BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Chicago BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260824T191959Z UID:D6F3E166-89ED-4DE0-B906-E64CFD36BEA7 DTSTART;TZID=America/Chicago:20260820T183000 DTEND;TZID=America/Chicago:20260820T200000 DESCRIPTION:AI agents are starting to do more than answer questions. They c an search systems\, choose tools\, update records\, trigger workflows\, an d make changes in business applications.\n\nOnce an agent can take action\ , it should be treated like a system identity. It needs its own identity\, a clear owner\, limited permissions\, and rules that control what it can do.\n\nThis talk uses a simple employee-badge analogy to explain the idea. An agent is like an employee or contractor\, and its identity is the badg e. Least privilege means the badge opens only the doors needed for the job . Bounded access means it works only in the right building\, on the right floor\, for the right task\, and for a limited time.\n\nThe session also e xplains why every action should be checked at runtime\, why the target sys tem must still protect its own resources\, why access should be short-live d\, and why every agent action needs a clear audit trail.\n\nAttendees wil l leave with a practical way to think about AI agent security: treat the a gent as an identity\, limit its authority\, and check every action before it reaches an enterprise system.\n\nSpeaker(s): Venkata Patelkhana\n\nAge nda: \n6:25 to 6:35 PM - Open for participants to enter and network.\n6:35 to 6:40 PM - IEEE LM and CTCN Business meeting and to introduce speaker.\ n6:40 to 7:55PM - Formal Program and Q&A.\n\nVirtual: https://events.vtool s.ieee.org/m/571370 LOCATION:Virtual: https://events.vtools.ieee.org/m/571370 ORGANIZER:bill.martino@ieee.org, uday.kanike@ieee.org SEQUENCE:20 SUMMARY:IEEE CTS CTCN/LMAG Zoom Meeting\, 8-20-2026\, "The Agent Is an Iden tity: Why AI Agents Need Least Privilege\, Limited Access\, and Runtime Ch ecks" URL;VALUE=URI:https://events.vtools.ieee.org/m/571370 X-ALT-DESC:Description: <br /><p>AI agents are starting to do more than ans wer questions. They can search systems\, choose tools\, update records\, t rigger workflows\, and make changes in business applications.</p>\n<p>Once an agent can take action\, it should be treated like a system identity. I t needs its own identity\, a clear owner\, limited permissions\, and rules that control what it can do.</p>\n<p>This talk uses a simple employee-bad ge analogy to explain the idea. An agent is like an employee or contractor \, and its identity is the badge. Least privilege means the badge opens on ly the doors needed for the job. Bounded access means it works only in the right building\, on the right floor\, for the right task\, and for a limi ted time.</p>\n<p>The session also explains why every action should be che cked at runtime\, why the target system must still protect its own resourc es\, why access should be short-lived\, and why every agent action needs a clear audit trail.</p>\n<p>Attendees will leave with a practical way to t hink about AI agent security: treat the agent as an identity\, limit its a uthority\, and check every action before it reaches an enterprise system.< /p><br /><br />Agenda: <br /><div dir="ltr" data-setdir="false">6:25 to 6: 35 PM - Open for participants to enter and network.&nbsp\;</div>\n<div dir ="ltr" data-setdir="false">6:35 to 6:40 PM - IEEE LM and CTCN Business mee ting and to introduce speaker.</div>\n<div dir="ltr" data-setdir="false">6 :40 to 7:55PM - Formal Program and Q&amp\;A.&nbsp\;</div> END:VEVENT END:VCALENDAR