BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Superpower Daily//AI Events//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Superpower Daily AI events
BEGIN:VEVENT
UID:b1a29e8b-28de-4081-a700-35c8bf4e8e31@superpowerdaily.com
DTSTAMP:20261027T140356Z
LAST-MODIFIED:20261027T140356Z
DTSTART:20261028T010000Z
DTEND:20261028T020000Z
SUMMARY:Steering Agents with Policies: an engineering session
DESCRIPTION:Nikita Agarwal\, co-founder and CEO of Failproof AI and co-auth
 or of the FIRE paper\, will share practical ways to turn agent failure tra
 ces into runtime policies that improve reliability without retraining. The
  engineering session will cover when to allow\, deny\, or instruct agents\
 , common policy pitfalls\, and a live example of writing and testing a pol
 icy.\nDetails: https://superpowerdaily.com/events/steering-agents-with-pol
 icies-an-engineering-session-b1a29e8b-28de-4081-a700-35c8bf4e8e31\nRegiste
 r: https://luma.com/z4rk34s4
LOCATION:San Francisco\, CA\, San Francisco\, CA
URL:https://superpowerdaily.com/events/steering-agents-with-policies-an-eng
 ineering-session-b1a29e8b-28de-4081-a700-35c8bf4e8e31
STATUS:TENTATIVE
TRANSP:TRANSPARENT
END:VEVENT
END:VCALENDAR