BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME:BrightTALK Event
PRODID:-//BrightTALK//NONSGML BrightTALK Event Calendar//EN
CALSCALE:GREGORIAN
METHOD:REQUEST
BEGIN:VEVENT
UID:https://www.brighttalk.com/webcast/9273/664192
DTSTAMP:20260613T152829Z
ORGANIZER:MAILTO:noreply@brighttalk.com
LOCATION:BrightTALK
URL:https://www.brighttalk.com/webcast/9273/664192?utm_campaign=commun
 ication_reminder_24hr_registrants&utm_medium=calendar&utm_source=brigh
 ttalk-transact
DTSTART:20260616T170000Z
DTEND:20260616T180000Z
SUMMARY:Live webcast: Structured Prompting 2.0: What the Research Actu
 ally Says
DESCRIPTION:Click here to attend: https://www.brighttalk.com/webcast/9
 273/664192?utm_campaign=communication_reminder_24hr_registrants&utm_me
 dium=calendar&utm_source=brighttalk-transact\n\nPresenter: Presenter: 
 Lance Cummings, PhD. > Host: Scott Abel\n\nPrompt engineering advice i
 s everywhere. Ask AI to act as an expert. Add chain-of-thought instruc
 tions. Include examples. Write longer prompts. But which techniques co
 nsistently improve results, and which are supported more by anecdotes 
 than evidence?\n\nJoin Professor and trainer Lance Cummings of the Uni
 versity of North Carolina Wilmington for a research-based look at how 
 prompting practices are evolving and what tech writers need to know as
  generative AI use expands.\n\nLance explores a shift already underway
 : the move from crafting prompts to designing information environments
 . You'll learn why content structure, information architecture, and co
 ntent type increasingly matter more than prompt wording, and why tech 
 writers are uniquely qualified to guide this transition.\n\nDrawing on
  current research and lessons learned from a real-world disaster commu
 nication chatbot project, Lance will examine the strengths and limitat
 ions of popular techniques, including role and chain-of-thought prompt
 ing, few-shot examples, and prompt length. He'll also explain why usin
 g AI to evaluate AI-generated content creates reliability problems and
  what a defensible testing process looks like.\n\nYou'll learn:\n\n* W
 hat research reveals about prompting\n* Why telling AI to act like an 
 expert changes style more than accuracy\n* How information types such 
 as task, concept, reference, principle, and process improve prompts, s
 ystem instructions, and agent behavior\n* Why AI-generated evaluation 
 is often unreliable and how to build a testing approach\n* How to appl
 y a repeatable rubric for assessing AI output quality\n\nCan't make it
 ? Register and we'll send you a link to watch the recording at your co
 nvenience.\n\nThis presentation is brought to you by The Content Wrang
 ler and sponsored by Heretto, a powerful component content management 
 (CCMS) system and content operations platform to deploy help and API d
 ocs in a single portal designed to delight customers.
SEQUENCE:1781542027
END:VEVENT
END:VCALENDAR