BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152727Z
LOCATION:Exhibitor Forum\, Exhibit Floor
DTSTART;TZID=America/Los_Angeles:20260727T120000
DTEND;TZID=America/Los_Angeles:20260727T123000
UID:dac_DAC 2026_sess228_EF108@linklings.com
SUMMARY:SIEMENS: Intelligence Between the Runs: Agentic AI for Feedback-Dr
 iven Verification
DESCRIPTION:Abhi Kolpekwar (Siemens)\n\nAs AI/ML SoCs, chiplet-based archi
 tectures, and software-defined systems increase design complexity, verific
 ation is no longer defined only by design size. Increasingly, complexity c
 omes from interaction, iteration, and execution context: how IP blocks, pr
 otocols, power states, software, and workloads behave when composed into a
  system. As a result, verification has become a feedback-driven process in
  which each run can reshape intent, change priorities, expose new assumpti
 ons, and determine what must happen next.\n\nMuch of today’s verification 
 effort now lives both within the tools and between the runs: planning, sta
 tic analysis, triage, interpretation, debug, coverage analysis, and re-ste
 ering. AI-enhanced verification engines can accelerate specific tasks, whi
 le agentic AI can help connect those tasks into context-aware workflows th
 at are easier to guide, analyze, and close. Together, these approaches bri
 ng intelligence not only to individual verification engines, but also to t
 he engineering decisions that connect them.\n\n\nRather than treating AI a
 s a chatbot or isolated code generator, agentic verification connects desi
 gn intent, verification plans, RTL, testbenches, assertions, coverage, log
 s, waveforms, and engine results so AI can help engineers plan, execute, a
 nalyze, and refine verification tasks under human-defined governance. The 
 session will examine the foundations required for trusted AI-driven flows,
  including domain-scoped agents, tool-aware context, persistent verificati
 on knowledge, traceability from recommendation to evidence, and orchestrat
 ion across simulation, formal, emulation, and hardware-assisted validation
 .\n\nAttendees will leave with a framework for identifying where AI can de
 liver near-term productivity gains inside verification tools, where agenti
 c workflows can reduce friction across iterations, and how engineering jud
 gment remains central to trusted signoff.\n\n
END:VEVENT
END:VCALENDAR