BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.devopsdays.org//devopsdays-austin-2026//speaker//V
 UJX3Y
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-devopsdays-austin-2026-N78MAJ@talks.devopsdays.org
DTSTART;TZID=CST:20260506T104000
DTEND;TZID=CST:20260506T110000
DESCRIPTION:Coding agents are already committing code\, opening pull reques
 ts\, and pushing features into production across modern development workfl
 ows. AI coding tools promise velocity\, but introduce a repeatable class o
 f security failures that evade traditional detection. This talk examines t
 he systemic risks quietly propagating across codebases and draws on findin
 gs from multiple studies\, including original research conducted at DryRun
  Security using real development workflows. Across this body of work\, con
 sistent failure patterns emerge regardless of model\, framework\, or appli
 cation design\, revealing structural weaknesses rather than isolated mista
 kes.\n\nThese failures stem from how coding agents construct software. The
 y optimize for functional correctness along the happy path and lack a cohe
 rent understanding of how security controls must persist and evolve across
  the lifecycle of an application. Protections applied early are not reliab
 ly enforced as new features are introduced\, and security assumptions erod
 e across successive modifications. This talk distills the practical princi
 ples leading AI-driven engineering teams are using to close these gaps\, w
 ith an emphasis on verification models and practices.
DTSTAMP:20260430T173058Z
LOCATION:Ballroom
SUMMARY:The Systemic (Security) Failures of AI-Built Software - James Wicke
 tt
URL:https://talks.devopsdays.org/devopsdays-austin-2026/talk/N78MAJ/
END:VEVENT
END:VCALENDAR