BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//speaker//TYFEH8
BEGIN:VTIMEZONE
TZID:EST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T070000Z
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T080000Z
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-devconf-us-2026-P9W73V@pretalx.devconf.info
DTSTART;TZID=EST:20260924T152000
DTEND;TZID=EST:20260924T153500
DESCRIPTION:As AI development moves toward agents that operate on real syst
 ems\, data context becomes critical. Agents need to understand how data mo
 ves\, recognize incorrect pipeline results\, and take trusted action.\n\nI
 n this session\, I will show how I built a data agent on Red Hat OpenShift
  AI using Apache Spark through the Kubeflow Spark Operator. An enriched co
 ntext layer and MCP tools connect the agent to the data pipeline and its r
 untime.\n\nThe demo shows the agent detecting a broken Spark pipeline and 
 using a diagnose-repair-validate loop to prepare a verified fix for human 
 review. The goal is to show how users can build and scale their own in-hou
 se data agents on RHOAI and bring the agentic development lifecycle to ent
 erprise data pipelines.
DTSTAMP:20260823T232100Z
LOCATION:106 (Capacity 45)
SUMMARY:Building In-House Data Agents on RHOAI - Sahana Sreeram
URL:https://pretalx.devconf.info/devconf-us-2026/talk/P9W73V/
END:VEVENT
END:VCALENDAR