BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//sf26-agenda//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:SESS-225@sf26-agenda
DTSTAMP:20261103T091709Z
DTSTART:20261104T231500Z
DTEND:20261105T000000Z
SUMMARY:From Alerts to Autonomy: Advancing the Maturity Curve with Agentic 
 Managed Streaming Platforms
LOCATION:Room 2010
DESCRIPTION:Bobby Calderwood\, Andrew Lee\n\nDouble the number of jobs on a
  multi-tenant stream processing platform\, and you'll more than double the
  alerts\, false positives\, and real incidents your team must triage. Sign
 al and noise both grow super-linearly with scale\, consuming an ever-large
 r scale of the platform team’s bandwidth. Applying AI at the right point
 s can bring that support growth curve back toward linear. At JPMorgan Chas
 e\, a small platform team supports thousands of user-submitted Flink jobs 
 processing more than 100 billion events per month. In this talk\, we share
  the three-stage agentic support maturity curve that made this possible\, 
 and how you can apply it to your own platform: Amplify the signals that ma
 tter. Learn AI/ML techniques can enrich platform telemetry and filter out 
 alert noise so real problems stand out. Human-initiated\, AI-assisted diag
 nosis and remediation. See how correlating logs\, metrics\, and historical
  metadata with point-in-time state provides the context an agent needs to 
 help engineers find root causes and fixes faster. Agent-initiated diagnosi
 s and remediation. Discover how agents can resolve routine issues on their
  own\, keep the right people informed\, and bring in humans only when nece
 ssary. You'll leave this session with a practical blueprint for making sup
 port scale with your platform usage instead of outrunning it.
URL:https://sf26.rmoff.net/s/from-alerts-to-autonomy-advancing-the-maturity
 -curve-with-225
END:VEVENT
END:VCALENDAR