BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.in.pycon.org//2025//UAD7KN
BEGIN:VTIMEZONE
TZID:IST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:IST
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-2025-UYRYEL@cfp.in.pycon.org
DTSTART;TZID=IST:20250914T145000
DTEND;TZID=IST:20250914T152000
DESCRIPTION:Technical writers spend countless hours manually editing conten
 t to aling with organizational style guides. What if an AI could do it for
  you - accurately and consistently?\n\nIn this talk\, I'll introduce Rapid
 Doc\, an open-source AI model fine-tuned on real-world sofwtare documentat
 ion rules to flag and rewrite violations. For example\, inconsistency in t
 erminologies used\, passive vioce\, ambigguous phrasing. I'll walk through
  how I built a premium dataset\, fine-tuned flan-ts-base model\, and desig
 ned a gradio-based frontend for instant feedback on .md\, .docx\, .adoc\, 
 .pdf files.\n\nExpect\, live demos\, insights into model training challeng
 es\, and a peek on hiw GenAI is reshaping the future of editorial workflow
 s.\n\nWhether you'r an AI practitioner\, a documentation lead\, or a tooli
 ng enthusiast\, this talk offers an edd-to-end blueprint on how I'm fine-t
 uning a model on real-world sofwtare documentation rules.
DTSTAMP:20260317T121351Z
LOCATION:Track 1
SUMMARY:RapidDoc - A Rule-Based Fine-Tuned Model for Enforcing Style Guide 
 Rules - Gaurav Trivedi
URL:https://cfp.in.pycon.org/2025/talk/UYRYEL/
END:VEVENT
END:VCALENDAR