BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260804T204606Z
UID:BA22BDFB-CF12-41D1-964F-C9222407F050
DTSTART;TZID=America/New_York:20260816T140000
DTEND;TZID=America/New_York:20260816T144000
DESCRIPTION:AI agents can reason\, plan\, search for information\, and use 
 tools. But intelligence alone is not enough. To make good decisions\, an a
 gent must understand the enterprise around it: what business terms mean\, 
 how people\, data\, applications\, and systems are connected\, where relev
 ant information is stored\, what is happening at that moment\, and which a
 ctions are permitted.\n\nIn this talk\, we will use a city-building analog
 y to explain how organizations can prepare their enterprises for reliable 
 AI agents. Taxonomy creates a shared language\, ontology defines meaning a
 nd relationships\, knowledge graphs connect enterprise information\, RAG h
 elps retrieve relevant knowledge\, and context graphs provide current info
 rmation such as identity\, risk\, approvals\, time\, location\, and system
  state.\n\nThe session will also explain why being able to access a system
  does not automatically give an agent permission to perform every action. 
 AI agents need both a clear map and appropriate rules\, boundaries\, and c
 ontrols before they can operate safely.\n\nThe key message is simple: befo
 re giving AI agents more intelligence\, organizations must build an enterp
 rise environment that agents can understand\, navigate\, and trust.\n\nSpe
 aker(s): \, Phani \n\nVirtual: https://events.vtools.ieee.org/m/571282
LOCATION:Virtual: https://events.vtools.ieee.org/m/571282
ORGANIZER:nxsvks@rit.edu
SEQUENCE:20
SUMMARY:Before You Give AI Agents a Map\, You Have to Build the City
URL;VALUE=URI:https://events.vtools.ieee.org/m/571282
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;gmail-pdq2pgselectionanchorcontaine
 r&quot;&gt;AI agents can reason\, plan\, search for information\, and use tools. B
 ut intelligence alone is not enough. To make good decisions\, an agent mus
 t understand the enterprise around it: what business terms mean\, how peop
 le\, data\, applications\, and systems are connected\, where relevant info
 rmation is stored\, what is happening at that moment\, and which actions a
 re permitted.&lt;/p&gt;\n&lt;p&gt;In this talk\, we will use a city-building analogy t
 o explain how organizations can prepare their enterprises for reliable AI 
 agents. Taxonomy creates a shared language\, ontology defines meaning and 
 relationships\, knowledge graphs connect enterprise information\, RAG help
 s retrieve relevant knowledge\, and context graphs provide current informa
 tion such as identity\, risk\, approvals\, time\, location\, and system st
 ate.&lt;/p&gt;\n&lt;p&gt;The session will also explain why being able to access a syst
 em does not automatically give an agent permission to perform every action
 . AI agents need both a clear map and appropriate rules\, boundaries\, and
  controls before they can operate safely.&lt;/p&gt;\n&lt;p&gt;The key message is simpl
 e: before giving AI agents more intelligence\, organizations must build an
  enterprise environment that agents can understand\, navigate\, and trust.
 &lt;/p&gt;
END:VEVENT
END:VCALENDAR