BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2025//talk//F7RDPT
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20240423T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T030000
RDATE:20251026T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T030000
RDATE:20260329T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Building Reliable AI Agents for Publishing: A DSPy-Based Quality A
 ssurance Framework - Simonas Černiauskas
DTSTART;TZID=Europe/Berlin:20250423T151000
DTEND;TZID=Europe/Berlin:20250423T154000
DTSTAMP:20261009T073509Z
UID:pretalx-pyconde-pydata-2025-F7RDPT@pretalx.com
DESCRIPTION:As publishers increasingly adopt AI agents for content generat
 ion and analysis\, ensuring output quality and reliability becomes critica
 l. This talk introduces a novel quality assurance framework built with DSP
 y that addresses the unique challenges of evaluating AI agents in publishi
 ng workflows. Using real-world examples from newsroom implementations\, I 
 will demonstrate how to design and implement systematic testing pipelines 
 that verify factual accuracy\, content consistency\, and compliance with e
 ditorial standards. Attendees will learn practical techniques for building
  reliable agent evaluation systems that go beyond simple metrics to ensure
  AI-generated content meets professional publishing standards.
LOCATION:Palladium
URL:https://pretalx.com/pyconde-pydata-2025/talk/F7RDPT/
END:VEVENT
END:VCALENDAR