BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.devopsdays.org//dodroxrox26//talk//Z8DCQ8
BEGIN:VTIMEZONE
TZID:US/Mountain
BEGIN:DAYLIGHT
DTSTART:20250922T000000
TZNAME:MDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0600
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T020000
RDATE:20261101T020000
TZNAME:MST
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RDATE:20270314T030000
TZNAME:MDT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Your CI/CD Pipeline Is About to Meet AI — Here's What It Doesn't
  Know - Saideep Navakoti
DTSTART;TZID=US/Mountain:20260922T114500
DTEND;TZID=US/Mountain:20260922T115000
DTSTAMP:20260729T051031Z
UID:pretalx-dodroxrox26-Z8DCQ8@talks.devopsdays.org
DESCRIPTION:I've built banking pipelines for 10 years. My company just tol
 d me we're deploying AI agents. I started researching what changes — and
  found 5 things my pipeline has no answer for:\n\n1. "Build passed" — bu
 t the model wasn't tested against this week's data\n2. "Health check passe
 d" — but "up" doesn't mean "correct" for AI\n3. "Deployment successful" 
 — but which version: the code\, the model\, or the context?\n4. "Cost no
 rmal" — but token costs don't appear in your cloud bill like compute doe
 s\n5. "No alerts" — but the AI failed silently because nobody defined wh
 at "wrong" looks like\n\n5 failure modes that your current pipeline has no
  answer for. 5 slides each. 5 minutes. Drawn from production failures docu
 mented in public post-mortems and infrastructure gap analysis from 10 year
 s of banking deployments.
LOCATION:Main Stage
URL:https://talks.devopsdays.org/dodroxrox26/talk/Z8DCQ8/
END:VEVENT
END:VCALENDAR