BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//python-asia-2026//speaker//A39GJW
BEGIN:VTIMEZONE
TZID:PST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:PST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-python-asia-2026-3EU3VA@pretalx.com
DTSTART;TZID=PST:20260321T144500
DTEND;TZID=PST:20260321T151500
DESCRIPTION:This proposal introduces an innovative approach to Python code 
 quality enforcement by combining fixit (a linting framework based on libcs
 t) with generative AI to create custom linters tailored to team-specific c
 oding standards. \n\nTraditional linters like ruff provide general-purpose
  rules but struggle to address organization-specific requirements and codi
 ng conventions. This creates challenges where code review becomes subjecti
 ve and dependent on individual reviewers' knowledge. Our solution leverage
 s AI to generate fixit rules from natural language descriptions\, dramatic
 ally reducing the barrier to creating and maintaining custom linting rules
 .\n\nThe core innovation lies in using libcst's Concrete Syntax Tree (CST)
  representation\, which preserves formatting\, comments\, and whitespace
 —unlike traditional Abstract Syntax Trees (AST). This enables safe\, aut
 omated code transformations that maintain the original code's style while 
 enforcing new standards. By combining AI-assisted rule generation with fix
 it's powerful transformation capabilities\, teams can quickly implement an
 d enforce new coding standards across entire codebases\, eliminating revie
 w subjectivity and accelerating modernization efforts.
DTSTAMP:20260501T070417Z
LOCATION:Teresa Yuchengco Auditorium (Main Hall)
SUMMARY:Fixit linter+AI coding - Naohide Anahara
URL:https://pretalx.com/python-asia-2026/talk/3EU3VA/
END:VEVENT
END:VCALENDAR