BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.28.0//EN
X-ORIGINAL-URL:https://osmc.de/
X-WR-CALNAME:OSMC
X-WR-CALDESC:Open Source Monitoring Conference
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T030000
RRULE:FREQ=YEARLY;BYMONTH=03;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=4SU
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-43675d9e95fa6fcff3217c6429c3e4cb@osmc.de
DTSTART;TZID=Europe/Berlin:20261118T080000
DTEND;TZID=Europe/Berlin:20261119T180000
DTSTAMP:20260615T133336Z
CREATED:20260615
LAST-MODIFIED:20260615
PRIORITY:5
SEQUENCE:1
TRANSP:OPAQUE
SUMMARY:When incidents fix themselves: AI SRE
DESCRIPTION:The next evolution of incident response isn’t about faster alerts, but what happens after alerts fire: autonomous and semi-autonomous resolution. In this session, ilert CEO Birol Yildiz unveils how AI SRE agents build on modern monitoring and observability systems to diagnose and remediate outages before anyone gets paged, moving along a spectrum from assisted decision-making to full autonomy. Modern incident response is no longer binary. Teams are beginning with semi-autonomous systems that investigate issues, correlate signals across monitoring tools, suggest actions, and support engineers under pressure, and gradually progressing toward autonomous agents that can, in some cases, identify root causes and execute fixes end to end. Through live scenarios, we bring the AI SRE agent to life. You’ll see how it combines observability data, deployment context, and monitoring signals to detect, understand, and resolve incidents in real time. We’ll demonstrate both modes in practice: how the system collaborates with engineers when human input is required, and how it operates independently when confidence is high. Beyond automation, this talk explores the risks and security implications of exposing AI to production environments and introduces a pragmatic three-stage adoption strategy for DevOps and SRE teams. We’ll also share practical lessons from real-world monitoring environments, including how to define safe execution boundaries and avoid common pitfalls when introducing automation into critical systems. Attendees will leave with a clear, actionable roadmap to extend their monitoring systems beyond visibility, toward faster and safer incident resolution, balancing autonomy, control, and trust.\n
URL:https://osmc.de/talks/when-incidents-fix-themselves-ai-sre/
END:VEVENT
END:VCALENDAR