BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//speaker//9C3PL3
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-VYLDCR@pretalx.devconf.info
DTSTART;TZID=EST:20260924T153500
DTEND;TZID=EST:20260924T155000
DESCRIPTION:AI agent platforms let LLMs execute code\, call APIs\, and acce
 ss tools — which makes them a security nightmare if left unguarded. This
  talk covers how I built a defense-in-depth security stack for OpenClaw\, 
 an open-source AI agent gateway running on OpenShift. I'll walk through th
 e 10 layers — from NeMo Guardrails input/output filtering and TrustyAI P
 II detection\, to AdminNetworkPolicy egress control\, OVN EgressFirewall D
 NS allowlisting\, per-session agent sandboxing with OpenShell\, and MLflow
 -based observability — all deployed without cluster-admin access. Expect
  real tradeoffs: wildcard DNS rules that silently fail\, OTLP ports blocke
 d by your own policies\, guardrails that return the wrong response format\
 , and why documenting dead ends became one of the project's most valuable 
 outputs.
DTSTAMP:20260823T232150Z
LOCATION:106 (Capacity 45)
SUMMARY:10 Layers Deep: Securing an AI Agent Gateway on Kubernetes - Suhrut
 h Vuppala
URL:https://pretalx.devconf.info/devconf-us-2026/talk/VYLDCR/
END:VEVENT
END:VCALENDAR