BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//speaker//3VHXXW
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2026-9PBYAP@pretalx.com
DTSTART;TZID=CET:20260416T113500
DTEND;TZID=CET:20260416T122000
DESCRIPTION:AI agents are increasingly deployed with autonomy: calling tool
 s\, accessing data\, modifying systems\, and making decisions without huma
 n supervision. While prompts and guardrails are often presented as safety 
 solutions\, they break down quickly in real-world agentic systems.\n\nIn t
 his talk\, we explore how to enforce safety constraints in AI agents beyon
 d prompting\, using engineering techniques familiar to Python developers a
 nd data engineers. We will examine common failure modes in agentic systems
  such as tool misuse\, goal drift\, and over-permissioning and show how to
  mitigate them using policy layers\, capability boundaries\, and execution
 -time validation.
DTSTAMP:20260412T142007Z
LOCATION:Helium [3rd Floor]
SUMMARY:Securing AI Agentic Systems: Enforcing Safety Constraints in AI Age
 nt - John Robert
URL:https://pretalx.com/pyconde-pydata-2026/talk/9PBYAP/
END:VEVENT
END:VCALENDAR