BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:edbc0af7d170a4ea97822cf47b945c7a
CATEGORIES:Public Event
CREATED:20260422T161301
SUMMARY:AI Meet Up & Exchange
LOCATION:TBD
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:<p>Presenter:&nbsp;<span>Matt Houseman and Michael Emerick</span></p><div c
 lass="wDYxhc" role="presentation" data-attrid="kc:/location/location:addres
 s" data-md="1002" data-hveid="CDQQAA" data-ved="2ahUKEwiLx9Wv7IGUAxWqFmIAHU
 8HNnQQkCl6BAg0EAA"><div class="Z1hOCe"><div class="zloOqf PZPZlf" data-dtyp
 e="d3ifr" data-local-attribute="d3adr" data-mid="/g/11dymnnrkn" data-ved="2
 ahUKEwiLx9Wv7IGUAxWqFmIAHU8HNnQQghwoAHoECDQQAQ"><span class="LrzXr"></span>
 </div></div></div><div class="R6qwef" data-hveid="CEoQAA" data-ved="2ahUKEw
 iLx9Wv7IGUAxWqFmIAHU8HNnQQ6rYMegQIShAA"></div><p><strong>Topic: Managing th
 e "Messy" Parts of AI Development</strong></p><p>For the May session, we’re
  planning to do a deep dive into what it actually looks like to build a too
 l using AI as a teammate.&nbsp;Most people use AI to write snippets of code
 , but we’ve been working on a framework, using&nbsp;Agentic AI&nbsp;and&nbs
 p;Microsoft Copilot<strong>,&nbsp;</strong>to manage the entire lifecycle o
 f a project while keeping things clean and controlled.</p><p><strong>The Pr
 oject: From Unstructured Data to Actual Insights</strong></p><p>We’ll be us
 ing a tool we built as our case study: an application that takes a pile of 
 unstructured invoices and turns them into organized data and spend observat
 ions.</p><p>Instead of just showing the finished product, we want to walk t
 hrough how it actually came together in less than two hours:</p><ul><li><st
 rong>The Blueprint:</strong>How we used "Procedural Guidelines" to keep the
  AI from going off the rails during the roadmap and technical design phases
 .</li><li><strong>The Workflow:</strong>A look at how we move from a high-l
 evel problem into specific user stories and prompts.</li><li><strong>Being 
 Honest About Bugs:</strong>We’ll show the points where the AI tripped up—li
 ke a side-nav bar overlapping the content or multi-file upload glitches—and
  how we used those moments to refine our prompts and fix the code live.</li
 ></ul><p><strong>Let’s Build Something Live</strong></p><p>Once we’ve shown
  the "how-to," we want to hand the keys to the audience. We’re planning to:
 </p><ul><li><strong>Take a live request:</strong>We'll ask the group for a 
 new feature or an "edge case"—maybe something like predicting future spend 
 or flagging duplicate payments—and try to implement it on the spot using th
 e framework.</li><li><strong>Brainstorming Other Workflows:</strong>This ap
 proach isn't just for developers. We want to hear what kind of "messy" manu
 al processes the group is dealing with in their own roles so we can talk th
 rough how to apply this same structured AI approach to solve them.</li></ul
 ><p>Our goal is for everyone to walk away with a practical mental model of 
 how to use AI as a reliable, predictable collaborator for any complex proje
 ct.</p>
DTSTAMP:20260430T003504Z
DTSTART:20260527T173000Z
DTEND:20260527T193000Z
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR