BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern 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:20260323T123541Z UID:44FB28BC-B24D-4792-80CA-8B1F69E8FA9C DTSTART;TZID=US/Eastern:20260317T190000 DTEND;TZID=US/Eastern:20260317T200000 DESCRIPTION:IEA: A Test Data Analytic Platform via Natural-Language-to-Code \n\nThe Intelligent Engineering Assistant (IEA) was first introduced in 20 18 as an early attempt to apply AI-driven automation to post-silicon test engineering. Since then\, the rapid evolution of Large Language Models (LL Ms) has profoundly shaped IEA’s trajectory. With each new generation of LLMs offering stronger reasoning and programming capabilities\, IEA has un dergone fundamental architectural redesigns to take advantage of these adv ances. In 2025\, IEA is re-architected once again—this time to leverage the emerging power of high-quality code generation as a central mechanism for engineering productivity. Over the past five months\, we deployed the latest IEA in an industrial environment. This deployment has transformed I EA from a research concept into a production-grade platform that measurabl y improves productivity and promotes broad cross-team collaboration. The 2 025 IEA introduces a strengthened grounding strategy that aligns natural-l anguage prompts with real engineering context. The system performs dynamic grounding using data tables\, enabling IEA to interpret intent with direc t access to datasets. Building on these capabilities\, IEA automatically g enerates analytic Python code tailored to user prompts\, allowing engineer s to rapidly validate hypotheses and iterate on workflows. Drawing from ou r deployment experience\, we discuss observed shifts in engineering practi ce\, the architectural insights gained throughout IEA’s evolution\, and lessons learned from integrating LLM-based automation into complex industr ial environments.\n\nCo-sponsored by: IEEE Future Networks AI/ML Working G roup\n\nSpeaker(s): Professor Li-C. Wang\n\nAgenda: \nWEBINAR: 7:00 - 8:00 P.M.\n\nThe Zoom Webinar link and password will be forwarded to all regis tered participants after Noon on the day of the meeting. Check your spam f older if you don't see the email.\n\nWebinar is open to all.\n\nPDH certif icates are available and an evaluation form will be emailed to you after t he meeting. PDH certificate are sent by IEEE USA 3-4 weeks after the meeti ng.\n\nVirtual: https://events.vtools.ieee.org/m/538618 LOCATION:Virtual: https://events.vtools.ieee.org/m/538618 ORGANIZER:ieee@gpamg.org SEQUENCE:23 SUMMARY:IEA: A Test Data Analytic Platform via Natural-Language-to-Code URL;VALUE=URI:https://events.vtools.ieee.org/m/538618 X-ALT-DESC:Description: <br /><p class="MsoNormal"><strong>IEA: A Test Data Analytic Platform via Natural-Language-to-Code</strong></p>\n<p class="Ms oNormal" style="line-height: 1.5\;">The Intelligent Engineering Assistant (IEA) was first introduced in 2018 as an early attempt to apply AI-driven automation to post-silicon test engineering. Since then\, the rapid evolut ion of Large Language Models (LLMs) has profoundly shaped IEA&rsquo\;s tra jectory. With each new generation of LLMs offering stronger reasoning and programming capabilities\, IEA has undergone fundamental architectural red esigns to take advantage of these advances. In 2025\, IEA is re-architecte d once again&mdash\;this time to leverage the emerging power of high-quali ty code generation as a central mechanism for engineering productivity. &n bsp\;Over the past five months\, we deployed the latest IEA in an industri al environment. This deployment has transformed IEA from a research concep t into a production-grade platform that measurably improves productivity a nd promotes broad cross-team collaboration. The 2025 IEA introduces a stre ngthened grounding strategy that aligns natural-language prompts with real engineering context. The system performs dynamic grounding using data tab les\, enabling IEA to interpret intent with direct access to datasets. Bui lding on these capabilities\, IEA automatically generates analytic Python code tailored to user prompts\, allowing engineers to rapidly validate hyp otheses and iterate on workflows. &nbsp\;Drawing from our deployment exper ience\, we discuss observed shifts in engineering practice\, the architect ural insights gained throughout IEA&rsquo\;s evolution\, and lessons learn ed from integrating LLM-based automation into complex industrial environme nts.</p><br /><br />Agenda: <br /><p><strong>WEBINAR:</strong>&nbsp\;7:00 - 8:00 P.M.&nbsp\;</p>\n<p>The Zoom Webinar link and password will be forw arded to all registered participants after Noon on the day of the meeting. <strong>Check your spam folder if you don't see the email.&nbsp\;</strong ></p>\n<p>Webinar is open to all.</p>\n<p>PDH certificates are available a nd an evaluation form will be emailed to you after the meeting. PDH certif icate are sent by IEEE USA 3-4 weeks after the meeting.</p> END:VEVENT END:VCALENDAR