619T111000
DESCRIPTION:Kubernetes troubleshooting means kubectl logs\, describe\, get 
 events... repeated endlessly. What if an AI agent could diagnose your brok
 en HTTPRoute\, trace\n  multi-hop connection failures\, and explain perfor
 mance issues—autonomously?\n  This demo shows kagent\, an open-source fr
 amework running AI agents natively in Kubernetes. Watch an agent diagnose 
 a real production issue using A2A\n  protocol\, MCP tools\, and full obser
 vability. You'll leave with a working example to deploy in your cluster.\n
   Everyone managing Kubernetes has faced:\n  - 3 AM incidents requiring co
 rrelation across logs\, events\, and metrics\n  - Gateway/Ingress misconfi
 gurations that take hours to diagnose\n  - Performance degradation requiri
 ng expertise across networking\, storage\, and compute\n\n kagent demonstr
 ates the future: AI agents that live in your cluster\, using standard prot
 ocols (Agent2Agent\, MCP) to autonomously troubleshoot and remediate\n  is
 sues.
DTSTAMP:20260430T115105Z
LOCATION:A113 (capacity 64)
SUMMARY:AI Agents for Kubernetes - S Venkatesh [ VENKATESH SIVATHANU PILLAI
  ]
URL:https://pretalx.devconf.info/devconf-cz-2026/talk/9M8LKX/
END:VEVENT
END:VCALENDAR